From a67a4468c06de85431d6b12ab4290f359630cd53 Mon Sep 17 00:00:00 2001
From: theengineeringworld
 <40331484+theengineeringworld@users.noreply.github.com>
Date: Wed, 26 Sep 2018 15:05:52 +0500
Subject: [PATCH 1/5] Election Poll Dataset

---
 poll-larger.csv | 10001 ++++++++++++++++++++++++++++++++++++++++++++++
 poll.csv        |  1001 +++++
 2 files changed, 11002 insertions(+)
 create mode 100644 poll-larger.csv
 create mode 100644 poll.csv

diff --git a/poll-larger.csv b/poll-larger.csv
new file mode 100644
index 0000000..9bdbee7
--- /dev/null
+++ b/poll-larger.csv
@@ -0,0 +1,10001 @@
+vote
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
diff --git a/poll.csv b/poll.csv
new file mode 100644
index 0000000..f49dcc2
--- /dev/null
+++ b/poll.csv
@@ -0,0 +1,1001 @@
+vote
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown

From 4b72692884b8238cb6265161c02cc7790171dfc5 Mon Sep 17 00:00:00 2001
From: Linagyu Min <siliconmagic@126.com>
Date: Fri, 12 Oct 2018 12:29:36 +0800
Subject: [PATCH 2/5] bootstrap samples in statistics

---
 bootstrap_sample.png                | Bin 0 -> 12371 bytes
 engineering_04_boostraping_match.py |  77 +++++++++++++++++++++
 grades.csv                          | 101 ++++++++++++++++++++++++++++
 3 files changed, 178 insertions(+)
 create mode 100644 bootstrap_sample.png
 create mode 100644 engineering_04_boostraping_match.py
 create mode 100644 grades.csv

diff --git a/bootstrap_sample.png b/bootstrap_sample.png
new file mode 100644
index 0000000000000000000000000000000000000000..51c754970e562dea038cbd4e99bba0b4b8c83660
GIT binary patch
literal 12371
zcmeHt2{@E}+xMj?EmF56WGPD_w2&fcvy83m*+~+kA#0XF>P{PKY(<vryUM-|r5h2l
z?<Uy|Mi|4`-t+3dzvq3{_jupud%xp-zT<dnO3iXz*Zi;l`8$8h`S_})GRt<Z?FfRf
zU{o$^BgiH{1Y!8byak?-Ztfd~AB@fyF}lp~%bWSeBl!O|M-@Y71YxyA|1hK~q}alf
zXIvDox#&3DbaA(IvPN!Ox;WZ9xY*lX=XbMqa<+BA@t=@@-$(gxxwtsWN=p9w8zdZ@
zY$PAXw(UR=egt#*g6`ed)BV1>p{@fPKRTJK_$A`5AG><1ZC~LQY;w|gxM##}>u8_X
zcAepJa{czvM>`cOyxy17`ntk(v7<6raru5D+l(=<sOXuj-F7na$+rmhb_0{)!t89e
z%-gpMn2;16rR}-8EZzCVJ0{rq^cUBLv64}Id2wY#r*x;uuKM>!84#p$|JsxUd@1Cf
zBEpCu$96L8h9{3Po`<KZb|dhPotOUih5wr+x!hxV{s`9Awz<>XH><1b+L;5pO6y@=
z$12|+<&kq!7ZDMe>}>jCWyx5{yF@4FghfW$xpN{&9Ji>LnCk~7jxN)O;>>>XyScf=
z(p<MbdHOWBIC8PfEJsyUH8eU}Jf+pv{Y-TnMgFU<q<qK#{qCZfh+X9wNmbJH1@z&S
zoSm(imX=2Jt<kuQOx-JJCEmGn=K?okb^ZEY4vreWM@T$;c<;etqOY8yiAls}emv`0
zI*ye-AgAuL68`Ei5#0q!|9!iF&DNa(@&DAUnl|{TT>9>n)!Cv+w$I%a)H~|_Qpeh3
zA`$+bdk}`ahZP*zgfbR4gSq=7og1@VoB|D9O3aLYW)~60ub#tAz5M+J>Re7~cvm>a
z?$sG_ocyM{cVicne6WGAfyde5FNOV1X`xQV_#Be%M%B=8EJkbdR0b3BaX-gB*x~yh
zBFqS4v40akg7{f7`@vHW4<eiX6EEPHw(?6I7;qmQi!wH<@N!e#!?0R$TYVGl$d=ts
za3FtUb^qaKF9vEA=8JrqTWXV9=1kH?Zdllb7-6H{1@30%PlW1XEWDSN#gH*r`>IB|
zP=(Jxl}6+)67UP4<!@<yC;*p#@K=PHe~Cq1-m7xXQ%FyBM*Z`|P8CCBcX|;sl<R*`
zs24bpr%#@^jD#78o;s!f`0?YCk#OTYcZylX@epARLe=2x3jH@ppFx@A<YXle5059o
z!3N&mWpi_LE(_yY702b=XWBkJW^1qT^^NvjU-q1OS98NqKh{A2Rw~+G0>O2?y>Rm8
zm#c<`uT<64TqoN^tZi&Eh{OR06CWR9dV0FIxn%hQfi&Nmtf8Z*_$%yNJrk46Cr`GI
zjEpSD<YZ*DhKlHf5(x3Z=jbX=IV3y$nRetk4u15rKMbcZ^`CJ@o<4oLmK-5zp8e_5
z<*<kdawInUM?>)A$1i%PXB>IF7N@lC+<8}5S108*bq&+<-nu?CEG((qizX^BZ<?W>
z)$%#yaQ^k*wila7Sl_sDi$ug56*<1yzJ2?!<7qlh0Cu(gUKfU0m;C&ELgI(}TUQ#)
z^X<a)vrW<x69q>`M<*3F<`vkX>@Yp=t)G4$8p01=Ayfx)rz|bqy**H7I59DSz96jm
z`bb3m2zN+GNJ6pm*yOhl_hCh_25MGT30&OV_*Pd}SAt+pr&vyBuNQZ}T94iK>Yk5=
zDvRaCNmPBi262*a+<T2Ovom<sa>7s__FWR?LyHXeufyxSTgJVbz83Pc`h{Dk#l@Xh
z*jR1~d+}m0%9qyfE+#Infh#mFb(?PKD|V&^`>tL}N=hOK2G=Bf`t-?-tfsCWS~K(`
zuz2?4j<uL8s;YDHom$9IQPGw%kNKVkNf8k(b#?W^!rYvED$_l7Cp=$q9$Zd(Ue<$0
zqe>cU>p$pJA-f>Q=sVuZn+9n7<HpCBi`V4UztU!GZ{2!Z%Gk@~ig=H|30U}iIQACY
zWuN)^dEX)tZzZLN62-&61ah8K;`3d7mtFLIJ7#irZ??6e&-@j>RyPI}n-t%%#^?-x
z|4k$pQ`2Z|9i6b~=&YimA_<%+Y2LG3R9w6rHplRA$2A5v0-iP%8a`Gqpxha4YtExV
zZ8@C9>g@DBDV1TYEL9xO8cys!B1oehI}cDdy))*s|0(3$>TH!KIjb=5&XAI+;|C_2
z175$e8`Ms?*lnz@m3)69HtbePZIB`5anq&?N%Ww(;(i>dx$;zddpp7B^e=a1;eNW;
z6$Q3V?3^^Ow8)V(`Bj%BK*xw5Hm>M3%%xUg<)RyL?Z12_ZdD`spI4ctSUw=Sv&!%I
znBga0-*SmnK2c`i?j_%qUXtutcCV8DQulf?RrJgmLjt-*dwPs+_ZBqB+$48orDtWe
zFZ~$8Tb;u7r6wl}lU@=Cza%9l=E+I#M3CK@P-=}Yk6#iq$ZjL&RAfT~@i@y1kLc5P
zE)o{HZDJ?h)$q11PWQUbe!EaU-zZly6eK5Q*LFnX<*^F{DeommQ{OdeT~m_*R4UX;
zXl!gwnobH@BHHAdPempY8nNe0(Op#HN|y3n_s&MPAc&>p_@-|JAvIlN;|xrQu*jJ+
z-L(9h4O|#)UER<D-wpi8@bD2h#7Ub*T{pLa0WXTY;^oUr9l3VxqSiNWipt3ucXxNw
zyPJHHJI%ZrXx;!VP!!aW2y?qHFOPf9e%Pva_3AeouL9J%<6ajE!`a^G)36cpEvp{p
zX4}ku`(RY;G{RYP<K|7fq3S@>bXFiuZA|@p&I3j-i2v6C`+q<251Jcnuzl?86Ln%a
zy7u;&zp$~n){7V3q70P#SOI!bXRBDTwa*W79kcMm5tnb`mq#LetakCpCPv{(Fq^mR
z{QCUhB`N1ob!lno<-qQ@miLu{d9%jHZ<)F@D|-I;jbp`o1x`G*&xOIU>LE+yajS>0
z33ZK((sfcaMPQpysZ`?e+?x&P_RI66+THHS!_)-xb+)DHwD<KL#n|C+9f2|fsdTz0
z`cj5LPDf8ZR@!UPo+P{L!09+{T+sysb9}zrRM#72KD;jM$ToPxW?}=J_TFBg8YyBD
z5{pr0MDJqwa(ZTF+1Tu2CBS@7_$t&MY|capIXgr!%cNKvSdu5DoE8c|4n>HkPo$)0
zX6mY{J`tRFWfRl9Fwsi=#CGL~goLIfaVh@cE}nG7r~5F3hpc?r)4he*5B^LgYm2>`
zOPk@;41dvD)ChI;^&?bIz`1Ge5NLYOp6x_i$eA-|&=zvy#0hWcEly5OZCzcdb8}7_
zF=q{p3+#UwEBC&PF!wPu%Q4VQ$u$)Z3=Fihw_nicY;VU9fCHA9IZ$r9NZMwI?8ok~
zIoM4b-Ir$WLUxxUFM5tF$S<e{Ip_Qqj-r(PUc!pkexQk$Nd9LLqwpj^-?h~-1p|O<
z!OufKj);n?-rvG9#~l?K3O!_qJ0vu8n6?^s;r?EBcGv3T7z{?%bux4p-?_};;bAu_
zJZn2p<}p1Q5gK|#SU7owyQc;!d|Kjz%E3<B3$>(RF(JJk{fn2K6Ow&4?yk{)kyb7$
zDGTzW$uraU?YxNdWo26^_u}H>nv(e7c7X@s^Bg~jpZk2cC(pLku*N7{D4=REYW>HM
zGmn*_eoDP6+T~Eph|12$(6O^if1jJn&cWf{!L_-8Oij<r)742<pO}3lOjlA_?9bIP
ziV^Ey$sTUZ%Lz*MoCxU%00`4=^K&+9`^)8Mb=%T(1K2R1&yr<1wZpil=uUz}(YH+`
z@50_Jz~lC|wj~~>%<SxrpD0~`>z^znMn-aZl$(*X6bgH%<+zrHTrVpri5@)orYh1z
zBElqlQCaY{rp?ujO<TP1gQAIa-sUTIXS(VAjgeV=X1x<GZW-Zzi}Kg#`xr0U`LYVY
zGK?GUHe<3k4CjSKDF0E-P46YGC+Fo!Rg5VI^8&@6aPKNjPgez)o@1)a%se{Xldq<y
zr$;<4BqZciY{Dh)ndk6jBA`)CRaNTdm;G*N>*)9oTgP5LzMPer(kr<(O&u$giX4z4
z;|3M<uoEXw;tiN=Y;3Tf9_@im+Zx0px3IoK!8X1=16_m`osR!@Z|lNu9OkLONPvSi
z`>u8RP5`iXyguV>-|Gf|exA7mDZ26bm-dbhyOu<Zs;1^5KFct-T4ogbRl9g$U%VWp
zOovTa{i?e9v-L6Gb>%&K_7D;uJz_40`gsx*)bU^&o6A_V`((H=t{HftH(5nZtrb3$
zz<O@!JQPIn`cjR;Wbs(ckbnh(obTFELPH8nAKejdZf-UzyZdgRq*>p@%Qu$-CUbn(
z$ef)g?|i?EU;R;In!N}5Na(*_A9<Wtic}s^7E5|4;AYS~Fo<_EK!Eyh;@^!v`G*c_
zId1c8Z-|9EJK~4%Bb)BEI3`N3{;q-g+w(X=_*vBROSdEEk=@9>^V~m$Prn{$w`xUx
zK&1bqviYBElrQ6U`f<zP+B9VP6GKDyf>bVF9*y#8x&jnsS3ng7+gEhwzucCn%Zotu
zyF`v`w!q`dm4XhWjm7#BTaSYtFaN1iC}s0Or1^iQ2Th&pKLsmWst6ii*~!^CEGo*Y
z`nW`d8m_RkYRnFcrOwq$lJh&wT3tI$4`YDRBmu{v0$mb0d{`N3m%h+?MbFSM4ZbX<
z<z&;@go)M^^5erXS4~VzD7d|_wVyNB3HXhDzt4K^>h<gK66FipBV%J3B_%yH6AzDK
zXaRtO_<3z@?a&u5-ZVtXs1XY6yV3Syz7&%9`t<?nQ>W6)%Fa4+gR0$aalwOe)*dd@
zwT8$2R@YlgS;udF>$3q0<K`PwbLfo{5%oeKAW~D0uy9G$IuwHt0<MW6)C_59YlE1B
z4uLX2z#8BN?Ok2tC>n<d0vLLf4-E8uGHce?Io7eSQFhwP`DvSE2~|!ZB*>%OiO%aO
zR8vg*9KIGEE8=Tof05+%kofB@q>P+h>K%OY#0eC&Sh!EAJ5;O{;7X?pG$V44s=+On
zSsSW}4qSd0AAbnGTu%QgH0IwveR8p8+XR^3HuKA~HcOJSMA*6PP+iVh&x;rSrr%H~
ztLj2O+^Z%2z1tk*M6N`<ew_(i(-s5)LGT|#eaug&A8=FN()%S^&VY%Di8xVGBAb+)
z3>;VP2<hZF)l(1HjEGJ$$cq>}!@?8Im6>i4@usjDyn&NVkAcN8Y<k2wTl~wA5OGD8
z(_@OayGgx1$ug4RzxZ&y?3{YCem`kxeq}*uNzMv9my@?`X4UuYW0<XdA%L<EC#Uy<
zwhQCUPO{OcEQ)p?5W&E%ZOJw*U4YG_MtJ}J{Q|I()b#YaLK6(;F?1lHVEuz+p!UTk
z)4?jIqZ{ManRYJHKkAhdl@~&cGz)yj#+r|l1Bmbvjw%wj;x*-wrO+fZzj@x%bmZBK
zoAx1Fk{8$1VAb~hY);R&R1VbylVdklQyl1(_co`erhWyPD}8s?f_>k<$;Dm=1Gvsz
zyk}EU3U=w?&gQJb0Z|Ni3Y~abe@b_*jo8717w&ImMSDc(t5*}HqNjoT2`D|gYGxL*
zzL26YQA#1UqA$kA@`WnTBaCl;cSaudhvm8d?&;iS0AJ;z+SM(UDA}4D{!E-GXw9be
zIR}RyHH?pzbDwNCFmG>8P!5Az3(_Ck5Gnm6Fpw%fKb6}gdg6q(`+!G^=IhgMusP-W
zV)~g^FJFEjD01k~MRd>cde2@!71P=ZtrG}Hp2Y|MO59PuucwZM`7!YiGg>3BrECdD
z>n9hMspQUBSDwGuXt0HLV9GG-9b7r%2e2^C`#*`L|AeXauY9@wClFj;k(NxqO9+4+
zI5-QVQ4Vx@2gC5~J9dNtqh4QI!2;RnDfcQQy@aX-n@Qx{IkO)>exNJ{w#8cYR9~?U
z+hI*zsCn1*<uNiS=MZZ{JP{8!%WZoda?RX4=Y@ds<nmZ7Wp+6w*2icEheX?alR^&a
zQGwY46tnrARgJe*vPM)gSXn?oGm46?v9q(oIp*cf4GdBM2#yE|De~bLUH}QnWZJRs
z*5Joq|2W5!yi&iQ;n7i18JWVWv7_}Z@rq9uR!AFWh5c?(f)il|W+=>>`L4P4`);iD
z<k|$Iwwb<uGMrSE5H4<<jB>yJQUkD_jKHhXj5(XeE~Z~Q;v^y<aA{?6y7l9)JAfqf
z2UP8OJIw@pF){A!rn|yhcO7^R5DrS+A*Oz$1$@1HkNKOJ7C0jCK*|nZf)uXr^lvpa
zD}k?0--!nZaZuOP3?i=6u{>w*9y`Xp8C=r)KM%zltV{?6X&|E@B7!mZ{_(4W`t|GA
zORd@1*zomUXL(KU4*ojb(Y$D4WMou2!u_{h0*BKg{h?Q)!2(m9<mjhI$6{*!WPq)F
zTK9=WrX3dgc^ArU#*LY`RGvzSjn6+??_j2!;@EU5d3w|HM$HXSt$(gSM*E(!zHMpI
zE>%0G9ROyQF1<)w+q#mxjcHFqU?hEQh)Py#J1{6av=sEVVnYR?$^7)V<ylx*+#)PW
zpYQO48>~&%Dj6QWL0X-hv?J{~3w^<XxSZVop5(KVMS59~a8JQ3plyBpdK4Ia>2YzD
zGNy3L+uC%&`vjGlz16r~26g7u)TFKJ_MVAu%$4*rYqllH%O#Bzx0F-Bzg^kB^X6ZA
zSVvY?Y&YdqG`o9!rN!9F-M4uU*J5jH>r~p0B7Uk?f*?jiL!$?@b&Thv2u539KOCq<
z{_WmVrmpRJgv2c4!t{ayeL!ehpvOY9GDwz0=-`+v<vA#oo@g%IkW=yMz{#%a370KY
zNsG6g9N9fo`S{p2r}xmHgM$ne7Jfrj$(1PzX~*ok5*izn2E;H;DDs08HvsomR8&+j
z-)u=sOA9#luFr#xw>mNnBNcp!9a+XH;2zo17bc!Oe%uVuDTt{GVC|%Kn&+&pdWVID
zrDbNSFE1}g%DSevw6+T6`=~#IEeKjVAKNJbm##TK)-<-=0@%r-{~Yr-aI&O5=5CN&
zdTl$sW{Q;osJ~KtXmY6E1>`@@&dv_Cd&59=o;uZ0_$6I01GOJW?H^@G-npc)?bS6k
z8K4HioBsOpxRuncul($L_bx?$N2@{k0w;1<BhsZ>&gt}lUC_GH-@bj@dK_&`bzx#n
zOR}$Cy#fJf<zA2CIOc-K_Wb}2_<(;lCHPkcRA{Du(geaSGn@R(-1D^UPG2XHWeW3r
zz;iw1v*4RqwKA2q74d7`jqEWC(pQx<5%S=k%6Ma*C*_ouch<n}%*4j)lS)r8Z&M&e
zBq}49@7kVj;abNT3$qlr#c)L$CkBfpd6B3Jn~vl^thkr9*v5oZ(wP02uUwJ{)0QY4
z%P%*>gc0O)oMfld7!bdc-wr_l`QI8nKDdD#J$f`0O+28ah-2dQ+Lo4YpfcJZ+t7%V
z!j!sG7LAoPGy);~KxHx5`_Mcl#+wuF4FCoA^V{(mIf98Wb$j(wE<iG}AWsACg#}>u
zgg!!TR_6OW?S`!j6_ItDdg<^5sz4Vi<@@*RXoHB4zX<t?n>{4Y=g*@`!Cg^FiOxgC
zS{a7#6E{jEZLHHurVDxnF*#*(PY49U0;GUskldXy@?N@-nY@30B9KQ;pO9zYeZtz>
z+7`Sy)hkz6#|vPg7`1D+R03%cgPsGr!>T5zeRX->wONs40(jco-LrL#jf;V<#U_z}
z>!%zBGC}K`gR`UshOFc&rlsi45c-vYTeBey4}z;!=x%Eb;#nwSJ(75>`vmhGn4pFR
z(kLpp`CHdJE9zuM&SZ<4WII$_LJgm<37}5rOn>RfkGq0k5n+7l1%-qro=Os*qryQ*
zSh&F00d$MQa*z}Vk$3N!QN%oqne!}%hx|bHKnE%qI&5I0_%vscZuj5>RtAj!)C;^+
zNLSdTuR5`W4|o?{F|Y2GG^+E~95BFz8EM9>_&4qs*`R2zF5?YM_FMT<IO+T18IH-w
zbka_rJgH-7XjroJ{V5fk&0C-w34&lK6+S~#2u)vN!toTbzluU43I(qIbg&M-Rr*~}
z*kU=WspTA(rDW_TX~CU2l3LCWGU~~36onJlwJOchrRIyXB^L%21lJNevB$Tqc+sS!
zq`FM~r!SsBVsMpy40T_=v;i+c9aR-O`8v=XQ`|bHrqgnw<7fcU5zk@)lLd+BEC7TN
z#!ZDJpWd0;!Qh6!ks8L3*_P*@DX;#M*Y%=x;_S+%!OB0gx{?^t#fzLwx?;pPI($P-
zYjdNA79AIiqslY;T)D)v;?<NF{o$nHHO9*7YNhG!TxHZbZE0zNI0O|jS_w)RLS$rQ
zo@Lb*d1{*uAra^XYU1=3+%B0+&k)2I7vl78-_EKI<|9q~t-$cqyIj%HdUem5U{qmu
zDv`F29N+^@5Vy8-qEx=5jmA%xXK|gP^j~VaD1|h>I;o7ZIn+jlZY#gOG?WgZpggTl
zAfW1vVeU=a_0{E)VS<{=XQ7B&@bACZU&<F+)Ch^@8}v@-FQOcNP_1t{2n@6Jk`--|
zzRPMn=e)0hj}(KZc2GvB!Xzw|lGZd2Yrg&pnmQGTB3fG@#Zjq{W!0Xp7kS1xnPN8>
z<v=uSQrIXH?*;O+TLm<uL5>-|dW>gR05DFyYuCCaUP5Sy9jOZ|H-WtV{OpcyIW$y`
z^ZIjW{ihS=|3|$8HJT8_^Ls|ZVO<?kn+=&yieGh%b&6y|-a2(2VMHEe<^;ujb#1c$
zy3N5kwp_{A=D|Re{EOX>-a_mSuSU{^qi0WHn@uCgDUTH<sML*IdeP0Sw5u9;Hiq4n
z5LhG39ts+(k54oP7nbhizu~wCGIl@9)0>!)ah(+N#69?>A|KI-SQ2k1CZj-^ylzAN
z!K-hxL3Vtx?dKINyb6+NDf)8fyhCXsDKq=)4DXinY1Bi37dFRxmc<0^<l3FI-pJfw
zq|<zu98pxuxCmYtLRVMju)WL|6w!g%pm9Wyho67ptxz)Oy&&gn;ae`_bv+jUWhck0
zN(o5S&&SS}s#G;|G5UHATuBW5R^d3bdT(u;4YQmHBiJN=IS()>?>8Qk5T;$Vr!?ah
zW%gXD7&wUIdyr<=zh}%LjF3&0WDlxfmr8HHk{Z@7&9IdezQFa;4qUt6Uv#KV(ykkE
zGXPVn<PofvUqgv!MsfHkl$*Ss>m<jWQQx}a_5-r$a#srXm$$zb``FTIfN?L&Qw(ef
zIvF&g?>x?o&gn$C(Da?f8&X^>YJ}G+R&pEfGCntMcykiI;;}vh<tr{LW`#C#?A`4;
zQNojrS))KrcTGKic(~^Cgv+9qHM0%+#x8i{c!|xa@dt&)#`UrFX|=GpEL^+W*B@J~
z^=Y2NAX{L4{XW=DM!9_K%~W(Z&5jjbPptp>RyU4=p9J%K%*MEv`^8Hg&R8XK_A=jN
z#=?R9d?J_FtY7nyMn+0pMV&0{u$9|8O1G82AQ^GPK6!@jld^khj7KY#{%Qm%#g74D
zcE(fhob9s~bb(0_gjuJ*ytTIYyM(}-r|`K8*@yYsyia*wb-qiUiB@W4a_8K3yLxLS
znvc_4W7iYY(?w0)x~+}!ZoSAR((Ov?Hz64Ljkr<g=83J+0!LlOGzFM_m9|z&V>?hH
zOP`P3$lS&zJf0L`rj5g8pIckdVd0T&o0&^Y2$NrVojDrbL5YdhzAR}*VatpiV14i=
z#^>sM@i)8)5A$e+^YLvhNMXMo|0hl!ghRq474_9O)+rkj81xD{a?Ept)WTC!Q)>sl
z{~r!jQW5lLV<D7w;d~!$AN7lrY&K@Cd#4q9`&sRjIG9#URTDetGo<V8?C0>yr#7uS
zx41uJ@dGs=Dk<415PbH#i~{&5Q8ErQj;{dH!R(_aW3gBv3<*z*M#G_fOAQQZ>!B`H
z8(~|_+p_fTMj5xg%}`awnF`oA@G^uZuHR1_-9MqS+lNrm0Q&>-7?<JNJ-C(uJq@bU
zDI<a)<%NKDTk%HCh&o=uJ5x)Uek874N^0UozMSiKT~c&>VBoXo2@^#@2hOzH<TRTO
z7FN`#w5leuNxN~hyrZ0p7+6-A)91-6rvxR3JZZ-?7*Z_(RW@pwvxvU0`|dQCmka=F
z!JytsJN4l&R-3;KRs}%xmkHiu#WGL|ATc}=I=Z@v9`mF5QL*9S9fze0h~wq>LLC1~
z`7>W;w)?AA>$n;C#c4}*&urh6EJ<5~BZ{0G_#!~A2Jr|sqC?O7Ot<--KUsL;;rqat
za#vMR8F%57gV<k0T3Qdp3OZd?dcf){XtCcPw3v5C)oOxxbRY%nPwJ}fLQdbP-3?iH
zo?MTCscHXAss%TArZ6uc<M6HW9$w$d;qlX_L#z*2#!Kb@czDrXc@F0UzAN;HiJTUo
zmC$P^Why|V0C_4*69sf6+Dz>^j}bj`1ogwJpK&HY;}th8(GA$e)3TZMtc5!|c!(E{
z2f6Zf=Fk)Yyxs>77#m_0%y;ZN`t>o};ROgXZHH@LxJ7he4;?xrW!oaCsKgab-5f;h
zz5mA};qZa*&z<L?o$asfq5)<iFP}g){T1FFL>}G)w-vm1@XyH4hB~rMGxi85fyZDA
ziI7nt&eTtI=asP*8frWYI_9m&dd&4v?(9f|Ycpl-$I&<={!R?MS@-tRxE)Dh>D&EX
zG}^`*X@kY0eQ+=%huD(iLlqMe6oe2_2~BpuNogwDxpKC|A6s*&5B$W$B(;c18-<l_
z&YIiZ?-kwqT_b*`KOM#n?GPHHIguTVpK!^!+54rl@QwAjr%^-bw3&XgjHGOdyMsN>
zzh0tL9fI8$2iZf1;#=Q=9rBe$rY{ZzDjNGj^!En!|G-=I_!;18;kw3ENxf73rJa<S
zy>NW9*tUJysPeS@$cRR>6yi!YgvnHhv!Z`A>P*d#i*B-Dmh)LHnjx;>#ElEogB8}7
zIBO(~@>EdI2%<}&{DIE9kbt9zus#=2!5H87wmFQbCYzF=ce=E;w$^!O2xxOE=xe*?
zctt`YQ~?$o9iz7v3>*91v<&D2!pDyv7sQ2dW}-F#IM8;>b0b6#4zs(1oDr6>$_96~
zpMKB)vm!8hl8{|GQ<59h57{#018bu&u5oLAv;nVY)-|b0O6sUQZQpeaos2<cIYj5p
zHS7;l{*V!1J)o0eZ&32n`Yw8!(p%^d(Mg^rYgehlRorY#)q+H?15%BQij6f2L+XjL
zG6+t&PTqVrQ#7;-IKLgd#Ry`E-!E$qa;a^yJp)bN<KyF<xhOyG{xpza0tv$#oFZAb
z!`O6srDC<d;?{3Z*wL|_g@}q(MKD++k6HRJQb?qlu!j-gfc^A$=~Qw)=pYamfqV*P
z%0UMv9KCH;R$!#XWodTseCUCF5RHI^gH{i=GrOJJq3q4Vf{UrwbUv!={lr*r$NH`p
zqn5FnMDb;EXHF*+Slp|VHt6A}T{ss#T-a0mE?u>@PV$+LBBdrKCaO_{oKGL{X$`l|
zj|ymXO`*U<N-HQQ?^eh#zp@*cy!q`Z2N}{xa)x%5CNvProtrn4!I*b}0SGec>Rq^S
zA)wwRufko5FPdyeYHe)|i;0<uYOJf%hV$$@dMyry5`_7s1MUMdp_5Z!ibS+|UUr3T
zZ1n!d<MnCMdRFU5*H|<A0fwCyK%S;UA`MW&&dHfpTdQ&#rtzBOX|E3n2mo~U;W!I>
z`)6*M!{k}%#_@RP{)v?dShy6ioHBxdpS+YsB?41AZap=Pi!}H&R3Bsfr?)NzME4t@
zl%^=Ap<tmy(JwV{pYtw)X^*yv6Mt;-lEofuzVn!-p04f^5k)F6?v23!<uOZ&fYBx}
z;3_<TO>-&uc*oW4@<7jgv|bx5Btl5Y=Bsy>V0@tsbgk^P72Gv2Xog*6H)~zLCTmQR
zdv8^<Ymp`acl~1Nm0ewh4zUkexI2EH`NR%O%kQ5acR2XWbCX;EBdN6l!Ar>stFxEH
z4juaF33CHk@?MMAuAEy=ge9>BDDQ?UK5b0ev13OT2yt?5)45#O=$8FnlydzWHxlz*
z$@+42EQXMO7o1!AwwVkzZy}7PWWr7|diU;K2XK4w`uCa2ydIxWb2o5fb-pR<<;(r#
z!iu#l>O@Mckz~c{`w<t}EVR`ZVA(Ee8?3BD)L;ZtUAbUm*+58N?>YQJ`6vb*S()y6
z@H`JZJFycdT0Fl$KAZ{VW(-q`@4-IJ3==b;SHEpaNV&^u@lw`h{5hSvGKf%M<RBkr
zV%BPWR|9^=bl;y!c0@{Jmv&Z~xp|U;dF9hl?E@VWjatAd{5kLjrr;@kPEX?MoZ1>7
zO&cJI>ww3YE!<idDW2!qla`)7Cnp~s9-a({r(Cf%?LhswLlU*EVGkYP3usm}o%Yhv
z2^szJDj|nRSA{F>w2m-M26<{M)8}~KG-@{?yKGJsb?=<V8r!Xc<<VgUaX>qF628y@
z(A%@l(vVc42KEV}^iAFme*AwBKmWtX<mCqIwnyo^OBOys(?k%AqUPo7ix&R>2IMcX
A$^ZZW

literal 0
HcmV?d00001

diff --git a/engineering_04_boostraping_match.py b/engineering_04_boostraping_match.py
new file mode 100644
index 0000000..268c49c
--- /dev/null
+++ b/engineering_04_boostraping_match.py
@@ -0,0 +1,77 @@
+#coding:utf-8
+"""
+------------------------------------------------
+@File Name    : engineering_04_boostraping_match
+@Function     : 
+@Author       : Minux
+@Date         : 2018/10/12
+@Revised Date : 2018/10/12
+------------------------------------------------
+"""
+import math
+import io
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+
+import scipy.stats
+import scipy.optimize
+import scipy.spatial
+
+
+def generate_random_grades():
+    df_grades = pd.DataFrame()
+    df_grades['grades'] = np.random.random_sample(100)*10
+    df_grades.to_csv('grades.csv', index=False)
+
+pop = pd.read_csv(r'./grades.csv')
+def data_peek():
+    print(pop.head())
+    print(pop.describe())
+    pop.grades.hist(histtype='step')
+    plt.show()
+
+
+def bootstrap_sample(stats_flag=True):
+    bootstrap = pd.DataFrame({'sample_mean':[pop.sample(100, replace=True).grades.mean() for _ in range(10000)]})
+    # print(bootstrap.head(10))
+    if stats_flag:
+        print('quantile(0.025) is {}'.format(bootstrap.sample_mean.quantile(0.025)))
+        print('quantile(0.975) is {}'.format(bootstrap.sample_mean.quantile(0.975)))
+    else:
+        bootstrap.sample_mean.hist(histtype='step')
+        plt.axvline(pop.grades.mean(), color='C1')
+        plt.savefig('bootstrap_sample.png')
+        plt.show()
+n1 = scipy.stats.norm(7.5,1)
+n2 = scipy.stats.norm(4,1)
+
+def bimodal_distribution():
+    x = np.linspace(0, 10, 100)
+    plt.plot(x, 0.5*n1.pdf(x)+0.5*n2.pdf(x))
+    plt.show()
+
+def draw():
+    while True:
+        v = n1.rvs() if np.random.rand() < 0.5 else n2.rvs()
+        if 0<=v<=10:
+            return v
+
+def data_set(n=100):
+    return pd.DataFrame({'grade':[draw() for _ in range(n)]})
+
+def plot_sample_distribution():
+    mean = pd.DataFrame({'mean_grade':[data_set().grade.mean() for _ in range(1000)]})
+    mean.mean_grade.hist(histtype='step')
+    bootstrap = pd.DataFrame({'sample_mean': [pop.sample(100, replace=True).grades.mean() for _ in range(1000)]})
+    bootstrap.sample_mean.hist(histtype='step')
+    plt.show()
+
+if __name__ == '__main__':
+    # generate_random_grades()
+    # data_peek()
+    # bootstrap_sample()
+    # bimodal_distribution()
+    plot_sample_distribution()
+
+
diff --git a/grades.csv b/grades.csv
new file mode 100644
index 0000000..9cc8978
--- /dev/null
+++ b/grades.csv
@@ -0,0 +1,101 @@
+grades
+2.885297375052974
+3.3787232652921926
+0.5157506783237786
+7.530575169035667
+9.180303136325387
+3.247731687659651
+4.950489892885538
+8.0015009035261
+2.6078622645074114
+6.009878816172289
+4.186469107435789
+6.682784643085828
+0.8751624089495602
+4.716497971747977
+1.4581406336496172
+3.19486133862394
+9.427085671165333
+6.284416630262431
+8.824918578038467
+7.890313682109427
+4.871002855810409
+0.6317857270649152
+4.991058184260214
+7.983451855523915
+9.962823526017296
+4.982658322178077
+6.670156683906837
+0.651839509549671
+2.3272059025484704
+5.699657540517821
+2.939261511228751
+7.686950454425226
+2.115272151014879
+4.431181488103318
+8.309128004682204
+3.6800550442415525
+9.925188218897102
+6.001069249897107
+8.825709702197125
+3.384629235908936
+0.5609961113278883
+1.819072372676147
+1.5203215232741374
+4.674224044344715
+5.662602199916055
+8.262112284506735
+0.09169696831957563
+1.7688617708731935
+2.3198470228685353
+0.8119208147379753
+7.38967923597217
+7.740937716712329
+6.02697965034129
+6.795766719596736
+6.737286587003727
+7.2815132151327155
+8.762215432029238
+1.989381334869742
+2.3957518451893645
+6.728593713620739
+3.741800153436029
+8.511174741265508
+3.1032573025601184
+7.372005794420275
+5.9909522992686535
+5.5695898456772355
+7.937879929877528
+6.5764800298040305
+0.565865516090116
+9.492054741000244
+0.3263210544678852
+2.2110798568334857
+1.7138778687188116
+6.459562568464453
+9.932064685278712
+4.013709190046729
+6.228670230996718
+0.4991353566920398
+3.661144528400065
+5.307086225597097
+8.286759912020758
+2.2077337939598807
+8.679519892820608
+9.7609243620153
+4.005484443419254
+1.8049505749718686
+6.051765899190481
+5.478650795676222
+4.099844770479421
+6.1098960622379215
+5.686654604592347
+7.229974729598268
+4.082606494697469
+0.2635738068212734
+5.92285729972296
+1.6047087942795302
+6.139898193153334
+0.6778877437965691
+7.886811347946667
+0.16635694961872893

From 429e005314fbe41e2f92192f1c3a0ce36d5963d4 Mon Sep 17 00:00:00 2001
From: theengineeringworld
 <40331484+theengineeringworld@users.noreply.github.com>
Date: Fri, 12 Oct 2018 12:51:34 +0500
Subject: [PATCH 3/5] Updated Files Added

New Lectures
---
 Bayesian Inference Python Statistics.ipynb    |   120 +
 ...alidation Python Statistics Training.ipynb |   382 +
 Goodness Of Fit.ipynb                         |   689 ++
 Hypothesis Testing in Python Statistics.ipynb |    95 +
 Logistic Regression.ipynb                     |   577 +
 bootstrapping In Python Statistics.ipynb      |   578 +
 cholera.xls                                   |   251 +
 fitting Models To Data.ipynb                  |   525 +
 grades.xls                                    |   101 +
 london.png                                    |   Bin 0 -> 59070 bytes
 ... and confidence in Python Statistics.ipynb |   269 +
 poll-larger.xls                               | 10001 ++++++++++++++++
 poll.xls                                      |  1001 ++
 pumps.xls                                     |     9 +
 whickham.xls                                  |  2630 ++--
 15 files changed, 15913 insertions(+), 1315 deletions(-)
 create mode 100644 Bayesian Inference Python Statistics.ipynb
 create mode 100644 Cross validation Python Statistics Training.ipynb
 create mode 100644 Goodness Of Fit.ipynb
 create mode 100644 Hypothesis Testing in Python Statistics.ipynb
 create mode 100644 Logistic Regression.ipynb
 create mode 100644 bootstrapping In Python Statistics.ipynb
 create mode 100644 cholera.xls
 create mode 100644 fitting Models To Data.ipynb
 create mode 100644 grades.xls
 create mode 100644 london.png
 create mode 100644 p values and confidence in Python Statistics.ipynb
 create mode 100644 poll-larger.xls
 create mode 100644 poll.xls
 create mode 100644 pumps.xls

diff --git a/Bayesian Inference Python Statistics.ipynb b/Bayesian Inference Python Statistics.ipynb
new file mode 100644
index 0000000..cfadd05
--- /dev/null
+++ b/Bayesian Inference Python Statistics.ipynb	
@@ -0,0 +1,120 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# The Engineering World - A Place For Learning And Exploring\n",
+    "\n",
+    "## Bayesian Inference "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Standard imports"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import math"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import matplotlib\n",
+    "import matplotlib.pyplot as pp"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%matplotlib inline"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "ModuleNotFoundError",
+     "evalue": "No module named 'pymc3'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mModuleNotFoundError\u001b[0m                       Traceback (most recent call last)",
+      "\u001b[1;32m<ipython-input-5-2e5c536b7c65>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m()\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[1;32mimport\u001b[0m \u001b[0mpymc3\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0mpm\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
+      "\u001b[1;31mModuleNotFoundError\u001b[0m: No module named 'pymc3'"
+     ]
+    }
+   ],
+   "source": [
+    "import pymc3 as pm"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.5"
+  },
+  "toc": {
+   "base_numbering": 1,
+   "nav_menu": {},
+   "number_sections": true,
+   "sideBar": true,
+   "skip_h1_title": false,
+   "title_cell": "Table of Contents",
+   "title_sidebar": "Contents",
+   "toc_cell": false,
+   "toc_position": {},
+   "toc_section_display": true,
+   "toc_window_display": false
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/Cross validation Python Statistics Training.ipynb b/Cross validation Python Statistics Training.ipynb
new file mode 100644
index 0000000..50af6c8
--- /dev/null
+++ b/Cross validation Python Statistics Training.ipynb	
@@ -0,0 +1,382 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# The Engineering World - A Place For Learning And Exploring\n",
+    "\n",
+    "## Cross validation"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Standard imports"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import math"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import matplotlib\n",
+    "import matplotlib.pyplot as pp"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%matplotlib inline"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import statsmodels\n",
+    "import statsmodels.api as sm\n",
+    "import statsmodels.formula.api as smf"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Loading gapminder data for year 1985 (Live Aid!)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "gapminder = pd.read_csv('gapminder.csv')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "gdata = gapminder.query('year == 1985')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Refactored plotting so that it works on arbitrary datasets."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def sc(data):\n",
+    "    return 1e-6 * data.population, data.region.map({'Africa': 'skyblue', 'Europe': 'gold',\n",
+    "                                                   'America': 'palegreen', 'Asia': 'coral'})\n",
+    "\n",
+    "def plotdata(data=gdata):\n",
+    "    size, colors = sc(data)\n",
+    "    data.plot.scatter('age5_surviving','babies_per_woman',\n",
+    "                      c=colors,s=size,linewidths=0.5,edgecolor='k',alpha=0.5)\n",
+    "                      \n",
+    "def plotfit(fit,data=gdata):\n",
+    "    plotdata(data)\n",
+    "\n",
+    "    size, colors = sc(data)\n",
+    "    pp.scatter(data.age5_surviving,fit.predict(data),\n",
+    "               c=colors,s=30,linewidths=0.5,edgecolor='k',marker='D')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Model formulas from the last two videos"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "f_groupmeans = 'babies_per_woman ~ -1 + region'\n",
+    "f_surviving = 'babies_per_woman ~ -1 + region + age5_surviving'\n",
+    "f_srp = ('babies_per_woman ~ -1 + region + age5_surviving'\n",
+    "         '+ age5_surviving:region - age5_surviving + population')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "shuffled = gdata.sample(len(gdata))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "training, testing = shuffled.iloc[:len(gdata)//2], shuffled.iloc[len(gdata)//2:]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "surviving = smf.ols(f_surviving, data=training).fit()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "plotfit(surviving, training)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0.8925854289943076"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "surviving.mse_resid"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXwAAAELCAYAAADawD2zAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDIuMi4yLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvhp/UCwAAIABJREFUeJzs3XlcVNX/x/HXGfYdWUQRFFRccd81dzO1cqvMrPSnmW1mi7nllpmZWl/TNlMzNcs200xNzdxXxH1JVAQRRTbZd5jz+wNBEBAGZgaQ83w8eJR37r3nM5TvuXPuuecIKSWKoijKw09T3gUoiqIoxqECX1EUpYpQga8oilJFqMBXFEWpIlTgK4qiVBEq8BVFUaoIFfiKoihVhAp8RVGUKkIFvqIoShVhWt4F5OXi4iK9vLzKuwxFUZRK5cSJE1FSStfi9qtQge/l5YW/v395l6EoilKpCCGul2Q/1aWjKIpSRajAVxRFqSJU4CuKolQRKvAVRVGqCBX4iqIoVYQKfEVRlCpCBb6iKEoVUaHG4SuKId25c4eN/+5HIniyeyfcqlcv75IUxajUFb5SZZz9LwCPVp2o17EHJ85dKO9yFMXo1BW+UmU0b9yQjf/uR4tgYPdO5V2OohidCnylynBycuKlZwaXdxmKUm5Ul46iKEoVoQJfURSlijB44Ash3hFCXBBCnBdCrBdCWBq6TUVRFKUggwa+EKIWMAFoK6X0BUyA4YZsU1EURSmcMbp0TAErIYQpYA3cMkKbiqIoyn0MGvhSypvAp0AIEAbESSl3GrLNHOHh4cZoRlEUpdIwdJdONWAQ4A24AzZCiBfu22ecEMJfCOEfGRmpl3aXfbea5995n9U//ayX8ymKojwMDN2l0wcIklJGSikzgD+Aznl3kFIul1K2lVK2dXUtdknGYi37bjV+0Rn0mbSAPUFRKvQVRVHuMnTghwAdhRDWQggB9Ab+M1RjOWHf4NEhADQeMFyFvqIoyl2G7sM/BvwOnATO3W1vuSHaWrP+F45FpeeGfY7GA4az+1okv23abIhmFUVRKg2Dj9KRUs6WUjaSUvpKKV+UUqYZop1G9esRd+MqUsp827VaLQmhQfjU9TZEs4qiKJXGQ/OkbYd2bZkyahjHVy3KDX2tVsvxFZ8w+/XRtGzerJwrVBRFKV8PTeBD/tDXZmWpsC9GVlYWycnJBb4VKYrycHroZsvs0K4tU4BpH77G/z6ao8K+COG3bnHyr5+pZipIsK9On6dHkH1fXVGUh9VDF/iQHfq7N/9R3mVUaOcP7aafT02EEJy/cZvw8HBq1KhR3mUpimJAD1WXjlJyZlY2JKVm3z+PS8/CysqqnCtSFMXQVOAbSExMDCPHvVZhp3jo2Pdx/FIt2X0riWpteuDg4FDeJSmKYmAPZZdOeYuJiWHMO1NoPGIC46bMYvmCD3FzcyvvsvIxNzen11A1camiVCXqCl/PcsK++Zgp2LvWoM249xk3ZVaFvdKv6A75+bPmz785cfpseZeiKJWeCnw9yhv2VnbZXSTmVjYq9Mvg6u1I6rbvxqUbalZtRSkrFfh6tO6X33Bp1zs37HOYW9ng0f1Jlq9eW06VVV6+tWtx/fh+WtRXT0orSlmpwNej8a+8jGP4JW6ePZ5ve3jAWcTFQ0yfNLGcKqu82rRszgsD++PbuGF5l6IolZ4KfD0SQrBwziwsA/1yQz884CwZJ/5h6YJ5aDTq160oSvlRCaRneUP/9Ka1KuwVRakw1LBMA8gJ/b+2/s0TA95WYa8oSoWgkshAhBAMfGKAUcJeSsmAp5+jcafuhIaGGrw9RVEqJxX4lZyUkgHPPIdn/xEMnfsN/YaPyg39xMREDh4+Us4VKopSUajAr8Rywr52/xF4t+6EnXN1Bn3wBf2GjyIgIID/mzCRxX/s5OcNG8u7VEVRKgAV+JXY48Oep3b/5/FufW9d+JzQH/DCGGr1G0G7599gy7lgft6wkbS0NIa/9CpzF35WjlXfk5CQwH8BAWRmZpZ3KRVOYmJieZegPIRU4Fdi0bFx2Dq5FthuYW2Dha09GpH9n9d30ItsORtE1wGD8Rr6CoFmrkz/6GNjl5tPZmYm67f9y8V42Ljj33KtpSI6uGsn6enp5V2G8pB5KAP/iP9Jftn2D/6nzpR3KQZ1YOtG9i6dRWTw1dxt6SlJ/DL9dbqNHI9b/ca5230Hj8S2bhNSEuNo1GMAYbaeLPj8i/IoG8gOfBMrG1zc3UlJzyi3OiqqfoOHYm5uXt5lKA8Zgwa+EKKhEOJ0np94IcTbhmwzPj6egIh43Ft15syNSFJSUgzZXLkyNzfnyI4t7F0yk8jgq9lh//6ruLq6UqdF+3z7RgRdITMtjep1GwHQoHt/Ak2diwx9KSUrvl9DfHy8QWq3tLSkXb1aRJ89St/O7QzShqIo+Rl0HL6UMgBoCSCEMAFuAga9g2hmZkZGajJarZas9FRMTEwM2Vy5Mzc358jOrXToM4A0Kfh63kyEMOGLtUtoM/IthBCEBwbg/+eP9JswCxPTe//Jneo24fzmlQXOKaVkxkfzuWVTi+1vTeL7JYuwt7fXe+3NmzahedMmej+voiiFM+aDV72BQCnldUM2YmVlxWPtmnP2gh8DOreuEl+Lzc3NObZrG+Hh4Xh6euZu/2LtEry7P0HYtrU4mGogz2LlsWGhhPy5gu+X/i/fuXLCPta9KQ1bdyGpVSdG5wn91T/9zOWr15g3c5paA1dRKhkh84SAQRsSYhVwUkr55X3bxwHjAGrXrt3m+nWDfh5UKfsPHuaXTX+y5JN5BAUHM3H+Yjq8MoOEqPDcsLewsMjdP2/Ye7bukrs9KfYOF9d+Ru/O7TkWkYJD7fqYBRzh07kfqNBXlApACHFCStm22P2MEfhCCHPgFtBUSlnkpPBt27aV/v7+Bq+nqrpy9Spvf7gQByuzAmEPsHnLNn46HkDLwS8WODYu/BZbF05lxGfZUzzfOu+vQl9RKoiSBr6xRun0J/vqXq0AUo586tdn9WfzCg17gMf7P4Z93E0ir13Ktz0jNYWdX8zliakLc7e5+7Ylo2En3pv5Acb6lqgoStkYK/CfA9YbqS3lAVxdXQsNewATExO++WwBCQc25YZ+RmoKv01/hR7j3sPetUa+/Ws2bcO5oFAiIyMNXre+/L17H6s2bCYqKqq8S1EUozN44AshrIFHgT8M3ZZSdnlD/9bF0/gvn8e6zxdwdeN3pCXfe/pTSsnxVYv46J3XqV69ejlWfE9WVhZXrl594FDSsJg4rNxqc/O2+rKpVD0GD3wpZbKU0llKGWfothT9yAl9mytH+PqjmTRv3oyVi+ZxcsXHpCUn5ob91P97lvZt25S6neDgYF5/d5LenijduH0Xp6LT+XnnviKnJhjYvTNNHM3UcFClSjLaKJ2SUDdtK7bIyEjGTpqOsLLn/ZeeK3PYT5jzCQ0Gjeb29h9YtfR/ZR5Cu/bPv/Fu343Qq5d5xMsl3xBVRXmYVbSbtko5uHItiI1/7yzy9fOnTzFzwmtkZWWV6Hyurq589+nHzHvzJb2EfftXZ+JSpx61nhzDmAnvlvlKv03Delw/fgC71Bg8PDxKfZ6UlBQ27djF71t3Eh0dXaaaFKUiUYFfRZ0/fYp1M9/i2axA3n9ldIlD38XFhaZNGhe/YxHyhr2pefbN42rutYsM/StXrzJ4xEhu375d7LmbNmrACwP78cSjvco0VHTrngPYNmiFS4uObNl3uNTnUZSKRgX+Q8ynrjdD+vctsD0n7D9u7YSvqw2jLMN1Cv2ymL/4CxoOeSk37HNUc6+NtlZDtv69PXfblatXmTh/MS1f/YBXps4uUejrQ0aWFnMLC0xMTNBqHu6pOZSqRQV+FZM37DV3r4KbuFgbLfSXLJhH6OZVxN6+mW/7db99NLZIZ8iggcC9sO/wygws7expM2660UK/U4umBBzaTcCRvbSsV9vg7SmKsajAr2K++mQu7zayzQ37HE1crHEKv4z/saMGbd/S0pLvv1zM9Q3LckP/ut8+3OOCmTl5IpA/7E3MzAAwt7IuUehfuXIFrVZbphq9ansy9ukneWnIAFo18y3TuRT9OnbiFDv27Cv2wiQ9PR2//XuIi401UmWVgwr8KmbhijXMCZREJafl2/7ztXhq9h9Bh85dijhSf/KG/rmtv+QLe4ANm7fg0enR3LDPYW5ljZNve7b9U/iCKVu27+DtBV8wftK0UoV+RkYGZ/392LtlI0f/3UmsCosKJSUlhQthd0i0rcF/AZcfuO/Jg/vwirqM3/bNRqquclCBX8XY2dnxyZpfmX31Xuj/fC2e9I6DGPn6BKPVkRP6g5u45wt7gCnvvIV96DlCzxzLt/3aoZ00Mk1mzIvPFzjflu07WLf3OF3fmIVF+/46h/5Zv2McWPMVbiGn6GaVQsvMcK5uWsOu335UK09VEJaWllQz1ZIcegXvOg/uamvQvBWn0yyo37r9A/eratQ4/CoqISGBqaOG0cwkAeuew4wa9iUhpWTanI9I9GqNR4sOXDu0k3qZ0Ux5+80C++aEfctnX83dFn75PGl+f/PlovloNPeua1atXYffydMs+/zT3G0XT51AXjhM01oFl4tMTEnlwB0t/Z4frSaJUyosNQ6/nKWlpXHr1i1SU1PLu5RC5Vzp1x01ucKFPYAQgvmzZ2AbfJIjqz8vMuyP+h1n1fYD+cIewK2BLxbt+zNx+uzcbSvXrOWXo+e5beXGc2PGAdkfLDdPHSk07AFsrSypp0ni+rVAPb47RSkfKvANIDY2lrV/bmfftQh++OufCjtRl52dHX2fGFjeZRQpJ/SnvzCo0LAHaNTAB2IjSYkv2N9++9Qh+vbsBmSH/W/HLtLz5ffoOGw0qTV8eG7MOEKCg/CyfPC33Ppuzlw75Vf2N6Qo5azEgS+EaCCEWCGE2CmE2J3zY8jiKqsjJ05Rr0M3POr54NOpO4dOnC7vkiotIQTt2xW95q2joyOrPl/Aue8X5Qv9M798y8he7enf99F8YZ+jwzPZoT9+8jQcrQrOHhoYFsGRgGAANBoNIiOtwD5VSVhYmJoG+yGgyxX+b8BJYAYwKc+Pch87GxuSErJnbExJTMTW2qqcK3q43R/6ecNeq9Wy4Itv6TF2YoHj2j/9f1y9HcOeswH5tl+5Gc47fx3nf2ci2H3uClJKtCbGXA20YklPT+fL73+oVNNgK4Ur8U3buzcFSj+BSgk8LDdttVotW3btIS4tExtTwcBHe2FqWnUDw1hiY2MZPf4dxo0cQdfOnbCxsUEIwYZNm1j8y1Yen/Rx7o1XKSW7V3xKTW0CL7ZvxKN1s6d4vnIznIlb/enwzkI0pqac+m4Bg90E7YeNoX6j0k8pUdllZmaq/4crML0vcSiE+ACIADYCud9vpZR3SlljAQ9L4Cvlb8ncWYwc/w7VqlUDyBf6ALtXfEotmcTqZV9y5uhhrINOQVZmbtjnPAMgpeTwt/N5+7lB9O7RvdzeT1WRlpZGXFwc1apVw+y+5zCUohki8IMK2SyllHV1La4oKvAVfZFSFhhGmRP6Vg5O1CI77HMc37eb8TPnMvDTnwo88CWlZNeCify+bEnuB0heJ0+fYdb8haz4/FNq1qxpmDdUCaSkpLBj/yEys7Q82qUDDg4OOh1/83owF7ZvwN3ahJBUQZdnRuHg6Gigah8ueh+WKaX0LuRHb2GvVA6XrgRyyK/ifygXNmb+qcGDee+5gTS21+QLe4B23Xvx1vjxnP79uwLHBR3+h76d2hUZ9h9+s5p2E+bxyrQPCAsL09+bqGR2HjiMrU9LnJt14O/9us8y+t+hf3nUxx1fjxr09Xbh5N6ip/ZWSkenYZlCCF8hxDAhxMicH0MVplRMmZkZZGRllncZpTZ44JMsXTi/0NdGDHuK4Z2bc+6P73O3PeiBr5ywbz9uGhbWtrQdN71Kh75Wq0VjYlL6B9TydDYIBLKMcyIpBenSpTMb6AE0AbYB/YGDUsqn9VWM6tJR9EFKyeplXzJs5BhsbGx0Pn7Dps38cSIAG7daJQr7vE/ypqck4798Ht/O/6DKde8kJSWxbc9BsqSWvl064OTkpNPx169eIXD3ZjxtzbiakEmHp0bi5OJioGofLobowz8HtABOSSlbCCHcgJVSyifLVuo9KvCVspJS8uG742kddY4dKfYsWPNLqUL/jz//IiQsjLdfHVfo6x99+j/CqtXHs3XnAq+d37KeIc3q8NTgivtQW0WVmJhIbGwsLi4uWFpalnc5lYYhplZIkVJqgUwhhD3ZI3aK7cMXQjgKIX4XQlwSQvwnhOikQ5uKUmI5Yd8/9TJP1nNmplcWU0Y9S1JSks7nGjroySLDHmD6xHewDz3LzdP5p5O+vGsjXT0cVNiXkq2tLR4eHirsDUSXwPcXQjgCK4ATZD+EVZLnzZcA26WUjcj+hvCfzlUqSjHyhn17N1sA3GwtyxT6DyKE4ONZ07ENOZ0b+pd3baSDiwWvjFa3tpSKSZdROq9LKWOllMuAR4FRUsrRDzrm7jeBbsB3d8+RLqVUk4wrevf7T+toEHY6N+xzuNla8rZ7GnMm6n+CuLyhf/DbT/Qe9su+W83AEaPUvPyK3ug6Sqe5EGIg0BqoL4QYWswhdYFI4HshxCkhxEohRL4OVSHEOCGEvxDCXz26rZTWkGefw9/Sk8t3kvNtT0jLYHGwZPJHC0p0nvT0dN4bO5KzJ0+UaP+c0F/w5mi9h71fdAatXpnJ6Lcnq9BX9EKXydNWAauAp4An7/48UcxhpmR/OHwjpWwFJAFT8+4gpVwupWwrpWzr6lr4FLWKUhxTU1MWrFzHt/HVckM/IS2DqRdSmbPqZ1xKMNojPT2dyaNH8LpNBD9/8I5Ood+0adMy1Z9XTtg3eHQIVvaONB89udShr9Vq+efgP/yx6w8iIiP0VqNSOelyhd/xbjCPklKOvvszpphjQoFQKWXO0kW/k/0BoCh6lzf0T96OL1XYv+2aSN1qVnzUyqlA6K/+YjGrv1hsyLeQL+xzlCX0/c/4o/XW4tHdg3/8/9F3uUolo0vgHxFCNNHl5FLK28ANIUTDu5t6Axd1OYei6CIn9Lc5tCxV2Hs5Zs9sqhEiX+ivXLwI+xNbcPDfwsrFiwxWf0DgNRzq+BTYbmFrT5aZJdF3dJu6ykRjgjZLmz3VBGrFrqpOl8BfQ3boBwghzgohzgkhzpbguDeBH+/u2xL4uDSFKsa37tcNJCQklHcZOjM1NWXGgs9KFPYAfocP4Zl0Mzfsc2iE4LV61sya8CpOZ7Yz1MueId72OJ/ebrDQ/+yjD0g7vp3wy+dzt2m1Wo6v+IS5b75Mvbq6zWaSmS7Zveowt/bf4rH2j+m5WqWy0SXwVwEvAv24139f7ENXUsrTd7uCmkspB0spY0pXqmJs/Xp1x9bWtvgdK7lHevTErf+L/Hg1Lt/20PhU3j4WznBvG4Z62eduLy70jx3Yx/aNv5eqFo1Gw5cLP84N/Zyw/+D10bRo3kync/n5n+CT1b8Q41Cf65cjcHZ2LlVNysNDl8APkVJullIGSSmv5/wYrDKl3Lm4uFSZhbtfeOV1ZNenc0M/ND6V+aFmmJqY8LR3wVkfn6xjy54/fyM9PT3f9sN797DzfzMJ/uUrNv/yU6lqyRv6+xe/X+qwn//9z7R/aTL1ezzOhXQrPv/629zXX3x1Au179ycrK6tUNSqVky5TK3wNOAJ/kX8+/D/0VYyaWkEpb+u+/Zqo7esINHdl0ZpfuH7tGssnv8qC1tUwvTtnTqZWy9STMby88BsaNrk3Oufw3j38u2Q2M5o7IYRg2aVY3Ie8zMBnR5SqFq1WS3R0NLqOXssb9nk/sAP3baOpeQpJyUmcitdg6eBIyL8b2fPXH5iYmJSqRqViMMRcOt8XslmWYKROianAVyqCfbv+ocMjXXMf7w+4eDE39IEShX2OsoZ+afQe9DS9pn9RYF5/gPUTX8Sn62O0HfwCABd2b+X6v3+o0K/k9B74xqACX6mockJfQIGwBxjapTUb+tQutAts1J4QvtyyFzs7u0LPHXL9Ot9+Op/Zny0lKysLK6uyrYH836VLTP30K9q/Mh2TPMsSbv1kMtUbNqfdkBfy7V+S0E9JSSlzXYrh6H3yNCGEhxBioxAiQggRLoTYIITwKFuZilI5NGzShNf/t5LX/reiQNgDvDfvM+advcP9F1DLA2IZ+tq7Dwz7T98YxQhtIEM6tuCNQY8SFhbGyePH0ZZyPvjGjRrxyXtv4PftPLIys9cuuLDlJ24HBtD6iWcL7t+9H9HJ6fyxaXOh59uz/wD9nxvF6p9+LlU9FVVmZuVd16G0dLlp+z2wGXAHapHdl19YN4+iPJTqNWhAvQYNC32tc4+e9HprTr7QXx4Qi9ugsQwa/nyhx+SE/cKW9jR1tWVJFw9s427x6pO92TL7Daa/9pJeQv/CXz/Ru151fl3xJRvnvElWRkbuftqsLLZ8NoNuLZvyzFNDCpxnz/4DfL1xB4/N+oo9QVEPTehrtVq2/7mpvMswOl368E9LKVsWt60sVJeOUtkd3ruH3Utm42phQo3BJQt7S9N73ShXohOZvvsiPw5ty38xKazPqMW8b75Do9GQmprKr2tX8+LLr5R49NR/ly5xMeAKTw3KHkF96tQpXp4xjyGzv0BoNGz5bAYt3Bz45vNPCxybE/atX3wrt73/tv1MT28X/m/EcF1/NYoBGeKm7S5gNbD+7qbngNFSyt6lLfJ+KvCVh8HR/fuIjY6k35CiF4ObOHYk423C8a5mXeC1Vaeu42ZjweMNanA2Kon1GbWYufgrpoweQW+zaE47N2P251+VeshsTuib2djT0t2p0LA/eOQoS37dki/sc/y37Wcea1CTEc88VeC4b75bzZ3YWKZPfLtUtSmlY4gFUMYAw4DbQBjw9N1tiqLk0bFb9weGPcBHX3zL/8IsuBmfkm/7rmsRxKVm8HiDGgA0d7FhuOlNBnduzWT3VAbXd2FA+hXmvP1GgfsFJdWqVSu+mz+LQe19Cw17AAsLC7Iy0gt9LSs9DUsLiwLbv1qxCv8YLaH2dfhgvuGmn1BKT5crfEspZaohi1FX+EpVkpKSwqRRw5jmkUEteyu2BIRxNiKe97veu0+glZLXdlxkSD0X+vm45W73C09km7lPma70i3PsuD8L1vxKuzGTcts4v2kNA1vUo1WLpjjYOVC9enUgO+xPxoFP7+yVvq77H8At6iofTJtkkNqU/AxxhX9eCHFICPGJEGKAEKLg44eKopSYlZUVi9b8yvxQM1adDWVHUDQhsSncScm+stZKyRu7LvNYnWr5wh6gvZstvpFnWb96VZHnj4uLY8prY4mPjy9VfR3atWXKqGEcX7UIKSXnN61hUMv6tGzehBOxJ9jst5nMzMwCYQ9Qp21Xwl3qqyv9CkaXFa/qk91vf47seXTOCCFOG6owRakKckLf4Zm3cO/+JEnOnky7mEp0cjozT91h2Jwl7Eq2JT4tI99xwbEpHBRuPP38i4WeNy4ujmmjhjHW9DrTRg0rc+j/PesVBrWszzNDBmFvZ09iWCJmWjM0Gg2b/t6B1yN9Cxzr2aozB0+eqZQT8D2sdOnS8QC6At3JXpv2DnBQSjlfX8WoLh3lYXD0n79JS06i+6AH9+PfT0qJlJKEhATeG/M8b0ydTct27YiKimLW6Gf5xNcKewszgmNT+DzShoXfr8fc3LzAeXLCfm4DU5ytzYlOTmfWlSzmr/kVe/vsSeDi4+PZ/Mt6nh87rkRdQllZWfkeysrMzESj0aDRaLhx4wbjZ82j7SszMLPIfjpZm5WF34r5fDh+LM2b+er0e1B0Z4hROlrgOPCxlPLPMtZXKBX4ysNg25pvSU9JZvCr7+jtnDmh/5qn4Ls4hxKHfY68oQ8w6YWh9LZJJdCrA1M//rTM9wHyhr6JqZkKeyMzROC3AB4he1Hy2sAVYJ+U8ruyFJqXCnzlYZCZmYlWqy00kMsiKiqKpfPmMGPBZ0We+/N5H9L62m66eVYr8Nr+GzEc8ehCyNkTzPHR4GJtwZ6bCfi5tmTyvEV6C33MLJj75ssGCfuMjAxSUlJyv6ko2Qwyl44Qwpbs0O8KvED25GlepS3yfirwFaVstFot7786mhfMw/B1scndfj4qiVVJLqTG3uHDu2GfY9/NBI7qKfRv3rxJYnIyDX0KrtpVVunp6Yx9ayJ3ElNYsXAuNWvW1HsblZUh5tLxB44AQ4BLQDd9hr2iKGWn0Wj4eNn3rEuvyfmoJCA77H/McCcjS8v73uQLe4DutexwvnyYvzc/uKf20oXzHNm754H71KpVy6BhX2PAKNq/NotXpn1AWFiY3tt52OkyLLO/lLKZlPIVKeUP9y9+IoQYpefaFEUphbyh/1tAJD9muDPvm1VMm/8ZC66kkZKRf9GTC9FJXKlWn8eeKHoBu4vnzrJq6uvsXzqbvTv+NvRbyCdv2Dt5eGFuZU3bcdNV6JeC3qZHFkKclFK2Lss5VJeOUpFs37+dyPRI3K3d6d1ZbzOIFCsrK4u9h49yKyYBLQJLIenSpjke7u46nUer1fLrD2sY9uIoNHcXb7l18ybzX32Bhc3tsDIz4Xx0Ej+k1uDjZd8XOTXyxXNnWf3+eOa3csJEI1h47g7tx02lx2P9y/xeS+L/3nib6v1ewMnDK9/29JRkji+byw9LF+Ho6GiUWioqQzx4VWybejyXopQrKSURGRHUbFaTW8m3jNrub1t2kOZcB692Xanb7hFqtO7CzhMXCbkRqtO5NBoNw0eNzg17APdatZi2bB2TzyZwIjxB57AHmNzMCb/lnxjtSr9WjeokRxa8kk9JiMPG3DR3oRqlePoM/EK/KgghgoUQ54QQp+/eB1CUCk8Iwan9p/hw0of8d/w/o7UbHBICzjWxq3ZvlI1Go6F+m44cOn1OL23khP52h5YPDHuAD94Ymy/sc0xu5sSa+TOJi4sr4kg4emAfyxZ9XOZ6P5oxDfvQs4SeOpK7LS4ijKDfvub7L/5XLoF/6cwpzvv7Gb3dsjLWFX5PKWXLknzlUJSKYOW6laTVS+P5Vc8T7RzNTxtKtyC5ri5eCaSmd/0C24UQpGiYo7bZAAAgAElEQVQ1pZ4w7X7utWox/ZNPi13WcMy7U/nqUmyB7b8FxdPtqedxcCh8hpWjB/ax87OZeF/6l8VzZpSpViEE82a+T9aF/Vw/cTBf2JfXKlxB505x/ULlm2igRIEvhNAIIYYVs9shPdSjKOVu5bqVnNSepMWIFgC0HtOafdH7jBL6FubmpKcWMUeh1Oo0bDIuLo6t/+xm045dXAu+XvwBheg3eCgNRkxg6cWY3G2/BcWT2PYJRr9Z+INlOWE/s4UTj3na0zTkSJlDX6vV0u7RxsRd2saJ5XOZMO7Fcl1yse9zo3js+co3WXCJAl9KqQXGF7NPUa9LYKcQ4oQQYtz9Lwohxgkh/IUQ/pGRkSUpR1EMZt1v6/KFfY7WY1qzN2ovG7dtNGj77Vo0I/RSwa6btNRUnK0KLkpelKSkJH7duQ/rhq1xataRA5eCuXTlaqlqyhv6uoR9zodTXz2EvkajwdHEkf49u7J++Te0adGm1OfSxX+XArh1q+A9HBMTE0zzrBdcWejSpfOPEOI9IYSnEMIp56cEx3W5O3qnP/CGEKJb3hellMullG2llG1dXV11qV1R9K5u7brEXI0p0HWi1WqJC4rDq5aXQdt3cHCgsZsjgaf9SU9LAyD6dhg3/A/Qt1uXEp/H/8w5ardsj6mZGUII6rZoy5mAwFLX1W/wUBq98BbpnYcWGfYASz+cyRRfxwLfRPp62nP94A5CQkIe2E56ejq//fhDgd+/EIKhjw7lxcdfxNnZGYtC5uPXt5OnzzBt8TJem/4hoaG63TCvqHRdAOUNYD9w4u5PsTdhpZS37v4zAtgItNe9TEUxjs4dOvPm42+yb+6+3NDRarXsnbWXqc9NpVWLVgavoWPb1jzRrilpgWeIPnOEOpoURg59UqcuDCkl3N/9U8anaPsOHMLzr7zxwH0+WbGWyafjScvMP9Z/RUAs3UdPoHbt2kUem56ezuQxI8j8axnzJr2tt/sVpXHy9Bk+XLaG9uOm0XbcdN6Y+dFDEfq6TI/sXchP3QcdI4SwEULY5fw70Bc4X7aSFcWw8oa+Nsu4YZ/DxcWFAb17MrhfH1q1aJZ7c7Wki5q3ae5LyCk/MjMzgeybjM3qexmq3Fy1vbyY+OXqfKG/IiAWlyfHMGRE4VM5w72wn+CcyHONqtMr4SIfvfdWuYR+bti/PBWNRoOZpVWRoR8SEsJr77xH2t1vYxWdLlMrWAshZgghlt/9s48Q4oliDnMDDgohzgB+wFYp5fbSl6soxpET+r+N+M3oYf8gp0v4YKKdnR3PPNqVhP/8iTpzhE713GnSsIGBq8tW28uLd7/8nnf8o1l6LhKH/iNLHPZ1q2V/i+lc05beif8VCP3ga9d47tFunD15wiC1x8XFMfnjT3PDPkdO6I+eMDF3W0hICONnf4xNj2cY/eY7lSL0dZkt8xeyu3FGSil9hRBWwBEpZUt9FaOetFWUyi/ocgBXDuzEND6a2xG3qVW/ERZejenQq2+ho4xmvT2eZ9Iv0ay6XYHXfr8cRVqfkTw/5mWCr13j8wmj+aSlA3POxvLcB4tp3lr/N29nfDSfmJpN8Gyd/55JwD9/0NHVkldGj8wN+3Z31wCIDQslZNNyvv9isVHuL9zPEE/a1pNSLgQyAKSUKaina5UqIjk5mZiYGO7cuUNycnJ5l1NhRUdFcWPfFvrWdaVXy0aM6NuD7nVrUCsmiBMH9xV6zPj3Z7Hshpak9Mx822/Gp7IvsxpDn3shN+wXtnLE0tSEea2cWP/BOwa50v9oxjSqhV3kxsl7I80fFPYAjjU9qD14XIW/0tflCv8w0Bs4JKVsLYSoB6yXUurtJqy6wlcqirS0NM4dP0r8zWBITsBaZmBlmn19lJKpJUVjDtZ22LnXplm7TuVyVVcR7dn0K4/YpGNWyJDFf65F0GfMm4Ve5UdERDDnpeEsbGaDjbkpN+NT+STUjIVrfiE8LCw37M1N7l2jaqVk+qk7hV7pp6SkMOPNV3l71lw8H3Cj+EFyrvSTo8Nzwx7gtXfew6b7M7jUqVfgmHPbfmVQoxoMe2poqdosLUNc4c8GtgOeQogfgX+ByaWsT1EqpJSUFPb++TtH131D3TtX6VXdgl5eLnT0rkkLTzdaeLrR0bsmPes409PVnLp3Ajm67hv2/vl7hbvyz8jIIODCeTIyMorfWV+SEwoNewB7jZaUlJRCX6tevTqzv/uZyeeSuBydmBv2VlZWnD1+lFb2Il/YA2iE4BFnM44f2Jtve0pKCpNHPct4m9ssen0kIdevs2jmVI7sy79fcT6aMY0adwLpVN0qN+wBPv9kHmF/ryX21o18+18/vh8fkySjh70udF0AxRnoSHZXzlEpZZQ+i1FX+Ep5Cjh3lhvHdtPFwwkrC91Wq0pJS+dgyB1qd+pFw2bNDVShbvb+uQHvlDCCrGvSY+BTRmlz189r6F3dvNCr+D2BYXT9vzcf+MBSREQE//tgOrM/W5pvGOq6b79Cc2ADI+rfm8rh75AErtZ7hDenf5C7LSfs3/fMpKadBamZWfzf9ss829CVC8ka+rzzIR27dQcgKCgIb2/vUr3PtLQ0xkx4F8+BY3F09+T68f243Qnkg6mTSnW+sjLUildDyV7xSpK9gLleHztUga+UByklh3ZuwyX6Go1qlu3hv0thkUQ5edPlscfLvHpUWZ3zO0rY6SPUbNWZZu06GKXNKxcvIE/vpsF9v8eUtHSOJFvQa+izpT533tAvSdjnSM3MYvI/F3ivU33WXk+lzzsfcnDXdm4d2cUjo8ajMTGlU68+uLm56VRPTujj2QQf0+RyC3swzJq2XwP1gfV3Nz0LBEopH/wkhg5U4Cvl4eD2LdRODKW2s37mVL8RHUuwTS269i96QZHKJjQ4iEuHdiOkpFbztjRqXvjgPCklB//egl3EVXw9qmOi0XAjKpZzSdD7udFlntly3bdfcWbDamp3fzxf2ANs+GkdqZuX8Xyjgh/aFyPj+elcKHN7NmbY5vO83NKTvnUc+eLULYJjEkl1cGP2dz9TvXp1nepJS0tj89ZtPDN0SFneVpkZIvAvAL7y7gFCCA1wTkrZtEyV5qECXzG2i6dPYnrxCA1qOuv1vJfDosho3ImmrYwz58uDREVFcfLsSfr26luq4xMSEjj+03J6+rgjhOB4cBi1+jyNu6dnkcfcvnWLgBNH0WZmULN+Yxo09c03rr0sAgMDqVev4A1TgM9mTaPlreP09rg3xDPwThJf+l1j4aNNWXIskJZuDvSpdy/YV54MxsbMhIPp9qUK/YrAEDdtA4C8t7s9gbO6FqYoFUVSUhJhx/frPewBGtR04bb/AZKSkvR+bl1ERUXxysxX+OnsT6We7TM87BY+jpa5XVRN3KoRGngZgNjYWC5eukhWVv6pFGq4u9P9yaH0HPIsjZo111vYA0WGPcDED+dz2r0d/4YmAHAlOjE37JefCKaFm32+sAcY29qLmNQM+tkmM+el4UREROit1opGl/8KzsB/Qoi9Qoi9wEXAVQixWQix2SDVKYoBHdv+F11ql2T+v9LpUtuJo3+X31+NnLDvOq8rncZ3KvUUz04uroQm3htbfv1OPK61PNFqtWzYv4FrFtfYdWiXPksvk5zQX3UhnFkXU/Cp7Y6ZiQbf6nb8FRhdYLqG1MwsLkUl0qqmI/N9rZk8tuingnNEREQQVsgsmhWdLvN7zjJYFYpiZMnJyZjH3sbSqYbB2rA0N8ci7jbJyclYW1sbrJ3C5A17K/vs0S6tx7Rm36p9sAFGPDWixOdycnLCsU0P/jlxCI0A+3q+NPFpgFarRSLRmGrQypLN8WMsEz+cz5Y/NrD2yYFs/f0Xlmz4livpFjzx/qfMWbmI2Xenb865oTu5iw81bS2ZduoOU+Z/9cBzh4WF8eFLwwkKvo5Py7Z8/sMvxS4kU1HocxHzI1LKTmU5h+rDV4zl6L87aZISir2NYYM4ITmF8xbudOrzmEHbud+QUUPovrh7btjntWPmDuaNnEfjxo3L3M6dO3cIuRVCs8bNKnTo7d35N01atqF69er4HTrItkXvM9XXkfF/n+OD7g1zw370/K9o7NusyPPkhL3lnVBebetNWpaW5bHVWLLu13J9/+WxiLlaSVipNJLDbxg87AHsrK1ICX/wtLp37twhOCioyIeSSmPS65M49vmxAt0XN47foK5FXRo1aqSXdpycnGjp27JChz1Aj779c2/Gtu/yCAMmfcxLfnFUa9uD4MRMncP+tXZ1aehiR3M3B8Y5xvDWC8MK3McAuHBOP+sQ64vBFzFXlIpGSolISTRaeyIlodBpftPT09m5fi1Bm9cgj27B/6dlHNu9Uy9tFjav/43jN0jdkcqi2YvK/RmB8ta+yyP8uHMfC5etwq9Wp2LDPisri0kvPp0b9g2cbXNfywn9yWNfzDd99crFi/h58kt8Nmsa0dHRrPh6aYmntzYUfQa+olQKMTExVDMx3l88J7Psq/j7Hf77Lzo7aGlTpybeNVzpWrcmDmGXuPrfRb20mzf0Q/xC9Bb26enpjH57NIuXLQYgPj5eH+WWCyEE786e+8Cwh+wlDVt27kZ4cgZOhSw16WZjQXJcbO6H68rFi6h2ejtzO9SixS0/hnZqyZWfvmTUgN7Z9z6kLPT/CUPTZ+BX7UsGpdJITk7Gxtx4XRDWpppCu2uyIkOxtcrfE9qwpivXz+lvBsic0Bf7hN7Cfux7Y/EZ78P16tcZPGowwyYM4+Tpk3qquOJ678P5NHviWd7acYGo5HujlsITU/kwWMOnP/yGiYlJbtg/5W0PQB8Pe6a198TN2px36sCoAb34aNLbTHmmv8Hm9S+KLgug2Nx92AohRAMhxEAhRN6PuuLHMilKRWHEDkgBhXbpiMK2CYHQc3GdO3Tmo2kf6S3sG01ohLOXMzev3cTzaU8GLR/Egp8X5Av9vQf2Vuor/6JM+3gRvo8Pyw39nLBfuOZXbGxs+H3taqz8t+aGfY5+9d1o7uaA380Y3qkjOLH1d77pUoOfDTTFc1F0ucLfD1gKIWqRPVPmaGB1zotSSrV0oVIpWFhYkGbEvtRUrbbQ6ZO1Ds5kZN43B3x0LC519XNDVZ/uD/tdn+/C3dcd3/7ZT9D2+LBHbuiv/2M9q46uYuzUscTExLB02dIKPUd8Sezac+85g2kfL6LFk8/x8u7gfGEP0LFnb47GZY/tzytLK9kZGEFPLxda13RkZlcf3ttxno9aORk19HUJfCGlTAaGAl9IKYcATQxTlqIYjpOTE9HpxmsvOg2cnQs+zduh/2B2Xo8hJDKGpJRUzt0I56K0w7d1saPrjC4mJoa4rDgcPRzZ+/Ve3H3dadLn3l//nNCfsXIGm85voss7XWg3ox29nu3FNc9rjH1vbKUO/T49++T78+SPPmH9wZN8tm5DbtgDeHh6MuWbH5h0Oj439LO0kqm7LjC2dR0autghpWTNmRs839wDjRB81MqJn2a/zZVL/xn8fegU+EKITsDzwNa723R5cEtRKgQTExO0FrbF76gnWkvbQoct2tnZ0X/MG6Q0eYQL1p449xrKo888r9dpCPTFzc2NhW8tZPe03Vg5WJEQkVBgn6yMLGJiYmg1shXaLC27Fu9i4KKBNH6sMU3eblIg9Df8tYFLAZeM+Tb0ytLSstDJ4PKGflJ6Ji9uOsHTTdxzw/6t7ed4sbkH7WplP+WdkpFFImY4OOl/io/76fJ/1tvANGCjlPKCEKIusKckBwohTIQQp4QQW0pTpKLom6lTdVLTDX+Zn5qejkk1lyJf12g0NPRtRvsevXH3KHoysoqgYYOGzHttHvGn49FmaTnyw5Hc1zLSMlg7Zi0D5w7EoaYDm2ZsouOLHXFv6g6AUx0nmrxzL/TX/LyGHWE7mLl8ZqUO/aLkhP6rp5PpN2EmHx+5xp2UdF7fcRE3J8fcsE9Kz2TKuSRmrlxvlEnbdH7SVghhI6XUaUYoIcS7QFvAXkr5RFH7qSdtFWOJjY3l8sbvae9V06Dt+AWF4TPk/6hWrZpB2zGmgMsBTFk6hdibsTQe3JimTzdl95TdWGdZU/+V+lw9chWn2k40fazgRLo3Tt3gwtILuPVwo9WoVmRlZrFn+h7mjptLo4YV796FvuzZuYP5k99i3jffEXD2DOLA7wyubZMb9rrOxX8/vT9pK4ToJIS4CPx3988t7s6RX9xxHsDjwMqStqUohubo6EishSNZWYa7eZuVpSXWwuGhCnvIvtJfNmMZ29dvp41JGza/tJnFkxaz9qu1hK8Px6uNF+e3nycqOP+CeIlRiRxedJhqHavRalQrAExMTeg5r+dDe6Wfo2ffx9h5+hLtOnXhhVdeR3Z9mlf94/QS9rrQZT78Y8DTwGYpZau7285LKX2LOe53YD5gB7ynrvCViiI6MpJLm9fRpa5hrvIPXwuj4cAXcHYt2ypalYlWq+WNaW/g/JQzWz/cyjOfP4OzlzOJUYkcnHGQZJHM0G8KrvmalZHFn//3Jzt+2VHkuY/4HcHvtB8TXp4AUOWfFs7LIHPpSClv3Lep4OQR+Yt4AoiQUhY55kgIMU4I4S+E8I+MjNSlHEUpE2dXV8zqtyAsRv/jxW/HxGNar3mVCnvIvifx1fyvSPoric8mfcalpZe4cfIGfh/6sXbxWga0G8CFjRfyHSOlZP+8/cydPLfI8x7xO8LSv5ZyveZ1ej/VmxFvjKhwi8ZXBroE/g0hRGdACiHMhRDvcbd75wG6AAOFEMHAz0AvIcS6vDtIKZdLKdtKKdu6VrG/HEr5a9u1B2czrIhJ1N9CJbFJyZxJt6Rtt556O2dlotFoWDx3Mb2692LFohVod2hZuWAldnZ2vDXuLerF1MsNfSkle+fs5d0h79K+TftCz5cT9t1ndadh/4Y0HtWYFPcUxk4aq0JfR7p06bgAS4A+ZD88uBN4S0oZXcLje6C6dJQKKCsri12//UhLi1TcHO2LP+ABIuISOJVqQZ9nnq/wM0gaw5GTRwi+E4ybjRu9OvXK3b5k+RICqwUScSaixGGftwvn/Pbz3Dh9A+swa1YuWmn09QYqGr136Ugpo6SUz0sp3aSU1aWUL5Q07BWlIjMxMeHRYS8QZO/F0aCwUs1oqNVqORoURqBtbR4d9oIK+7uuRF/Bp6cPN9NukpGRkbv9rXFv4Zvi+8CwB/jgsw/oMrVLgf56336+JEQkUOfFOoyd9OCHuhISEoiKiiqwXUpJSkpKuc9gaUzFPjglhJgspVwohPiCQmYgkVJOKElDUsq9wF5dC1QUY9BoNHTs3ZeI283455+tVM9KxLeWC2amD/4rkpGZyfmbUUSY2NBqwHCq1zDsMM/KxkbaEHg6EE2SBtP7fpfjRo4r9vhlnyxj4rSJ9P6kN6bm944/9P0h6nWph2s9V65qrxY6Fz1AXFwcL097mUxNJkunLsXDwwOAtLQ0ft/1O8JRkBafxiMNH8Gnrk8Z3mnlUGyXjhDiSSnlX0KIUYW9LqVco69iVJeOUlFE3L7NhaP7kXFRWGSmUcPKBCuz7MBJycgkPCWLVFMLhIMLTTt2o3oNwy2VWJlptVpiY2NxcHAo9beeoKAg3v3fu/RZ0AdTc1MOfX8IS3tLGvVqxJHZR1jx8QocHR0LHJcT9h0/6Ii5tTl7pu1hyZQleHh4sGP/DqxbWpOVmYWtgy3nd5xnVP9RlXbkT0m7dErz4JU9IKWUBZ+tLiMV+EpFlJqaSnhYGKnJ2Td2La1tcKtZs9DH6hXDyAl9M08zTK1MaTu8bYnD3sYpe66bjNSM3ND3v+xPokMiyz9fTsytGLr36M7YgWPxbepb4JtIZaD3wBdCtAW+J3s8vQBigTEPGnKpKxX4iqIUJSgoiNMXT/PXrr+IT4ln5ScrCw17gKEvDeWR+Y/khn2OjNQMdr6zk+F9h7P24FoGLRrE5X2X2TZvG+YW5jSp04R1X60jKCgIHx+fIq/4pZRERkYihMDFxaXcvxmUNPB1+ShbBbwupTxwt4FHyP4AaF66EhVFUUrO29sbb29vnnzsSTIzMx/4DatZw2bcPnObej3r5dsedSUKK6z43e93Bi0ahEajwaO5B9U8qjF86XDib8fz2PDHsKtjR327+jg7OuNdy5unhzyNmVn28h9SSvZs+g3nuJtI4EK12nQfOLTcQ78kdBmHn5AT9gBSyoOA3rt1FEWp/HKW8TMEU1PTYrvT5kyeg9UpKwL3BOZuCzsXxuVvL5Nun86j8x5Fo9GQGJ3IXx/8xfClw7Gyt8KtgRs9PupBYlYiJyNPEt4onM83fk6z7s04fOwwABEREbjE36RFnZq0rFMTh5gQoqMrx4DFkozSaX33X/2EEN8C68kerfMsatSNoih3xcXFcfTMUSJSI5BmErRglmlGE48mNGvczOjTPs+ZPIfZC2cTSCDWLtZE/BLBgukLGD19NFnpWaRnprN59maGfDwEK3ur3OOq16+OxkRDi4EtaNi9IT7dfFg/fj2vz3mdr2d/TT2veiSlpDLtp9/4v0e6UJlWdy3JKJ0HTYEspZS9HvC6TlQfvqJUThcCLnDi5gnqtq+LZZ51eqWURN6MJPZ8LE/1earQlb8Mbc6nc4iOjebzDz9Ho9Fw48YNRk4dycAlA/lz1p8MmDYAh5oOufVum7cNn+4+NOjaIPccGWkZrB+/nqTwJBZNXMSsxdPJsNYiJIxqP5g33pterl06BhulY0gq8BWl8gkJDeFQyCF8OhQ9jj0lKYVbh24xrN+wCtHXnRP6Ty5+kh9f+5FnP38Wh5oOXD10lYC9ATw+/fECxyRGJ/LDyz+QEJmAZ0tP+rzdB2dvZ9a9vI4Fry7gkU6PlMM7yWaQydOEEI8LISYLIWbl/JS+REVRHgbHLh6jfvv6D9zHysYKs9pmhNwIMVJV2TIyMjh38Rynzp0iNTU1d7unpydrP1nL+lHrkRmSNS+tIS4sDqERBPkFceavM/nOk5qYyp+z/iQ9OR33pu70ebsPrvVc0Wg0vLDiBaYsm8LBIwcLreHGjRsV5mleXebDX0Z2v/2bZHdaPQPUMVBdiqJUAnFxcWTYZZToqt2jgQcnL580QlXZIiIj+GHHD1w1vcrePT/w2ZIZBF0Pyn3d09OT438fZ/2i9YwZPIYdE3eQuCURn9o+BB8P5szm7NBPTUxlw5QNRAdH4+TlxGOTHsO13r2JHnNCf9IXkwgODs5Xw8EjB3lj0RtMmD4BrVZLTExMuU74psuwzM5SyuZCiLNSyjlCiM+APwxVmKIoFd+t27dwrFX4WPj7aTQa0oTxFjLfc3IPvo/5EhMZQy0TSayLBQcvHsSrtle+D6iGDRvSsGFDJr4+EYCoqCheevclEmISOJ5ynIC9AWRlZFGnXh2CLgRx7ei1fIEPEHcrDkfhmG8xk4NHDvL1zq8Z8NkAws6G8fK7L3Mn7Q4WwoKVC1dia2u8dZVz6NKlk3L3n8lCCHcgA/DWf0mKolQWWq1Wpz55WXA6LoNJN01Ho9Hg7OaMw5B+NH6mH6aOpsVeYbu4uPDn2j/54ZsfaBDVAG2oFk2chvdffJ+d63ZybM0xjv14LHf/mNAY9k3fxx8r/8DKKnu0T07Yd3u/G0II3Fu44/acG0k2SbR6vxVjJ48lMTHRoO+/MLpc4W8RQjgCC4Gcp2vVsoWKUoW5ubpx/vp5XN2LX8tCSomp1njTFmgy713POrs5A5CZ9OAHtu43+a3JTH5rMunp6ZibmwOwfc12+o3qhzZLS6NejQqE/bkL51j611J6zemV78OwTps6mJiacHDFQbrN6MbYyWONfqWvyxX+p8AY4EXgCNnBP88QRSmKUjm4uLigjSrZDcmw4DCaexnvwfxmtZtx9eTV3IfAbgTcwNvBu1STuOWEPWT3/e9Yu4OTq0+yd9refGEP4FnLExkrSY4t+E0iyC8Ij+Ye2Fe3p82MNoyZOKZ0b66UdAn8NUBTYCnwBdAYWGuIohRFqTxa1m3J9fPXH7hPZkYmsZdiaVC/wQP306fmjZvT0a0jt/bfInRfKI1MG/FIu/xDJ4NDglm9dTUXAi4UcZbCeXh4cHb/Wbav354v7AEcHR1Z8fEKjsw+QlLMvZXUDqw4gF11O1oOaglAdEA0DbyM9/sA3bp0GkopW+T58x4hxJki91YUpUpo7NOYuJNxBJ4KxLuFd4EnahPjE7l+6DpDuxt/vhmv2l541fYq8vW4hDiwgjtxd/Tabk7ov/z+y3Sa04mj3x/FzNosN+yDDgRhetSUuVOLXsfXEHSZLXM1sExKefTunzsAo6SUr+urGPXglaJUXiE3Qjh+6Tgp5ilYOFigzdSSHp2Oh50Hndt01stTtufPHCIiLIAuPZ/X21O7SUlJWFtbG+TDKDY2ljHvjuHpx59m9+Hd1BlTh6SIpNyw11ebenvSVghxjuy5c8yAhkDI3T/XAS5KKX3LXm42FfiKUvmlpaWRmJiIiYkJDg4Oegk1KSXR0dFs/X0etavfIcv2WZq3bIuLi4vR5+gprczMTMZPH49LNRfmTtFf2IN+A/+BD1dJKR/ceacDFfiKouSIj4/n3JEDpEXdRqQm4mwGpMSSkhhHdfc6JGVKotJAWtli4uhCs07dqObkVKq2wsPDOXXpFGamZrRv3h47O7sSH3v46DE6d+xQqnb1Rc2loyhKpRQWGsr5g/9il3yH5jWdsLYsvusmLT2Ds7eiiTG3o2HH7tSp9+CpHvI6ee4klxIvUbdVXTIzMgk8GkivJr3wrOVZlrdhVAaZS6cURVgKIfyEEGeEEBeEEHMM2Z6iKJVXZmYmB/7+i5u7fqdPdXM6etcsUdgDWJib0c6rBo/WtCb+8FZ2b/yN9PT0Yo/TarVcCLtAg/YNMDUzxdLakiY9m3D4wuGyvp0KydCdX2lAr7uje1oC/YQQHQ3cpqIolUxMdDQ7vv8G38wI2tapUer+bSEEzTzcaKL7EYYAABYcSURBVG+RxL+rvyb81q0H7p+cnIypvSnRMdHZI3buniPTJLNU7Vd0Bg18mS3n+WGzuz8Vpw9JUZRyFxURwfENa+nn7Uw1W5viDygBWytL+tV34+LW9dy8HlzkftbW1mTGZXIj4gah4aFA9g1i8yzzIo+pzAx+e1sIYSKEOA1EAP9IKY8Vd4yiKFVDfFwcJzb9SJ96bpiY6DeOhBD0qOdOwM4/iAy/Xeg+Go2GVnVaYXrbFK8aXsTHxHP+n/N0bdFVr7VUFAYPfClllpSyJeABtBdC5BvGKYQYJ4TwF0L4R0ZGGrocRVEqCCklhzb/Si9vV4MNrRRC0KNuDY5v2UBWVlah+/g28mVw68HIixKrYCuG9xhODbcaBqmnvBl1lI4QYjaQJKX8tLDX1SgdRak6Th46QPWwC3g4l2x65bKIjk/kklUtuvTtb/C2ykNFGaXjeneGTYQQVkAf4JIh21QUpeJLTk4m/j9/o4Q9gLO9LSY3LnEnOtoo7VVUhu7SqUn2nDtngeNk9+FvMXCbiqJUcGcOH6B1DQejttnKw4WzB/fqdIyUkiuBVwxTUDkw6OTUUsqzQCtDtqEoSuUipSQx5Ar23i5GbdfC3AwZGkpGRgZmZmYlPi4oJAifekUv0F6ZVI5JKBRFeWhcv3YNb8vyGZ3duJolAedKPsmvEIK+PfsasCLjUoGvKIpR3QwMwNNIfff3c3O0JzLkWrm0XRGowFcUxajSY+9gYV7yLhV9EkJActnXktVqtaSmplKR5iIrCeMtMKkoigKQkgBUK+f2Sy86OprNhzdjXs0c80Rznur7VKWZolkFvqIoRiW0hT8AZcz2pZQIIYgMv83lM6ewtnegRfuOJQrug6cP0uSxJpiYmBB2PYwrgVdo6NPQCJWXXeX4WFIU5SGS3Q2ilVpkOUytJUT2SKFbN0K4sGkdbWUU7rfO8c8vP5Soi8bc1JyMtAwA0pPSsbKwKuaIikMFvqIoRiWFCQBn/jtDUEiQ0dvXItBoNFzyO0R3n1pYmJvhVs0B17QYYmNjiz2+Z4ee3D5ymyt7r+CU6ETt2rWNULV+qC4dRVGM6+4VsU9tH8wtymFWSnNrAITGhCxtBqYm2R9A6VlaTE3vRWJWVhZHTx6lXu16+ebWsbS05Om+Txu3Zj1RV/iKohiVsLZHq9Via2uLuVk5BL519vKFrXo8yj+B4YRGRnP+xm0y3X3yLW14+vxpYlxj+Pf/27vz+Kqqa4Hjv0USEpJAJiCEMSEyqAwxRkYFVMABFEUq+tRaqGOfc5Xi0CfWqQOWavm0D+f6rIqtY21BI7Q4IEOYZyRCmEISAoQhIeN6f5wTuIEbSEKSe2+yvp9PPrnZ9+ScvT4ne+Xcfc9de/m8xu9jA7ErfGNMo2rXrTt5mYuJj238e/GPFB0lPK4zANExMYz48d3s2PoD0a3b0KdL1SUNz0o8iy2LtnBWQs2XSzyV/Px8wsLCiIion5r/dWEJ3xjTqLr36k3GsgXE12298TOyPucAPa8Zd+znVq1a0fOcc71uGxUVxcTLJp7R8b745xuEtAyj1zkX8v2K6RwsjGLMhGk+u43TpnSMMY2qVatWlES1p7y8ota/m75sCY+88ntKy44vQbi3oICv1y6p0uaNqnKgZRtiYhrvMwCpA66kf+oogoKCKSkNQn18jW0J3xjT6M4ZPIx1u2u34FH6siWsy32Tu27N4BevvXAswa/etpoilrE959T725q7j24pA+rc57po2y6e2Li2xHdIYPCoX3H5NVN9+iEtS/jGmEaX0KkzOWFxFBWX1Gj7ymT/wOT9JHdT/nvSqmNJf+mmTGbPX8XOvd6XMQQoKy9nU0lLelQzfdMYIiMjadnSt2vlWsI3xvjE0LHj+XbHvtNu55nsK1Um/euefojzUhfw6nMFLNr2Gl+tXuF1Hwu35TD4qglOLZ1mzBK+McYnwsPD6TLoEtbsyj3ldp8smsfEsftPbv+3cvuNeYy+6CgiMOXOfL7benLSz8zdR5tzBxJdh7l7VQ24AmmnYgnfGOMzvfr2ozQphY3Ze6vd5rc/fYhn/9ibbI//C396B3omwlUXH2+rTPrfZL5KxuYNAGTtPcCemERSBg+tU//e+egz/vFF07kP3xK+McanUocOoygxhWVZe7xeTYeHhfLbyVOrJP11myLYsOXk+9lLSiEnrxXx0W1ZtzOX3TFJDBlV94XL+5/dk769e1Zpq6ioYN2aDIqLi+u8X18Rf3q5kpaWphkZGb7uhjHGB7b/kMm6eZ8xtGMb2oSfXJCs8GgxU17/NXFxexjWYzLFpSVkFrzNvbc69W+KS2DK85342eUPkFUSTNLQUQ3yJm1WVhZffvwgcZ3HMXbcTVXKMXhSVbKzs4mPjyfILd/QUERkmaqmnXY7S/jGGH9RWlrKws8/o0XONvrHR9EmIrzK84VHi9myaxf9krsD8K/F35JZ8DZ33HiAh59L4JLzJxOV3JchV44jLCys3vu3fs0Sdv3wD2IjsoiIaM1XC7+H0PPolzKcbt37kNDxeCG1helzaL17I/tiujH86vFV9rN54xr278th4JCR9dKvmib8Bv0UgIh0Ad4COgAVwMuq+mJDHtMYE7hCQkIYPvZaCgsLWb3oWw5t3URsi1I6RobRPjqK8LDQY8m+oqKCtJ592PbdVUy4/0t+MulpRl57fZV6OHVVWS/f0+5d2zmS8z6jhkQC3Sk6WsTFafv4etFfiaKA71fMJyjo57SPTwBAgkJYvyubI0UQvnIp8XHxdOncBREhucc5VFT0PuN+1laDXuGLSAKQoKrLRaQ1sAy4RlXXe9vervCNMZ5UlYKCArK3Z5GblYmWFINWgLSA4Ja07ZpIx25JxMTE1Ostl4uXLmZA2oAq+5w35xXWLn0DkRZcNjKFpK4x7M3PoezwEj78/AidOnWl1wXPEN22ExkbMyhsWUhQbBAdu3SkvKycAzkHKNpRRGJcIgNSBhASUn/LPPrFFb6qZgPZ7uNDIrIB6AR4TfjGGONJRIiOjiY6Opqz+/VvtOMOvGDgSW3pc/9GWnIGxSUV3HbPQmJjIph43VB27zxCdOQRcvOLaLU3nw3l20kakYSibFy/jIjWPQBoE9MGesOBfQd4d+67jL94PJGRkY0WEzRi8TQRSQTOAxY31jGNMaY+zJo5jbTkb5gw2lnpKjQYduw5zMyXP+fSQTD7U6FdQmtis2cw4vqh5OUGE9+hG+f2ObmUQ3RsNJGjIvngyw+YOHJig7zXUJ1GuS1TRCKBD4AHVPXgCc/dISIZIpKRl1e72hrGGNPQZs2cRoegF5kwuuhY23WXwcYfYNo98PT98PS9SmjFZmL3z+ftR55n6/qlABw+eJhDBw+wZeVStq5czPYtm1CU4JBgkkckk74wvVFjafArfBEJwUn2f1XVD098XlVfBl4GZw6/oftjjDE1VVJSwtf//itvPnV86UNV+N1rcMMYuNid+bl8GJRXwKZtcPeNZdz1yxfYsSKXDenvUBHemV9OfxRUKCgqID8vl7bt4glrFUaBFFBcXExoaGijxNPQb9oK8Bdgn6o+cLrt7U1bY4y/2bRxHX/63VW88OBWgoNh1mxI7ASXXXjytp/Oh/wDMKg/PPEizP49TH8DFmcmU1J0iPzc/aReM44R469AKyooKiyj3eHOjBk19oz6WNM3bRt6SmcocAtwiYisdL+ubOBjGmNMvenV+1x+9sg/+PmMRMrKYNQQeP1D54NenoqOQvpC5x/B2cnw/IPw+B9g6u3QpXUmLYpzefyOUhIP/53fT7qPWXffS3stZMuSuXzx3luUlNSscuiZsA9eGWNMDThX+mPZszuLMcOV71bCHx6D0JZOsp8yHR69Azq2d6Z9npvlTPkEBzlX+bdcfbz2z/TXISgI/vl1GDdcfTs39kllwd5SLrtpcp0+lesvV/jGGNMk9Op9Lvc9Opd7pn7JG59EsXZrNJMfhwMH4aZH4LYJNUv2AA9PhvJyGHPRUd79aBaHCo+SElHOhlXeyzvXF0v4xhhTQ8ln9eKi4Zcwf+F+XnljAT17pzH+/kiOFMG9z0DOXnjsD5C5HYacB/O+g6AWMHbEyfu6/xbn+bd+XcKtMx6kZVALdq9d3qD9t4RvjDG1JCIkJffi/EHjmf7cnfROvYJBlw3kRz8PZXN2LJF9xvPES8FMuQ1y8+GxGc6Vf6XSUrj7KXjpcWgVCkFB5RQeLSGk5EiD1t/37Yq6xhgToEJDQ7nimikcOnSIe7rk8Vn6VN75pC/bthexO+RSdm7pz4hJzxAR244Fy/J5fEYxzz4IZWVOsn/sTohuDbdMCWH6pGfpGt+WHw5Xv0xjfbCEb4wxdRQUFER0dDRRUVHErRjLx99upG3XZJL79qF7v76kjR7BwYMH2L1mOa8++gyHni1nZw7ce5OT7G92k/05iV0AKA0Ja9BlGG1KxxhjzpCIcNP4H5MQOYDoDl2PJe3wyHDiOyawL7iC6568m4IOw7jwkalMmxXO9Q8FVUn2ew8eIq5HnwbtpyV8Y4ypB0FBQYwfPZ6YvBg2pW9ix6YdVFRUIAhBoaFEh7akfYcuhOSX88SLz3LTtT87luxLSstYnHeUvl6KttUnm9Ixxph6IiIMTB3IAB1A1vYs1n2zjnItp3Sj8IMqfVL7cVZCDIfzD3NOTAKqSmZOPpuLgxl+w6R6LZnstX/2wStjjGlYZWVlzPlqDnkleeTs3EFoXhEpXZLRlmEkpQwgqUfPM5q794t6+MYYYyA4OJgxI8awdHE657fvSf9UL4V4GoHN4RtjTCNYveJbOkd+SYsjH7A9a6tP+mAJ3xhjGkFUdDu27Sxjz14hIuLM192tC5vSMcaYRpCU3Js20U8QHBxMVFSUT/pgCd8YYxpJXFycT49vUzrGGNNMWMI3xphmwhK+McY0E5bwjTGmmbCEb4wxzYQlfGOMaSYs4RtjTDPhV8XTRCQPyHJ/bAvs9WF3GkpTjKspxgRNM66mGBM0zbhqE1M3VW13uo38KuF7EpGMmlR/CzRNMa6mGBM0zbiaYkzQNONqiJhsSscYY5oJS/jGGNNM+HPCf9nXHWggTTGuphgTNM24mmJM0DTjqveY/HYO3xhjTP3y5yt8Y4wx9cgvEr6I9BKRlR5fB0XkARGJFZF0Efne/R7j677W1ClimiYiuzzar/R1X2tLRB4UkXUislZE3hWRMBFJEpHF7rmaLSItfd3P2qgmpjdFZKvHuUrxdT9rS0Tud2NaJyIPuG0BO66g2pgCblyJyOsikisiaz3avJ4bcbwkIltEZLWIpNbpoKrqV19AELAH6Ab8Fpjqtk8FfuPr/tVDTNOAh33dpzOIpROwFWjl/vw+8BP3+w1u2/8Cd/u6r/UQ05vABF/37wzi6gOsBcJx1r74EugRyOPqFDEF3LgChgGpwFqPNq/nBrgSmAMIMAhYXJdj+sUV/gkuBTJVNQsYB/zFbf8LcI3PenVmPGNqCoKBViISjDPwsoFLgL+7zwfiuToxpt0+7k99OBtYpKqFqloGLACuJbDHVXUxBRxV/QrYd0JzdedmHPCWOhYB0SKSUNtj+mPCvwF4130cr6rZAO739j7r1ZnxjAngHvdl2euB9nJaVXcB04HtOIm+AFgGHHAHIMBOnKvmgOAtJlX9wn36WfdczRCRUJ91sm7WAsNEJE5EwnGuErsQ2OOqupgggMeVh+rOTSdgh8d2dRpjfpXw3Xnfq4G/+bov9cVLTH8GkoEUnOTygo+6VifuQBoHJAEdgQjgCi+bBsztX95iEpGbgUeB3sAFQCzwC591sg5UdQPwGyAdmAusAspO+Ut+7hQxBfS4qgHx0lbrMeZXCR8ncSxX1Rz355zKly3u91yf9azuqsSkqjmqWq6qFcArwACf9q72RgJbVTVPVUuBD4EhOC8xK9dI7kxgTYl4jUlVs92X0MXAGwTeuUJVX1PVVFUdhjN98D0BPq68xdQExlWl6s7NTo6/koE6jjF/S/g3UnXq41PgVvfxrcAnjd6jM1clphPm3a7FeYkaSLYDg0QkXEQE5/2J9cC/gQnuNoF2rrzFtMFj4AnOXGqgnStEpL37vSswHudvMaDHlbeYmsC4qlTdufkU+LF7t84gnGnH7Nru3G8+eOXOx+0AuqtqgdsWh3PHRFecQfkjVT3xTQ6/VU1M/4fzslOBbcCddTlxviQiTwETcV5KrwBuw5lPfA9n6mMFcLN7ZRwQqolpDtAO5+X0SuAuVT3ss07WgYh8DcQBpcBDqjqvCYwrbzEF3LgSkXeBEThVMXOAJ4GP8XJu3IuOmcDlQCEwSVUzan1Mf0n4xhhjGpa/TekYY4xpIJbwjTGmmbCEb4wxzYQlfGOMaSYs4RtjTDNhCd8YY5oJS/imSRORESJS4FE293980IerRWTqabb5lYiMbKw+mebJ7sM3TZqIjMApmzu2gY8T7FE8zhi/ZFf4xm+JyMcissxd6OIOt+2nIrJZRP4jIq+IyEy3vZ2IfCAiS92voXU4XoSI/FNEVrkLbEx027eJSFv3cZqI/Md9PE1EXhaRL4C3xFkA5lyP/f1HRM4XkZ+IyEwRiXL31cJ9PlxEdohIiDiLrUzwON5TIrJcRNaISG+PGNPd9lkiklXZL2NqwhK+8WeTVfV8IA24T0Q6Ab/EWQBiFE4ly0ovAjNU9QLgOuBVj+cGu0l8jmdC9uJyYLeq9lfVPjjVGE/nfGCcqv4XTmmJ6+FYzaSOqrqsckO3vMYqYLjbdBXwuVuw7UR7VTUVpwrkw27bk8B8t/0jnI/fG1NjlvCNP7tPRFYBi3AqBd4CLFDVfW6S9CyjPRKYKSIrcQpNtRGR1sByoJuq9gf+iFOrpDprgJEi8hsRuaiy/tFpfKqqRe7j94EfuY+vx3uZ79k4NXvAWSdhdjX7/dD9vgxIdB9fiPNPBVWdC+yvQf+MOcYSvvFL7tz7SGCwm6xXAJtO8Sst3G1T3K9OqnpIVQ9WFjxT1X8BIdVNg6jqZpwr9jXA8x5v8JZxfKyEnfBrRzx+fxeQLyL9cJL6e14O8ylwhYjEuseaX008lYXnynFW4wLvNdGNqTFL+MZfRQH7VbXQncMehLP04HARiXFr71/nsf0XwD2VP4i74LiIdHArDSIiA3D+5vO9HVBEOgKFqvo2zgpYlQtFb8NJzpxwTG/eA6YAUaq65sQn3X8+S3CmoD5T1fLT7M/TNxyfMhoNBOqqTsZHLOEbfzUXCBaR1cDTONM6u4DngMU4i1evx1liEeA+IE2cJe7WA3e57ROAte7U0Es4C61Xd2taX2CJOy30OPCM2/4U8KJblvd0CfrvOFM1759im9nAzVQ/nVOdp4DRIrIcZ2GdbOBQLfdhmjG7LdMEFBGJVNXD7hX+R8DrqvqRr/vVGMRZU7dcVctEZDDwZ1VN8XW/TOAIPv0mxviVae4HlMJwpnFO9SZsU9MVeN+9rbMEuN3H/TEBxq7wTbPjrvg0z8tTl6qq1/l9Y5oCS/jGGNNM2Ju2xhjTTFjCN8aYZsISvjHGNBOW8I0xppmwhG+MMc3E/wM5wAL9sVCNagAAAABJRU5ErkJggg==\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "plotfit(surviving,testing)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0.4079953254522058"
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "resid = surviving.predict(testing) - testing.babies_per_woman\n",
+    "\n",
+    "df = len(testing) - surviving.df_model - 1\n",
+    "\n",
+    "np.sum(resid*2) / df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def cross_validate(data, formula, response, n=100):\n",
+    "    ret = []\n",
+    "    \n",
+    "    for i in range(n):\n",
+    "        shuffled = data.sample(len(data))\n",
+    "        \n",
+    "        training, testing = shuffled.iloc[:len(data)//2], shuffled.iloc[len(data)//2:]\n",
+    "        \n",
+    "        trained = smf.ols(formula, data=training).fit()\n",
+    "        \n",
+    "        resid = trained.predict(testing) - testing[response]\n",
+    "\n",
+    "        df = len(testing) - trained.df_model - 1\n",
+    "\n",
+    "        mse = np.sum(resid**2) / df\n",
+    "        \n",
+    "        ret.append(mse)\n",
+    "        \n",
+    "    return np.mean(ret)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "1.6328902506912195"
+      ]
+     },
+     "execution_count": 30,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "cross_validate(gdata,f_groupmeans, 'babies_per_woman')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "1.05384635172714"
+      ]
+     },
+     "execution_count": 31,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "cross_validate(gdata,f_surviving, 'babies_per_woman')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "1.2083936363431724"
+      ]
+     },
+     "execution_count": 32,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "cross_validate(gdata,f_srp, 'babies_per_woman')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.5"
+  },
+  "toc": {
+   "base_numbering": 1,
+   "nav_menu": {},
+   "number_sections": true,
+   "sideBar": true,
+   "skip_h1_title": false,
+   "title_cell": "Table of Contents",
+   "title_sidebar": "Contents",
+   "toc_cell": false,
+   "toc_position": {},
+   "toc_section_display": true,
+   "toc_window_display": false
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/Goodness Of Fit.ipynb b/Goodness Of Fit.ipynb
new file mode 100644
index 0000000..1e58a35
--- /dev/null
+++ b/Goodness Of Fit.ipynb	
@@ -0,0 +1,689 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# The Engineering World - A Place For Learning And Exploring\n",
+    "\n",
+    "## Goodness OF FIt"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Standard imports"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import math"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import matplotlib\n",
+    "import matplotlib.pyplot as pp"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%matplotlib inline"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import statsmodels\n",
+    "import statsmodels.api as sm\n",
+    "import statsmodels.formula.api as smf"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "gapminder = pd.read_csv('gapminder.csv')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "gdata = gapminder.query('year == 1985')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "size = 1e-6 * gdata.population\n",
+    "\n",
+    "colors = gdata.region.map({'Africa': 'skyblue', 'Europe': 'gold', 'America': 'palegreen', 'Asia': 'coral'})\n",
+    "\n",
+    "def plotdata():\n",
+    "    gdata.plot.scatter('age5_surviving','babies_per_woman',\n",
+    "                      c=colors,s=size,linewidths=0.5,edgecolor='k',alpha=0.5)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Setting up model plot"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def plotfit(fit):\n",
+    "    plotdata()\n",
+    "    pp.scatter(gdata.age5_surviving,fit.predict(gdata),\n",
+    "               c=colors,s=30,linewidths=0.5,edgecolor='k',marker='D')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Three models from last video"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "groupmeans = smf.ols(formula='babies_per_woman ~ -1 + region', data=gdata).fit()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "surviving = smf.ols(formula='babies_per_woman ~ -1 + region + age5_surviving', data=gdata).fit()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "surviving_byregion_population = smf.ols(\n",
+    "    formula='babies_per_woman ~ -1 + region + age5_surviving'\n",
+    "            '+ age5_surviving:region - age5_surviving + population',\n",
+    "    data=gdata).fit()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "plotfit(surviving)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "plotfit(surviving_byregion_population)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<matplotlib.collections.PathCollection at 0x1d984660dd8>"
+      ]
+     },
+     "execution_count": 22,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "pp.scatter(gdata.age5_surviving,groupmeans.resid)\n",
+    "pp.scatter(gdata.age5_surviving,surviving.resid)\n",
+    "pp.scatter(gdata.age5_surviving,surviving_byregion_population.resid)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "1.4979520263709156\n",
+      "0.9423025333008321\n",
+      "0.8480227300570339\n"
+     ]
+    }
+   ],
+   "source": [
+    "for model in [groupmeans,surviving,surviving_byregion_population]:\n",
+    "    print(model.mse_resid)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "0.6364676965596588\n",
+      "0.7726009080146058\n",
+      "0.7999775707885213\n"
+     ]
+    }
+   ],
+   "source": [
+    "for model in [groupmeans,surviving,surviving_byregion_population]:\n",
+    "    print(model.rsquared)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "103.88003937611684\n",
+      "150.3418060343098\n",
+      "86.48787556725166\n"
+     ]
+    }
+   ],
+   "source": [
+    "for model in [groupmeans,surviving,surviving_byregion_population]:\n",
+    "    print(model.fvalue)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<table class=\"simpletable\">\n",
+       "<caption>OLS Regression Results</caption>\n",
+       "<tr>\n",
+       "  <th>Dep. Variable:</th>    <td>babies_per_woman</td> <th>  R-squared:         </th> <td>   0.773</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Model:</th>                   <td>OLS</td>       <th>  Adj. R-squared:    </th> <td>   0.767</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Method:</th>             <td>Least Squares</td>  <th>  F-statistic:       </th> <td>   150.3</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Date:</th>             <td>Fri, 28 Sep 2018</td> <th>  Prob (F-statistic):</th> <td>8.26e-56</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Time:</th>                 <td>14:45:56</td>     <th>  Log-Likelihood:    </th> <td> -250.30</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>No. Observations:</th>      <td>   182</td>      <th>  AIC:               </th> <td>   510.6</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Df Residuals:</th>          <td>   177</td>      <th>  BIC:               </th> <td>   526.6</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Df Model:</th>              <td>     4</td>      <th>                     </th>     <td> </td>   \n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Covariance Type:</th>      <td>nonrobust</td>    <th>                     </th>     <td> </td>   \n",
+       "</tr>\n",
+       "</table>\n",
+       "<table class=\"simpletable\">\n",
+       "<tr>\n",
+       "         <td></td>            <th>coef</th>     <th>std err</th>      <th>t</th>      <th>P>|t|</th>  <th>[0.025</th>    <th>0.975]</th>  \n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>region[Africa]</th>  <td>   18.2658</td> <td>    1.168</td> <td>   15.639</td> <td> 0.000</td> <td>   15.961</td> <td>   20.571</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>region[America]</th> <td>   17.0859</td> <td>    1.315</td> <td>   12.990</td> <td> 0.000</td> <td>   14.490</td> <td>   19.682</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>region[Asia]</th>    <td>   17.8647</td> <td>    1.279</td> <td>   13.971</td> <td> 0.000</td> <td>   15.341</td> <td>   20.388</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>region[Europe]</th>  <td>   15.8722</td> <td>    1.352</td> <td>   11.739</td> <td> 0.000</td> <td>   13.204</td> <td>   18.541</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>age5_surviving</th>  <td>   -0.1419</td> <td>    0.014</td> <td>  -10.294</td> <td> 0.000</td> <td>   -0.169</td> <td>   -0.115</td>\n",
+       "</tr>\n",
+       "</table>\n",
+       "<table class=\"simpletable\">\n",
+       "<tr>\n",
+       "  <th>Omnibus:</th>       <td>13.021</td> <th>  Durbin-Watson:     </th> <td>   1.947</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Prob(Omnibus):</th> <td> 0.001</td> <th>  Jarque-Bera (JB):  </th> <td>  18.362</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Skew:</th>          <td> 0.443</td> <th>  Prob(JB):          </th> <td>0.000103</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Kurtosis:</th>      <td> 4.279</td> <th>  Cond. No.          </th> <td>3.25e+03</td>\n",
+       "</tr>\n",
+       "</table><br/><br/>Warnings:<br/>[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.<br/>[2] The condition number is large, 3.25e+03. This might indicate that there are<br/>strong multicollinearity or other numerical problems."
+      ],
+      "text/plain": [
+       "<class 'statsmodels.iolib.summary.Summary'>\n",
+       "\"\"\"\n",
+       "                            OLS Regression Results                            \n",
+       "==============================================================================\n",
+       "Dep. Variable:       babies_per_woman   R-squared:                       0.773\n",
+       "Model:                            OLS   Adj. R-squared:                  0.767\n",
+       "Method:                 Least Squares   F-statistic:                     150.3\n",
+       "Date:                Fri, 28 Sep 2018   Prob (F-statistic):           8.26e-56\n",
+       "Time:                        14:45:56   Log-Likelihood:                -250.30\n",
+       "No. Observations:                 182   AIC:                             510.6\n",
+       "Df Residuals:                     177   BIC:                             526.6\n",
+       "Df Model:                           4                                         \n",
+       "Covariance Type:            nonrobust                                         \n",
+       "===================================================================================\n",
+       "                      coef    std err          t      P>|t|      [0.025      0.975]\n",
+       "-----------------------------------------------------------------------------------\n",
+       "region[Africa]     18.2658      1.168     15.639      0.000      15.961      20.571\n",
+       "region[America]    17.0859      1.315     12.990      0.000      14.490      19.682\n",
+       "region[Asia]       17.8647      1.279     13.971      0.000      15.341      20.388\n",
+       "region[Europe]     15.8722      1.352     11.739      0.000      13.204      18.541\n",
+       "age5_surviving     -0.1419      0.014    -10.294      0.000      -0.169      -0.115\n",
+       "==============================================================================\n",
+       "Omnibus:                       13.021   Durbin-Watson:                   1.947\n",
+       "Prob(Omnibus):                  0.001   Jarque-Bera (JB):               18.362\n",
+       "Skew:                           0.443   Prob(JB):                     0.000103\n",
+       "Kurtosis:                       4.279   Cond. No.                     3.25e+03\n",
+       "==============================================================================\n",
+       "\n",
+       "Warnings:\n",
+       "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
+       "[2] The condition number is large, 3.25e+03. This might indicate that there are\n",
+       "strong multicollinearity or other numerical problems.\n",
+       "\"\"\""
+      ]
+     },
+     "execution_count": 26,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "surviving.summary()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>df</th>\n",
+       "      <th>sum_sq</th>\n",
+       "      <th>mean_sq</th>\n",
+       "      <th>F</th>\n",
+       "      <th>PR(&gt;F)</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>region</th>\n",
+       "      <td>4.0</td>\n",
+       "      <td>3927.702839</td>\n",
+       "      <td>981.925710</td>\n",
+       "      <td>655.512121</td>\n",
+       "      <td>2.604302e-105</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Residual</th>\n",
+       "      <td>178.0</td>\n",
+       "      <td>266.635461</td>\n",
+       "      <td>1.497952</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "             df       sum_sq     mean_sq           F         PR(>F)\n",
+       "region      4.0  3927.702839  981.925710  655.512121  2.604302e-105\n",
+       "Residual  178.0   266.635461    1.497952         NaN            NaN"
+      ]
+     },
+     "execution_count": 27,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "sm.stats.anova_lm(groupmeans)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>df</th>\n",
+       "      <th>sum_sq</th>\n",
+       "      <th>mean_sq</th>\n",
+       "      <th>F</th>\n",
+       "      <th>PR(&gt;F)</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>region</th>\n",
+       "      <td>4.0</td>\n",
+       "      <td>3927.702839</td>\n",
+       "      <td>981.925710</td>\n",
+       "      <td>1042.049316</td>\n",
+       "      <td>8.236854e-122</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>age5_surviving</th>\n",
+       "      <td>1.0</td>\n",
+       "      <td>99.847912</td>\n",
+       "      <td>99.847912</td>\n",
+       "      <td>105.961630</td>\n",
+       "      <td>9.003514e-20</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Residual</th>\n",
+       "      <td>177.0</td>\n",
+       "      <td>166.787548</td>\n",
+       "      <td>0.942303</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                   df       sum_sq     mean_sq            F         PR(>F)\n",
+       "region            4.0  3927.702839  981.925710  1042.049316  8.236854e-122\n",
+       "age5_surviving    1.0    99.847912   99.847912   105.961630   9.003514e-20\n",
+       "Residual        177.0   166.787548    0.942303          NaN            NaN"
+      ]
+     },
+     "execution_count": 28,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "sm.stats.anova_lm(surviving)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>df</th>\n",
+       "      <th>sum_sq</th>\n",
+       "      <th>mean_sq</th>\n",
+       "      <th>F</th>\n",
+       "      <th>PR(&gt;F)</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>region</th>\n",
+       "      <td>4.0</td>\n",
+       "      <td>3927.702839</td>\n",
+       "      <td>981.925710</td>\n",
+       "      <td>1157.900225</td>\n",
+       "      <td>1.132132e-123</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>age5_surviving:region</th>\n",
+       "      <td>4.0</td>\n",
+       "      <td>110.113541</td>\n",
+       "      <td>27.528385</td>\n",
+       "      <td>32.461848</td>\n",
+       "      <td>3.514845e-20</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>population</th>\n",
+       "      <td>1.0</td>\n",
+       "      <td>9.813987</td>\n",
+       "      <td>9.813987</td>\n",
+       "      <td>11.572788</td>\n",
+       "      <td>8.313090e-04</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Residual</th>\n",
+       "      <td>173.0</td>\n",
+       "      <td>146.707932</td>\n",
+       "      <td>0.848023</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                          df       sum_sq     mean_sq            F  \\\n",
+       "region                   4.0  3927.702839  981.925710  1157.900225   \n",
+       "age5_surviving:region    4.0   110.113541   27.528385    32.461848   \n",
+       "population               1.0     9.813987    9.813987    11.572788   \n",
+       "Residual               173.0   146.707932    0.848023          NaN   \n",
+       "\n",
+       "                              PR(>F)  \n",
+       "region                 1.132132e-123  \n",
+       "age5_surviving:region   3.514845e-20  \n",
+       "population              8.313090e-04  \n",
+       "Residual                         NaN  "
+      ]
+     },
+     "execution_count": 29,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "sm.stats.anova_lm(surviving_byregion_population)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.5"
+  },
+  "toc": {
+   "base_numbering": 1,
+   "nav_menu": {},
+   "number_sections": true,
+   "sideBar": true,
+   "skip_h1_title": false,
+   "title_cell": "Table of Contents",
+   "title_sidebar": "Contents",
+   "toc_cell": false,
+   "toc_position": {},
+   "toc_section_display": true,
+   "toc_window_display": false
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/Hypothesis Testing in Python Statistics.ipynb b/Hypothesis Testing in Python Statistics.ipynb
new file mode 100644
index 0000000..931538f
--- /dev/null
+++ b/Hypothesis Testing in Python Statistics.ipynb	
@@ -0,0 +1,95 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Python statistics essential training - 04_04_testing"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Standard imports"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import math\n",
+    "import io"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "\n",
+    "import matplotlib\n",
+    "import matplotlib.pyplot as pp\n",
+    "\n",
+    "%matplotlib inline"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import scipy.stats\n",
+    "import scipy.optimize\n",
+    "import scipy.spatial"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.4"
+  },
+  "toc": {
+   "base_numbering": 1,
+   "nav_menu": {},
+   "number_sections": true,
+   "sideBar": true,
+   "skip_h1_title": false,
+   "title_cell": "Table of Contents",
+   "title_sidebar": "Contents",
+   "toc_cell": false,
+   "toc_position": {},
+   "toc_section_display": true,
+   "toc_window_display": false
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/Logistic Regression.ipynb b/Logistic Regression.ipynb
new file mode 100644
index 0000000..c656fdf
--- /dev/null
+++ b/Logistic Regression.ipynb	
@@ -0,0 +1,577 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# The Engineering World - A Place For Learning And Exploring\n",
+    "\n",
+    "## Logistic Regression"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Standard imports"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import math"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import matplotlib\n",
+    "import matplotlib.pyplot as pp"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%matplotlib inline"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import statsmodels\n",
+    "import statsmodels.api as sm\n",
+    "import statsmodels.formula.api as smf\n",
+    "\n",
+    "# fix error in some versions of statsmodels\n",
+    "import scipy\n",
+    "if not hasattr(scipy.stats,'chisqprob'):\n",
+    "    scipy.stats.chisqprob = lambda chisq, df: scipy.stats.chi2.sf(chisq, df)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "smoking = pd.read_csv(\"whickham.csv\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "smoking = smoking[smoking.age < 65]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "color = np.where(smoking.smoker == 'No','skyblue','coral')\n",
+    "jitter = 0.05*(np.random.rand(len(smoking)) - 0.5)\n",
+    "def plotfit(fit):\n",
+    "    pp.scatter(smoking.age,smoking.outcome + jitter,c=color,linewidth=0.2,edgecolor='k',alpha=0.5)\n",
+    "    pp.scatter(smoking.age,fit.predict(smoking),c=color,linewidth=0.2,edgecolor='gray',marker='d')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "smoking['outcome'] = 1*(smoking['outcome'] == 'Alive')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ols_group_age = smf.ols('outcome ~ smoker + age', data=smoking).fit()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "plotfit(ols_group_age)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Intercept        1.264665\n",
+       "smoker[T.Yes]   -0.038738\n",
+       "age             -0.009615\n",
+       "dtype: float64"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "ols_group_age.params"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>df</th>\n",
+       "      <th>sum_sq</th>\n",
+       "      <th>mean_sq</th>\n",
+       "      <th>F</th>\n",
+       "      <th>PR(&gt;F)</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>smoker</th>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.899981</td>\n",
+       "      <td>0.899981</td>\n",
+       "      <td>8.181417</td>\n",
+       "      <td>4.314608e-03</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>age</th>\n",
+       "      <td>1.0</td>\n",
+       "      <td>17.713821</td>\n",
+       "      <td>17.713821</td>\n",
+       "      <td>161.030213</td>\n",
+       "      <td>1.806638e-34</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Residual</th>\n",
+       "      <td>1068.0</td>\n",
+       "      <td>117.483303</td>\n",
+       "      <td>0.110003</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "              df      sum_sq    mean_sq           F        PR(>F)\n",
+       "smoker       1.0    0.899981   0.899981    8.181417  4.314608e-03\n",
+       "age          1.0   17.713821  17.713821  161.030213  1.806638e-34\n",
+       "Residual  1068.0  117.483303   0.110003         NaN           NaN"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "sm.stats.anova_lm(ols_group_age)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>0</th>\n",
+       "      <th>1</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>Intercept</th>\n",
+       "      <td>1.198828</td>\n",
+       "      <td>1.330503</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>smoker[T.Yes]</th>\n",
+       "      <td>-0.078622</td>\n",
+       "      <td>0.001146</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>age</th>\n",
+       "      <td>-0.011102</td>\n",
+       "      <td>-0.008129</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                      0         1\n",
+       "Intercept      1.198828  1.330503\n",
+       "smoker[T.Yes] -0.078622  0.001146\n",
+       "age           -0.011102 -0.008129"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "ols_group_age.conf_int()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Optimization terminated successfully.\n",
+      "         Current function value: 0.346766\n",
+      "         Iterations 7\n"
+     ]
+    }
+   ],
+   "source": [
+    "logit_smoker_age = smf.logit('outcome ~ smoker + age', data=smoking).fit()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXcAAAD8CAYAAACMwORRAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDIuMi4yLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvhp/UCwAAIABJREFUeJzsvXeQJNl95/d56SrL265qb2e6x7udmZ01g3XchSUBLLAAsTiSIAkCIfB0R/EiFLo73R1DClE8HckQKVIiQSMecDyCBEFgCQ8u1tvZ2ZkdPz09Pe27urq8r0r39EcNZgEBPAK4hSBu1Ceio6Mz82U+k+/78vd7v/daSCnp06dPnz5vLpQfdwb69OnTp88bT1/c+/Tp0+dNSF/c+/Tp0+dNSF/c+/Tp0+dNSF/c+/Tp0+dNSF/c+/Tp0+dNSF/c+/Tp0+dNSF/c+/Tp0+dNSF/c+/Tp0+dNiPbjenAqlZKTk5M/rsf36dOnzz9KXn311YKUcuAfuu7HJu6Tk5OcPn36x/X4Pn369PlHiRBi5fu5ru+W6dOnT583IX1x79OnT583IX1x79OnT583IX1x79OnT583IX1x79OnT583IX1x79OnT583IX1x79OnT583If9oxV1KSblQoN1s/kBpSsUirVbrDcmD1e1SLhTwPO8Nud//V3Q6HWzb/q7ja5tZnj99lmK5/F3nut3u90yT297muVfOUKvV/qvz5TgOGwtXyN5Y+L7rVErJjeUVltfW+X//y0gpJa7rfs90xXKZcqXyXcdbrRZLa+u02+0fvABvAFJKcqvL5FaXv6s8bzS5zU2y6+s/UJp6tUK1VPqu461Gnc3r89RKxe847nkeL756jmdOvYplWd+V7v+vfUdKiW3bP/I2+FEiflyZP3r0qPxhFzGtL1yh9PhnCbeL2KjUBndy8JGPouv635vmwumXuf6Z3yPQqSOFQi01yXv+5W9gGAZSSq4uLlGu1tgxMUY6lQSg3WhQOPcSsrQJmo4ysoOR/UcB+NLffJaL84sYeHiGn4dO3sHB2++g2WrxzIUFttoOKpK5ZIjj++YQQnDxhad57a//FMO1cGNpHvjor5Iem6C4lWXhsf+b7ZVlDF0lMXeIoz/9SyiKgm3bPPYn/wet3CZjh09w70++DyEEUkr+7rHPsbiwgKaqHLnjTm67424AVm4scvHrn8dntehGUrzlfR8mHImSyxf43IvnWNouI5AcGMvwyL23o+s6v/1H/xFfJE4wEKBSqxFVJb/46CNUa3WePHOB9c0cAsnczmnecnAPmqbxmSdeYEsG8MWSdAo5dkcU3nHXUWzL4ulP/yFXr1xGVRQOnriTO977KEKIv7d9Vq5cYv6P/iemtC6uFCyLMMf+u98gOTTM4rUFXn7hGRzLwef3cfK+BxgeHWN1dZUXT71Kud0FJMmAn3tO3kk6nWbr2iVql0/RLmwTHBwhuvcEA1M7KJTKPHbqItsdF0UIMqbCe+88RDQc5svPn+Ll02cJeBZt1c/J24/wE7cfuZVHz/MQQnxHOU6/+DzZV5/DsFpYRpCRY2/hyO0ncByHP/vzP2ep1bt2OgA/9+FH0TSNpaVlTj/7JHRb4Atw2933Mj09Ra2Yp3L6SYYUCyEEWVcncuReogNpimvLtBfOobRqeP4w5o6DpCamcByHr//O/4y2chGBpDs8x0O/8u/wmSZWt8v2/PleGjNManYfZiBAOZ9j/i/+T6LFJRQBlegIkw9/jMzEVG+wXN+kUGsSC5jsnBhFURTajQbZlx6nvXQZRUr0sZ1kbn+AcCLJ0ivPIS8+R8Tr0hAa3enDzN7zdlY2NvnyhWUCYztQNY3K6nVOjsY5vGeWheU1nl9Yo4WGgcOR0QGO7N6JlJLLLz7NpXOv4TguO+fmOHz/29A0jUqtzvxmgYYj8SkwnYownE7dagvLsnBdF7/ff+vYZr7AwnaVpguGkExE/ewcH+n173abG9k8nicZScVIxKIA5FducPWlZ7BdFzzJxO69zNx2B1JKslcuULt6Bs/qEJzew/ChE+iGwXahyJMXrlN1wKdIbhtPs2/n9K33Jrd0Hc+2SE3M4Pu2/P0wCCFelVIe/Qev+8cm7o7jcOa3/3t2BARC1ZGei3RsFgf3c/yDv8jWtUs4K1dR7A5uOEls7zH8kSj/+Z89SmLnfpT0GG63g7oxz7YNH/yXv86fffIPSdMiqqtstF0CE3O8/30PM//YpxkqL6N2m0ihYJlhmoce5MzCCpVr5zia0DE0jXKry7Mll1/4p/+cr5y7gTs4jXZzoOk26kzLMlp+ldY3/iNxnw9DVek6DvPVLu//rU/x5f/wP1KSBqoiUFQNrA5jYyMceOcH+ZN/+6soY7tRoilkbhm1UeBXf+dP+N3f+k1qwRRGchjpuXQ3Fjk4McT+/XvZ/MzvsitqID0PoSg8X5a8/V/9B/7NH32GRjBFJD2ElJLK2hJ7ohoBp4UeTaGrAiEUPOlRqTc4ODnI5YVlut0upY6NgiQRMBlIJogmB7hIHMUMYLWa+IIh7Eqed4wFefrTf0B9ZB+h8R1IT9JYvMCEV+HRX/3XPH/2Ii8sbdF0IaYr3L97nP2zMzz28Xdxe8pAvymctid5rq5x9Ff+V774+FOExmbwNB+K3aa+NM/PPPoBPv2Xf0MNnYHBITwpyWc3GQlpvOcn7uPCZ/+Yhh5CBMLIZo2o7HDw0U/wx0+8QkEECaYHkZ6kVdhiTO1yYDzNq197jLviAr+m0bIdni0L7n//B9k9Oc7lr32O6uXTICC+93Z2v/W93Lh+na2/+yxGt4buWtiqgW1GGHrbh/jLbzyFcuAezFAEgE6jhnfhaT76/nfzzF/8KXFdYbtaYyAapmJL7v7AR3DnX0HZuIZo9awg6Y/gDe8gdts9dF/8MoWNNcpti6jfIDM8inb8bTz+O/+Ow1aWoXAAgO1Gm1MyxsO//kes/N3nUMpbVGp1oqEgIp5h6P738uLv/hsOtNeJGSpCQKXrcE4kueff/j5//dTLFLUQqj+E22kR7pT5wD3HOf/Fz2Bmr6MKiZASWyg0w2mm7n0X5c/8Nm67QUM18Tsdgn4T+dBHeKrgIiSESisIz6URHaEpdD54fI4//ruXCSTTvU4toV2v8J5DM6yff4V8qUpyII0Qgkq1iuzUec/PfpQvnrlGOxDHlqACptXgvpkMsXCQp069xlqxhOcJ0tEA9xw9hK6pPL+Ux5/4tgGg3WKn38PQNZ66uMh2rYnneUSCfu7cOc5YMsKTX/gs4em9KErPsdHYXGZ2bg7aDSrPPEZVDSJVDX+7TGjHPna961F+86+/TjQaw/BsHKFSs1zeuX+SyYE4m09/EbO8iYKk7YsSvf0B0tNzP5RuwptY3F97+nGiL/4N1VodTdp4CIQZoKKHmf3pT9B97VmuND2a6IwoFqmwyelsHaVeJDi+E0f2fFEqHisvPYW65zgz1JHy5heZ9NiuNZi44z6mz3+VjPm650pKyQUvwlMrJd46HuXbP0QrrQ5P1A2iD3yAtaVl2o4DnkcqNUDKp9D+i/+N2+PgC8eRug/RqdGo1XnaimL6fBwYThFIJJGOw3Z+mxtbRVqKgXb4AcyhCTwJqpCUz73IkFdj3TdAetdBpNazPBTHInfmOW73NTihlHEQIARCekjX4xv6JKfCs0zddufr5fEkC09/hTGnTDw9hKxuY+LSEDqB1BDrNxYQZpDgwDAD0TCehK1CkXZ2icy+YxQvnYFGCSUYQdbLiJGdRBMxKrkco/tv61lSEizbZv3lJ3nv+x7mCwtFAnaTEDY1xU8bhZOBFiNf/306vjBZcwAhXSasAvlymfkD78bYdYzS1iaiVUOJJonEktjzL5NzTaJ+nVCrhATakQyFUoW3DJq0UBG+AEJRkZ6H26wRNFS+LkYZ3X8cvtV2EtbOPE9y9QzvSnqonovnuSiKii1UvtoM8paEILV6lrSpghTkui7FmRPk2jbD2UvMBlUUBTwPrjZdVlJznE0cID4+g7z5kggpKa9eZ7aygL+8wXDQYCgWZqtSZ71h4QyMc4wCe0wb9aaouJ7H1baK2HcXZ597lurIblxfCM1qElq/xG0n7mTrs7/H3kyUhmqChKDscn27QuCD/4L2y18j7rRI+TVKXYcCJvE730H7C7/H0XToO/rVQrnF/AOfIJuaxR+KYFsWmqFjdzqMtTaRj3+aWdMD1wYJQtPYsFXy4UEClS286UMYph/HtnGWLoBmcDk+yyFZwm1WUZAIf4TrgWHq3S76xF78gSDdbhfDMHAdB2djASN7ncmZnXQ6baQE0/SR3dxg7PBxlrQ0zoVnSbTy1PUQ7v57GNO6dApb3Cg1cbodEKDpPoLS5uTdd1E04xSqDWyv138SoQChboWrV+bZMmKEBoYQQtCuVvA2F7kjbdJQ/eRsQRsNHY+0IfHX8zSvnKatB0nKFornUtWCOPUKzv57aOohYn6DTqeDbhhIBNmtHG+NO2xdfY2qP4kjVKLdKjHT4OjH/wc07Yfb/eX7Ffcf294yPyybW1vYxTw740GE6GW/bVtcyuYwL5zhGwUfVnIMdJ2zjRrDK9fYun6Vg8fvoCEMhOHr9UKnSyuaQd3eJB8NUQ8NIFUdrdsgrnV46qtf5rZxuFz12NbCqJ7DjNpCtUsk6CKlR7fZxHNsVDNA1O/DWc5y5eIlUnMHiQZDSKC2tU5h4RpTbhd3aB92bACEAM/FWbtO9sw17j1xnOhgz1TEgNGJEEvlNhVfkohUSC6/RlDaVBQThqZ58kt/weEP3YMXSfXuhcBzbaxQAnvzGtZgqGcBAB4gpcX5M68w9EsPg5Q4zTooKlogiJlMUzx3kd2mzUTUD0IHz+P8xgJXXz3Fgfveys6IjqH0/KWRZJAzWZUrT32N5Mxu4kfvw/D56LRbFF97jouvvsRdD/8M7vYqkXYRTyi0QxkYGOWxF88xrbbZFQQhBJ7jcbal85knXuEhJUR49/1E/D4AFusNKi9/nWytxcDzX+IOtUJMg1JO8KqaZrvlEg20Oara+MM9M7feWOKJJtzYEKR37kX1B/HkzSpSNC6cf5XgyduxujfnHATouoERTWLkV9BiGQxFoOkKjushPA99Y4F2rsrGyCyLqXGklASKq3jnnqWsRLgvrfSEXUpURbA7qPDS5XPwwAmE4UNVVABcz0X6gixducD79k5g+nRcCeloiKjf5utL1/ENKdiKSqnc81uHYgn8lscLr51jefggjtDQGg1s3Y8+cpjCs89zm65RDI+g6732LrkO/nqXp770eX4y2sX0LJyaSxAVn27z8svPsle6PLttcSUyhUQwVV1izucxv55DI0z5m39JtF2mZEQQe08gdJVUrczV0AzW8CRCKCj5VYLVRV5dLnHy/odQVA3bk6BqGDsOcf30CwTrF4gZDYZ1D4Ek39gi52XZCk8RU3WqjkT1R+jaForr0W40CXiw3gU3PIJQFGhUCEfiPPnMC+x3C9ytV9E8C1eoXHhynuU9D7I4f5XU1C7CY7Moqko9n2VzY4XNzU1W3QLh3HXc0haEYtwYmGEqk2Cx0mJo/95buhKIxSk301zdXKCVnETzmWhCYkmVpa5HpNGlVapyNFbDsHpuwLBaZVmanH/1FfYcv4tuqULQ0Ol26nRQcVtVLq7O45veT1jX8ADXy3BjeZ7M/FWm9u77kekkfB/iLoT4U+BdwLaU8rtyI3oOyN8B3gG0gI9IKc+80Rn9FlWpMyQUELBpwZABPlWl7jp8cX4b/egDhKOJ3sVSsnxNoOQKrFsqYUXStroIzyUWMNiUPsx2l8i+fQQMA6REKoNkN31UNs7zpYKKvvPwLaE81ayhbV2n1Szh5DukVA9dVWjVquRsFTOaxhwYxgiGb32xRQZHqW0s0Qwk0ZKDiJudHXSMkRmqL19laGgYt9tGaZTxFA0RiRMJBrhiCd4qt4iEdUAHXK6Xl3gJFc8XwHJcpFABD0WCo5ss1B0mkgpZfQBb92N2a2S6W2y1bUL1MsnGFjFN4klJqa7jdTuEujVSvkHOlzu0hUEMi5kAdKolxiJ+TO116yWkKSR1j7Lnktl9kJAqENIiaOooB+9i5cxLyGuvcHDAh+I3ALBbq+RyVUQoyu6JGJ7r4jg2mm5wKGBzTlWpDe1lxO+7ZQ3FwyGW0zupL8/z4Z0h/LoPIQRRUxJtZvnfl+vs25EhEB2/5QOPGCZjuQVyxEn6grSliiclCgLDDFJ1oN2oYsZT6IEgAI5t02038Ypb6DsGcFtthHTxhIpmmNQ3l6gfPERi+gDBb1VCNE6+3qJzY55GLI2nmwhNRzo2it3B367QqhTITM/eshBUqdIq54mqCj6fjrx5QiIwDB3hdKnUbHzZHGGz59LLl/OU/ANcMzJErBWOORskNUnZEbyiDJIXQbJ6lHHT4Fv2t64aXFMi2M0WoWCHqP6ttnOp2w1qxSxfaYYIP/hhwrE4ADfqDc58/T/hVwShJz7FXNhEhqOIdoHiC3/FxuQx6kaayaGdNDsdJC7B9CTz9Q4i6VBxIKT25oEE0HQ8GpEhpnPnmBkK4bkeUkrGNZVyfpUFNUnHg6DioHXruAi6mkG3UafZcYikRrGaTTyrSzCR4dqlLSK1HHcam8RullQAR2SLjQvPICLTREcnbxljkfQQ3VaLb37ty0zHgzQTg5iD07TrVdSrL5Jr7kQq3z0/F4inOPfC15m7e4aAcnOiV4AuBAvZIjtaZTJhk3yzgetJhiIB6p0WzVIdp1ogPjAIgOkDrdslu75IORhCqBEaZgKpaBitKrHkOCtrqz9+cQf+DPg94FN/z/m3Aztv/twO/F83f/9IaFWLFFLTlHI3eO7Qowinw90LX6UdH6YcTjMRTdC6dgbhefh3HSU+vZsLZ5+nVu0ykZ6kW8zhdTpktShF4ScUTqJ5Do1Sla1Gmx3pFG4ojjE+x4JPJ9O2yRdyJISNMjhONjBJrHKBDUvl1NA+yrZG2ioTXr1AZWyA+NAort1F3owCUFQNIxCiFUrhCQWkvDUh6qo6cnCSzbVljvqahDQFT0JxM0ehbTLo1oj4hr+j/FNhg7iw2Vi4wvixe7C3V5G6Dy2aora1Qcuf4eXoTqYHU73hQEq+ei1AcszEPvsE0duOI6SCKiHhtVEXzxJQBE/WTVJzBzB8PrYbDZaunCaiCkL1PGuOi+WPI6RLoF0l0q4QjA8QUSUgkQg0PBKmRnBgmEx5GTl0AO/mQCY0Saq0jDCnaVZB3qyXbqeNkJJhH0RSadquh3pTqF0pUSMJpstZdBnofcUJAZ5HSINx0WBA7+16+i3XokQSFQ5nWw6xbJahbpGgtGgqPla1BF1/iEYhR2pyJ26nDQJUTadTK5MI+8hdv0Q6FmWlLRnzCzaLVSLhEJXUFDHXpdHpAhAyfVSSk+QXFlnVkwzoHkFdoyk0tgmQ98oYTpvKjUsEwzEAmvUKPreDGgxRaVkEdYVW1yLgM2jaLmY4ztbqKfZMDlDrWEgJiXCI88trdFMZHkq2iAUNBBDxQbKzySfLglxokLrtEtJ7dd10XHLhIdpr59AzMb7Nc4gmBO1Knvque0lHYng3RwQzGKSz9y0ol19iMDOEO7W7944C+sYSXHmZcmqcRKNBwqcigEqzSTWQQjUlN9oCs2uj+Ew8y8J2PZpGkJji0qqV8KsCRQjajkfS0IjEYnRWLqNMzoGmoUqJs3qVmN9gueRwI7tNbHAEVTNYy23S7XZJ5heJjSi40rjlajM9i4H8AtdjOxBSfkdZA8Egq4Use2fuxJ9Mo+o6hpbEMXS25y+gp3fg2jaKdlPkpaSRXSXhU3CyiygTsyg366Cez2K2yvjadV6raAyPzaJpGldym7j1bcajY4Rzi+TLBaKGQsuRyG6b8YDKFTVKNDqCoffqzfaZrDsu6e8RefZG8w+Ku5TyGSHE5H/hkncDn5K9HvaSECImhBiSUmbfoDx+B5o/zNL1Mlt7H+b+tSe5Ed9Jxxdks+IidBPH9dAMP2J4hualF9Fnj6ECyak52utL6LNHEJVtlHCCeHEbrVUmt75KJz6Cb3iYzfmXaEaG6VaLmFN7Ca29yvqeB8jWy4xtXSYfmiZiO7yy9724qKixBDdsiaFGUG6cp7R2g8TwOM711/BadZR9d9GtVbG1MOttGA6ofLNpcH+gy7kmRIJ+mlvraJMJrjUFg4BQLJxSkWAszcp2iWZsGFc30LtNIuUsISS+eoH45/89s5kEtuNwvtBAD0/iN/3UdxznXGEDU7g0hYl+24O0/+R/4aheo3pFITA0hWtb2JuLjFSX2AgMsWvvEVRFIJAEAwGUXUfRL5/n2so6Iz9xO8JxEQJkNE7u1BNogTa2FEjNuCW62B3c4gaxqd3UCjkUVUciwXPxBUMEYzFcp4sRDKHpBna3Q6dWJTWQpF7Kk4pO0XMygSvBa1TRNR1V01ivdWiqPiJeh8GAD5/po+QqRCoF0HsWgnAs6sKg5imk8gvEAwa6YaB3a7QrJV7eshmbMLjx4pOEhsZAQj27QtA0cGLD5Fp5LCXC4EiYlXKNutolNDrJalfF6igQuuk6q5fI2hobk7ezGvKjGw6FTgstEmClq7E2nmCgsIItBFWnN8jLah4zv4Ltj3JjfYNpUxL3KZRLLsuWQk4kmFVVzm0UGA71BOdcqYauaiQqq8SGh26JlwBCPp0pZxsnMMsFf5RALY9A0gwN0vV30HHJt21kKICCh0Sh3OnQrtUIpgaRCF4PEhUkRye4+NyX2Hv87tdFUkpCQ+PY167hc7sMB41bFkdGUylUq1QLBRpaiMyB4whVA8+lev0yspSj22rS9Pmp+aJIBIpdo1prEBp1iIVMCosXQPfj2R1SIT+O6qEmMiQHh7FcF9dtE04kkK1h1p8rYo9k0IXSE3Ih8BSVeruOrBdxyzkcXwgUBaXTpLO1StTwkUomARu708WnCJSAyZrrMTcQZjW7ihqJIwFhdQg0tjGcGqNKh+LyRRw9gOp0GdOBWpaqGWX3ngO9Dw0gMxXmuiNIZMaJFBY4HMrhdFRUJNttm5XIBJWGy6hp0LFsPCR+QyffaNII/NdFzHw/vBE+9xFg7dv+Xr957LvEXQjxMeBjAOPj4z/UwzzNQAsFmezmOWatMZSv8efT78F3/ik65XW6lx18c8fADOJLDJJ76Qnu2LeLfLuOkh5BiQ2AP4R99UU0zyGwepHE3BxtTXJk4Ss8PvEAu5ee4cWVFcYCkqtDB5kuL5ILD9HVDOK5aywkd5GZ3A9WB2V4Bjn/Mp2997Jx+RLK5VfxNi6T2H8SUSuzefU8cmOBdrfDS74xYkKi7ZjiiSunyGJS2cxy14Ewi5UOzx95FNlucN/Vv+WQ0eFLHUFmaCe1cpGWEmBiYIS1tkXDt8Jb6gsc2THGFzpxZrrbPDgdwLoyz7YeR7oO+vgctlAwPI9ufpOmbTPq15jrzFOfv4SuCDRN45t+k+1QBENVvsP9An6CA4PY6VG260081wVFRfVs2qkJ3OXLlLa3SIxNgwApFLavXUNUc6y7B9g1kMQw/Ugp6baa5DWLbV8Kt1NkQkqcTgtFUbkhwixaLfZWF6ilB/GHehN9jUoJKjmuyBBm0094Zj+uUCh5LueuniUXSNNsa0zEVSK6AggKtsKCbTCmuaRSAxjBMJ5r44vpZOpVhopbtKtlZk7ch2NZICA9Os7K899go2ZxYuckfk1BQTCWitMMhziz2sDTS9h7jvCt6nGDUazFaxjRFBtju6ldfY6406Hc1qjtOoFaP4/VrZPZcxvKzYHHs8fZ2lpBa1dJ65KQ00RzPUJSIa0HOVsoYlsWu0Yi6KI3JxH16Ty3WccVbQr1JuuBISx/GKPdYKSZRZUu+VaXaCZEd2oCCch6iXKuRCASw2412Oh00DQNx3URrkMsNUAuv4E6NvEdk8rV9SUsfwSkpN3pgPRACEzDIO9qHKqtYzPDt5yKnlAYrq3z8vwyu/afpLWxjKIqeK6HGQpRarVZcXQCSpiY4yKAhhrmkuWSz20R0UxGRid7E/5CoV4qkNvYwBrYiU/XCBjfypqgHIxSG5jgVKHKyUH1VhTLxXKHG8FhjNWLFNKjDFlldFy2jDjt6+fQ/GE6lo3pMzC0m3MfjoOtGUzP7WLz0gKl61k8JAHTx5F9B9jOXaV17VUCe09ihKM43TaNhTNQzxPOjCIB27ZxXQ+foTMyPsG5K0scTEC11aVjddA0najpo5LfJujPsHLjOonp3ag+k43lBYJum7XFH2x9wQ/DGyHu3yt4+XuG4EgpPwl8EnrRMj/Mw9rZVfKTJ/nwymOYeMx4ZY7lz3I6OUxy+xr67sNg9ryjcngH8VoZWVhCBjWUiRMAKD4/WmYKY+UrjKtdNoYP8da1JzhWu8JKa5briVn83cs06yX8UxF+4tLnmY/O8NTw3URWv8B6ahpnew1t1zEUTUcOTqOsXSFnphjXVOKjc6ixNF4gwkA5R96z0YensFYXUE7cx2DpBtnRWfS1JbT0CN3mJs/vegQjksCKpCgs+ZCdFs7cbjaaNmpyAnV8F0uXXqDpS9J1XOYGImxudVCPHGK5WWN34UXGfJDzBfDZbVqX51HMIJ7hR1cVGuh0mw1C4QCfit3NaOEa71ILuN0WplLGUBUsKZD0ImxMVaG1uYK39zijuStMmR6OJ1lwTNajw3QnDSJr56kUN3HNEEarQqxdoz5+mPnQFGmvSYaeWZvDZDkyhlpuwo7DtLavEpU2RdVPeXoPxRcfx/NHUOZfoqyHENIj6HWRgRh5kWZ9ch9TTo2oLig5sLrjJLkzLzA9NMJnqx0G2goSKNk+Mqkghc01/OYoqtsFoYDTxW+a2M0S0VQKq5wnXNsEBPXoCOFwhLDqoWg6LaHQdTx8qoJmKKidLNGgH2XzOg3XAwkBVSHq91FbPMuIv8nsUBToxUhfXT7FwsJ5Qve9H6+cu7VwR9N1QtN7UJ/9KyYmQ8SCqZ6AS4mv1SFBi7gO211JOdhzN8Va2yQNwdJmjXP7jzE4OomuqCBdLm2a3LjwNN3hAYrFLprVW8xnNSyMwACHdgepXX+KqaCGrio4nmClZjN45E5Kp16iMjpFPNNz+VUEDNAwAAAgAElEQVTLecTlFxGBMNfzFZKJBJ5hothdtktl6kIj08yiL56lEhnCEwqxRo7R6jJKIs2wXxDRNAQgUWi5ki1/CKEPMxDVMdwuAjBUg5AI8WSuyjvNFaTbwvKHUa02sWqesy2bgGtRrVTQjJ5F6NoWbqvGwI591GSFZysbBL0uHaHSSe7AcsKo5Sz78ucJCxekx4CS5aKuIuJR1kpVhmJhglqvXYuWQygxwHqljlWrEtq8iiaglRimbs9wo9xlOD1Dcv0qqgKu7SDDKbZDw0h8XOoY2LFBhK6jVLYJtLZx23WqTY+E3yATDtFxHMr1BqJj4YXHmZrdTaNawa44DI+MULSaWNs3fhj5+4F4I8R9HRj7tr9Hgc034L7fk/b2BsfdMjNeb3WhAI7XrjAfvYPa8C7kwPjr5qtQCPj9rJx5gcjDn0AxA7fuo2Qm0Md2sxlOMN3a5FjlMgI4ufEMazseQQ1HKex5kLuyp0g7NZLFsywM7GV95gjG1gpqZhzFMAFQk8PIagHTbpFOp1GGpnrPMEy0oSlaKwuIrWWmjt/LdHGBh65/iU8f/W9IBX3kux2eadVQ7p/hLWf/nPXYJJf2vI/wxV9HbTehY6DM3oZiBtGGZwiWi3QdSdfxOD15BCU1ApEkXyqsMSQ3GRgZo375FMaOQyhju+DKSzS31xlPJ0j4LV5peog9u9jIjHPt4l+RUF1KuQUK2U1ajQpKKI4vmsBeukS4lmU0f5W5sRTfqPlIWDmOpkxymxusGRHae+8mkV/C7zSox2LU546hLn4KdXiGs+EwZnULFwV7agThXKJ18QXSs9MEZ/bhAXGAYgG7vM2qbmHvvYsBt4kUghURoHrxFYIxH1N+QUTrxYvHTZh2YNkMsNW0yNzxEEIoCCQDtkPxxS/TdCR022imCXggoNtq0pY6o5Ust9UuE/T32q5WvMKpTggcm6rUUQNhdNNPu93GbdXwbJsADjsKlxj1gZSwbguuyiCzaovJ8iJdZRTN9ON02kxVVtnUbDYbdULDEwRDYQA6jTq1zTUi7Qbx4M2Iqd5LSjxg4jVyFAMh2rsfxAz2rJfVVpPO6cfx+x1ELEOt1UZXBLaUeOEk0VCQNSEYO3YfvnCvfqxmg9WXvsmJY7fRqi+SqxcQlosUCmpymKmpaazlKyhnPk/WP4RUBOlalp0jMRbPLVPp7kOPj6Eq4ElBsVQn2ipwwTX4ufYqEXcTJLRcj78qOyRCOiHhoolvfdNDUAG9VSUZkARCYaTslccnBOOyjZ63sAdnSNbWiHbzNNAoxYcItgocMhrkPQvNCPZcR3aHmcYajttE7jxMtTyE7bToKj6cxDCDCxdwAwazWoe43nMa1W2LVihAPZVmff4KTmYEXySK3WpS387ytgfv48uPf41josD0aG+QzZeXeOqrq5T0IGOT+xCqS6vTRTcMQKXdULje6XBsch8BVfQGskicV89b1Ko1BoaijIZ7kV4YOjFd8MJWHndYx27UCEWjCAS21cHnMyhr4TdADf/LvBHbD/wt8LOixwmg+qPytwPU0Em18t9hLvhxmChcYTZ3npn5b75+wmozu/Qs7WadxOZlPPv15c+ymGV29VmSW/OcXHny1v1GrDLHl55EmAEGSze4e/sVoLdo4u6VJ8CxicYzKJHXF0YAvcU8zRpaahTFDL5+fGCUicmdjA8OYoRjnFx+nJTX5LYbT6IMTuEvb1B56z9npHCNQ50V7sydQg+EqNzzKBGvhTo+hxLuRTUomUlUxSPgdXmmbqMMT7P76tdIl5dRx3az7WkcSIXwx1Mog1MouoEyvIPxTpHZwRR2vcTpHe9CHZxCGZri8fSduM06RTXETPYcanoCddftdKtF9nY32eh47DQstjeLMLGH0tjtdBs1hp0y8dXXcHQ/2eQQy0aSzsxRus0G0ewlOu0mmhnE08OIeG+Fo+fYHK4uYK5epJldpVEq0txcJrZ5nl2FS0zsPojuC1BJTVNNTOI3TUb2HSZWz5IwBJqioCoKmqowYECotgmxQfw+H8GAn0AggD9g4kbSxIXNla5OsVLDtbtsl6sseCFGDJf09jVSpkZIuISES9rUyFSW6UQzNPUQuhkABLo/QFUNYIVTRDcvMRPSMHUNv6GxI6gS3ZonPDLJlNZlpLRAcP0iI8UFpjWb+NgMwrbRg693YD0YRjgORiRJrd193baVUO9YqJEEWwO78IfCfGviwR8Mkc3sIh5PkDEkhipwUNAVhYwuUf0BQkMT+P0miuchPBfT5yM6OkVxK8eRu+4lffAOkrtvI33wDg7ffR+adChrUWbm9nBXSuVkXDC3exd5LUpsaJyxwTROboVuPou1tcxgPEJsZApjYIjTRYvz23UuFuqcKrSRiQwzUT/N5Xncm1aNlJLG+g3GdBu/8LCkwJW9ORRbguJYxNwO/lSGzo7jbEydoLnzBObQBP5WhXHNZq6xhG/jKvrGPFOV6xwOOQwPxFHWr2BmxnDH9qAPT2NUsowEdYbtKnGfghAKCIWQT2eGJu2N6/yLGY0TSglz7QpznSy/PCoxVy4y0lhnZnDgVqTVQDzGQa2JaNXo+KMU1TBdf5SKFqQVSqF5DonMEKstSa7jkeu4LDVdktO7MEyThqfeihYCqFouwVAETyjY1SIUNhDFDWRhk47rkjBfHwx/VHw/oZB/AdwLpIQQ68C/oxeXh5TyD4Cv0AuDvE4vFPLnf1SZBdixdz+LSxcYl3Uy9KIXLhMnr4aI5C6TWvWxOXKYTmKE6fknMEsb7B4fZGbrNc5kd8H4HjzbYmDpJbYcnfGojuZ85x4joVaB6fE97M+ewuD1vS9m2pvs72iULUlrZZDGrt5yf2l1mLzxHJdME1lYx8uMo/h6EyZeKYu2dAFZKHDA12DM6sUw31U4w4KRpqhJXN3kzvnP48djRDa5/fJjPJM+RrTbQU2N3nq+UBREPINPkaiH3kkIi/vWnmajeJXHTvwy7sH72BtTuBicQAv0hEVJDpGfu4sjzes8Kx2UoR0IRUUEwqjjsyxeTuGN3s6FSBh9cKrnZhrewbkbqwwcvhu7vM2ZXe9Ey0yB1ebJwjoT9XNMB1W6T36K6sG3oew6Qf3yywxf+DL1zDC2riNUBdVt4hZKKMO7UBSNAdHmeO4VVlvjvKiPc7d1g5nGGgVpMTm3G11VqJdLKIpCaHiaXG6bgdbTtIs5/MnMrXpo59ZJNkskx8fRWlXsm13KQBJKZQivOGjSozCyj2yjgjEaQ1+9SsKvc3g4SrXZRtNUpATHdTg8HOXV6G6uOR6x0goBr0tT9VFL7SYTnmDwwmM0yiXUQAgkuO06Q0qX1s79lEoGgcomaQUaHpTiIwTMMQa7Cu18FuVmO3itOhkD1OEJVp0CgWKNiKFQszzaRpDA8CBeKEax46D11p9hexKZGiXa6WJZNiHTwPMcFEXQsSWRSJR2MIgmPVy7gwBURRCJxmh7LaDD6OjrRrWUEi2cod5qcr0ZZToYRSiCpbrDdq2JGU8RjMbQO52eUJkahulHRBLssjfJ7DmMJxSklAwqgkwlz/Ndwe7GElvX6li+ILrdZrZTJDs2hlnP0e12CIYjCCHoNBrYjsvojjkq82dJ7DqCfnMhT2VlgYCpUwmmOBRR2Cud3jsvdK43U+w8cZzNv/lD1KvPQCQJ7QZurczshz7B2T/9LTzZi8ASN8vpdDuMJQYJ+Szu9sHdcfNWPWQdi6QOeD2LBnqLzHZmEpyrl2itL+INT6OEI1iWRaeQY18qyLZrkUpFaXYsJJIhQ6dT2mYonSKZibJQqWJIGwcFf2SAaLtKsLwBew9TkxJcFyORwHvlSe65/+QPLn4/IP/gl7uU8kNSyiEppS6lHJVS/omU8g9uCjuyxy9LKWeklPullD/S/3r9/kceoa3oXCZyy5+7qMQhPszI7sO0azV2XPsmvtIGqdWzZLpFJo6/hUZ4iN1Xv4rXqKBkFxnfPMOOmVmOPfSTXJOBWx9SWyJA1pfgnY98iMsiTkG8/lJcIk4hPoFvfCdHr30NWd4CILR6nuniVX7hFz/C29a+gZdbBsBzbLzsIrucPINRlTsLZ2/dS0Vy++aLjO0/yj1XPsdO7/XNum5rLrLn2hMYjRKh9Yu3jkspCWYXeN8HfxrPcThy9SvEvRb7GkvMLjyJdBy+ulRGib0uhEIIRCTB4MQ0Yv+DqInXzymZCTj2MHFFoo7N3RIiNTGEun8/e3ft5nSpjTo0herZCH8YZXSOomcz+9DDVFMTKCMzvTmM4SlUOrzv5z+O4rnYl19CGZpBy0xjv/Yc0YCPQiBN2KrxUmwv2t7jvKYO0WlUUWaPU6uU0AwfV+sON2oWqqaj4SF1k8zaWeTia1gbi7Bwhsz6a+jhCM3CFrrPJGzohAwdzTQR3SaD+48z2dwgcu0FIqVVYteeZ6Szzfixk4yMT7InEyXuU0mYKvuHE4xNTJMZHCQ0exDl+DtoHf8p1OPvIDCzj8nxcdxwiqDTItQsEG4VCThtvOgAB26/g/XYFHLuOJWxfTB3nNXoJHc+8CB6p8aYUyFezxKvZxlzKhhWg5/5pY+zrMQxR6ax05OYI9MsqzEe+blfoGtGUPxBpKbjqTqKP0TbCPJTH/4IlaUrlOtNbBQqjRblhUu8/UM/g1JcR1EVfD4Dn89AUVWczUXueuAhVn0JOjdD7izHZYkQUwePMm4VaXU6nHPCnLWC1CyX0eY6E6OjFDsO/lCYQCSCPxShZntEoxGkqpEWHUJ2g7DTYsBrYrkecweO4gWizMgyh91tZt0SmH5Gdx9g+Pi9mLqGU97GK+cwcEnsP87x++5H92y6rz1Fa/407XPP4K/lmDl2N8rMQRYsHcv18DzJUhvqo3uYnJjg4KP/lNDwBGanhhEKseuRjzK+ez+RiR00LQvXtnAsC8vq0gknmbrjPkqt7nfoh+t62OkJOkJHFb0QXg0PTYHNSo2HP/yz7PGKBLLztLdWUbPXmSxd58G3v51pv4csZQlgExAeSqNEpLTKve98mO1ak1QyQXRgkGQqjVBVknP72X9gP4GzX4eVK8jsDcSr3yCjOxw9etsPrYHfL+qv/dqv/cgf8r345Cc/+Wsf+9jHfuB0uq7T1X1cvlEgRIslguQjY3zoox/HPzSGungGt54jU17F7VRRhmY4+TOfYHF9HTW/TsOFmbWXSIxOE9h5kNnDx6h1OpSzG6To8Boxdv3kP2Fo527cYJztaxcYo0VF+DilD/Gej/8Kew4c5vIL38RvtSmH0pw4+xkWgxO8+598hP/03GskK5u0BibwSlkevPSfqR17D+Nze7GXL5MWvZdNAvNemPf9639P/tkvMsbruxC6CNbVINFkhjuyz3EjfQDXDJJZepm3XHuMez/xr2h97je5t714a3QeqG3QrFX4qQ88yoUrV/GSvbA96bkY10/xzre9jRcuziOSwz3zFRDtBk5uGVVaKFMHe6t3byKtDj91cJoroWnUkVn2nfsCRrNIfXQ/Xf8AP/uB9/Js3kHNTPTuFYxS86d49J0PcvrUy2hD06ipYRR/CBWbAwN+3vbwI/zV3z6Gc9f70QansDSdrQun+Ohv/D61cpl8qUIuPExX9xO1qkyMDBMdyJC9egGTDhdSB9mRu8CNapv7fv6/pbR8nY4ZxYjEQTeo53MMdUs8/NMf4qkLC0QMlbDsYplh1o0UP/1zv0Ddckg4TUaScTLxKELVsSb2MzYxwXyujBeIgu7D0XzQqvG2gztxJXQtC0fR6Oh+rGiG6MET7D16B20zyqVyh4oRZUOLsOPwceamxmmWi1RqdUw8dM/G7rSZmxjh4OEjjMzu5uUbm2y0XEqBFG/9wIcZGR0lW6mz5RmoholjBMmrEYbSA5y88wQhvx9l9SL+VoWw22Tu5IPsPHY33bV58sUqjqrhdTvI3BL7tCYHbjtGfGIHZSNGVfVjDc8ycug4mqZhdbsMrb6Kk10iUFxj1isSPnIfJ3/yYV48fQY7GMeSgroD1e0s773/JJdvrDAhOoR8OqbW23/oVNvHuz/+z9jeXEeoGnWpIUMxtNQQe3/i3cQnd/RivhHIcAxj5iBDd72NHTPTnC20cYwAfp+JHU7RyEzzyFvvR1cU6kO72PYPsB0cRN91jJQmmRzOEIwnGD54nIEjJ5k8fs+tVd26z49TL1OzXdpCxwsnGDh8F7vufoAr61u4hQ3Chkq5bXFRTXL4Ax9ldWsbUcnh0/4f9u48PKrqfOD499yZSTKZzEz2DchKEhZBkEUQBTcUF0Dcca1ara3UnxutdY1rrbtVW2tbW7WtOygqihtuiAKKIEs2ErLv20wmmcxyz++PCZMMAQmGReP5PI/P433n3ntOJuGdO+ee+57AcEq3z0eRN5wTz1pIckY2sV0N2BrLyIqO4JCZx5GclUtYt4uwlhrc7i7CvF3Ee1rJjrVw2Jz5VNQ30lVfic/np7PbQ53JxvG/WETWyBxqOtxEu9uI1TuJiE9m1knzSIiN2evct8Mdd9xRm5+f//Se9vvJ1ZbZwefz8dp9NzFyzllMmjwlGK8t2ETRZ+/jrC5l1JHHkzhxBra4eJwdHaz6fBXhXy7BYYgk/oTzOWLqpOADRe/ecz3DfK2En30DeWN6H0uuKSvD/ezttIgIJt/e+356PR6+u/dX1NoyMDpqOeH2vyKEwOlysebB37E6ew6R7TVkm7qZd/lvEULwWv7VHEM9sXgoIoqWOVcxbdo03n7xOcYXvBtM8N8SzaG3P0N3dzfb7ruSmuRD+ObQs5j/2YM0d3YzI/9p1uZfxhR6S696EHxIMt7ELEY2beGNo65HRCcRVrmJOd88Q8bvnuKd+2/GOWoGdXlHA5D59askJMRz7Pwz+eMr7yNGTgQCHwj+Tau45eLTufuFt7FHx3LxmsdoCYvmpcMX4a4sJNzVjD7uWLSo6GAf/A2VXHV4Jo+//QmGnCmEuZ34IizoPh/+rV9y62Xncvd/38QwaipCM6B3d+HduobbLzkDgLtfeBtD7hSkz4Mo+Zo/nD8fgDf+8yzfiVi0rEPxFX7F9FgTs+edhtfjYcVrL7HeZ0N3uzkiFo5bcFagimFXF19+8QVd7i6ioqKYfsSMYNXQ+tISfPXlICAsNYuEtMAN8LLqOtaV1uDyg80IU0YOZ0RyIl6Ph4o1n+IoL0QIDVtmHmlTZgZrg/j9fjo6OoiKisJg6B1L3fD111RWB6a8DU8dxoTJ318ORErJ599spKS5Ax2d7BgrsyYfGhwX7nJ10FpXR3RSEpE9N2r9fj/rP3qXmppaQJKclMjEY0/quRG4+3Y2f7wCSjeAlOjDRzHuxPkIIaipquSjjz+hw28gHC+zZkwna2QOXq+XF558BFtrFULqtEQlcvoVV2OPjsbr8VC3dQPetgaMUTEkjBqP2dJbu8bldOL3+7BF9yY0v9/PxqIyalvbSLBZOSQ7LVjNsbSqlroON34piQs3MjpzxPdWFJVSUrP5W6jfDn4femwKKROmBX8/zfV1VG5aT8zwDNLzRgePe+/113CWF4PuQ0Qncsp5FxMeHr6bVgJ9rl73GbK2DN3rwZg0nNhDZ2CxB/4NtNTV0NVYjWa2kpydF+yzlJLt1bV4fD7SkxOJiIjYbRsDMWQLh+1P7734b0449xf94p8/dR+pM+aQNW5CSPz1h/OxOeqZcv39WK29N888Hg+l915Os4hgxu1/Czlmbf5ljKWdlSRySv5fetvO/w1HU0c7Jj6z5HL64rsAePeRO5jQvpUNcePJbd6C+MXdZGRk8N5/n2Fc8fuk4AZgCzbSF/+F5uZmvM/czLrU6ZSOPYnZq5/A0NHKxPxnWJ9/KbFhRl6eeQNR7bVcvO4JVst4ci79A9X/uptPjvotxKRgqtzMrG+eY3L+P1mzZg3+T19lekcxAG/FTObU/7sZgLvfWIUxLVDdTkqJf9u33HLWbO5+7SMMmeOYtOY5HJFxFI89GX/BVwwzuamJH4MhJgljeyM+ewL++nIuHJPA1vJqvvZFB55DAPyNVVxySCKpqan86+Ul1CSMwhCdiL+hklOTNQ499FAAPvp0Fas9gdkul4xPJTW194neuro6/v7OZ1x71klERYUWylKUH0pKia7rIR/kB9JAk/tPdrGO/WFXiR3gyCtv7JfYAU67Lr9fYgcICwujJmMKI6+8s98xDWOO5lOSQhI7wLTr7qMIOwXYg4kdYM61t1OJhVnNX1NkiCcjIyPQ1/MvpQA7fqANE9vCU7BYLKSlpVEkojm55iOy1i9hREcNTZmBbzaVphhiPK2M2fouU4veoVmaCJ92Mh+/8E9yZTsjiz9GdjqYWfQmNry0t7fTtfyfHN6T2AGObl3PW/mLAEjb8h7SGfj2IBrKGbF5KQDDfM1EF37OzLrVzKxYSVjp11wwYxzpSSPA58XcXMlxa57G0NmO9Hux2+2sbewKJnYALX4Yz3z6LQDVxjgM0YHysFrCcN4sqAvu90V9F1psKlpiGs988m3Ie/qPlV9jGHsEj7z+ITu79/nXue/51/rFFWVPhBAHLbHvDZXcB2nnxL7Dsb9YRFJSUr/4KWdfyJz8J/vFbTYbmyNSiTv7mn6vGWdfzCckceKtj4bEpy5+iBKsFGJl7h/uC8ZPuv1xyrByVtPnFGBj9sW/BmDezQ9RiI3Z1R8zrr2IAqI5cs5cLvr9HRRjY0HtR4z85jXGd5RRShR2ux0joTU7TEhMSF596hGO6y5m2LYvkN5uJha9xzQ6aGtrY8LwVKaVvk8EfhJ9DiaVvE98fDzHzpqGr6qYiVvfYmLndkZvegvqtmO32wnr7kDv7r3vILucpIQLnnruP2hxycG4EAIRm0xxcTH3/etFtJTMngU0NLTULP72QiBh/+vVZWjJWWimcLTkTD76eFXwHJWVlciEEfjiRuxyVa67//7ffjFF+alRyf1H5Jwb72HMmDH94hNnzOTEna70ASwWCwWmZLzTTuv3WmXSGL4ggbGL7gmJt48/gUYiKMbGEYsfCMY9UxdQhYWzmr+gCCvTr/0jAMajzmF7bz1EirByYv6TxKWm40Pj7PI3id3wDie2rMXf8zHQ9f6zTPD2Puowo3s7qx+8AYCjKj9mRnNg1tDMulUc3rIBgN8tnIelaDUQ+NobVvglly04iSsvugC9rSHkZ5COZnJycvDZE9Es9mBcs8XTqAX6Wm3sHeLRYlP4oqn3g+PZVZvQEtMwJKXz8NLQq/r7nl+CGHkYD/x3ab/3dM03G9m0aWu/uKL8GKnk/hM3/+b7OXLO3H7xU369mLRLbyE+PvRhq+NPP4ct2CkNS8Ji6U3aM08+mSKs1BFOkSEeuz2QNA8/7jiKsONGo4UwSsICwyPHzDudQqwI4FfVb9OOia3EEB0dTRcafVfG9KDRjYkNqz4lT7Zi6Jl4apNeMlzVOBwOWlpaOGL7h0Q2lRNbtZFZFb1J19xajbE5cGPSVF3AqIieR/rb6tFdbVjriwhvqUZvayJJdvHi0jcQPcM40HO1H51ISUkJ/3ztTbSUrEBMMyBSsnjjg48AaGlpwZ+QhiE6ge6YYf3WUX2vrInXC6r35tejKAeNSu5D2O6Ks83O/ytzb/pTv/jUa+/jUxI549YHQ+In5j9JETYKsLHgpvt797/mjxQTGJYqwMoZ+YFho8NveJAibMH9irFxav7jRCck49vpT86HIDw8nPV/vonD9AYmFrzNtOJ3OIR23s7/DQC5Nes5tOAdpM/D5MLlmGsKAbjx0oX4arYxpeBtJhQsx1tTwuXnLuDcBfORPVf7Wmc7UkpkWwMjR46kFguaLS7YviEmie9aAnPB//LeV2iJgffMkJTOQ0s+CO7355ffDDz1m5zJ3159K+RnaGpq4q7nluyzhdcVZV9QyV0JstvtnJ3/512+Vhg5HMNR54bEoqOj2SpiWE8M9TlHBuNRUVGUaDE4MVJHBNXJgaml6bm5FJkS6O75s3NgpDp+FOHh4YShowFHNq9nvHMbRnTC0XG5XGR56jm2aS3jv3qOmc6tDKveEGzr8C1LmNK2haMa1zKteHkwPszXhqG6iCO//DvUlHBEfGCaXURnK3qnM7if7mwjRnbxyadfIBLTe58B0AyIxDS2bduG2+3GYUlAi7SiWew0hsfhdruD53jq/TUYx8zg4Tc+7ve+Pf3SUp5+qf8Qj6Lsbyq5KwNy1u/u4vDjjusfv/0RCuLHMu/80KoTc297lK3YKcTGKVdeH4zPvvkRinqu9guxcfyiPwBgmXclZViC9dyLsXLY1ffy0RuvEo8bA5JTmr5CAHY8lJeX887fHuUw2hCAEckY2vjyg3cBuOTMeUzetIQjnIVM/m4pxx49A4AbLjwDvb4M6JnSVl/KVeecxtQpE5FdjpCfQbpdZGdn8+CS9zEkZQbjWlI6D732HgDPL30bLTULYTCgJWfy8lsrQs7REBFHQ0To0JiiHAgquSuDtnDR9buMew6fS96Vd/SLN2VO5ltiMJ98eTB22GGHUYiNLjTaMbEZO7Gxscw972JKekpNQODp3TKiSE9PJ772OxLoLQY3gi48ny8BYEX+VUx3B5L49O4y3rr72uB+480+ImqLiKzaxFnjA0/Yms1mLO216J1OpO5Hd7UR29UUOEBovVUcAWEwBJdRLNeswSJyWnQCRd7eRRju+vcraIkZaInp3PXsqyHvQWdnJ3f96xU1lKPsNyq5K/vNkSfNJzk5uV/8mIsX4T7yLA6ZOi0kflL+XyjGRgFWzuozPBQ791fBGTvFRHH44ocAqA+PwdGn9l0zYXTEZ1G0YQO5tBPRc1s3Ch8jfS00NQWSddy6N5hV8DrHFb5O3atPBY+/9rwF6BVbGLfqGXwVhfzm7HkALDppBnpDeXA/f10ZN5w+m08+W43oM34PIGyxfPfdd9TU1ATG6CMiA/8lZVBT01sJ+6GlH2AYewQP7WIOvkoNOOsAACAASURBVMfjoaOj4/veWkXZI5XclYNi2vEn7TJeYEqiMn1qSGz0pEkUYaeRMIpN8cFZPqf+4UEKe27cSqAAOycvupHubme/P2xDT6L/+t03yPU3MdFRzCGuCnK9dWxduzq43zGFr3NKyxqOLno9GIuOjia8rRbZ3oje3ojFWU9ERASzjpqObK7rXcNVSmRLLePGjeOZT74N3pwF0BLSeOaTwBTQFZ983mcOfhbvfPRJSF8fXLqSx95ehaIMhkruyo/K2Tffx5mX/Kpf/MT8J/mEZObe/HBIvGvCHKoxU4aF5At/D8C4qUdSgA1Pz7x7FwaKRSzx8fH4v3o7ZCgnBTct7z4PwJv33MC4njH8Q2hn2QO3BPe7YeE8xq1/jbHfvsa1584Pxo8dFo3eEpjTrzfXcFJW4ME13duN9PmC+0m/L7iewNpmD4bYwDcaQ0wSX7f1ThxduXotJKcjkjN4+5Mv+r0Pn3yxZk9voaIAKrkrPyFn5j/WLzbztLMoxEYR0WRnZwfjR/2udzpmETZOvj1wrD93Kq2Ygvs1EkbElBNxuVyM9DZiI5CQY/GS5arC5QosX/fWndcws30DR7dtYNk9i4PHHzF9Enp9GdZvVyDrypg0aTwA1y44Plj6GUCv385tFy1g/fr1IXPwAUR0Ip/3JO1VDV1otng0Wxzr2/wh+634bDWfN3az5P2P9+p9U36eVHJXfvKOzX+KOflPhMQiIyMpi0qjABsNaYcF49MX/pIiEVjxXgKFhngmzZnPus8/wYY35BxR+KioqAgkfr0VGz7s+Mj2NgaTPsAhZZ9xSvk7jK/+KhizWq0YmyrQXe3ornaMTRUATJw4Edm60xO3rQ0cecRUnnj1HbTEjGBcS8rgsVfeCW6vbfZiSBvNls7+dU2+/noj73+2ul9c+flSyV0ZsubecCdb4g/hxEsXhcRTL7yeSiIpJYpxV98LwKwTT6YIW/DJWh+CEqyMHj2arx64nhx6p0nm4eCrBwLlFFwuF7m+JjJwke2uDUn6N15yLnrNNvTaUm68pPcZgUkxBvw9C734W+uZYA+M2bf7BSK8d7aNCIugQwYS+WMvvxlYXIVA0n/opdAHqd4preerBjeKsoNK7sqQdvqixf1iI7Jy2W4ZTnVsdrDMAsDY39wZfOK2EBvTFwee1NUhpHyaDuwYTf/igcXk9ST+HBys6kn6O0zb8iLTN78QEjvp2FnodYGa4LK2lFOPPxaAy2ZNQG/qLW+gN9ewcHIODoeDDmtycG1eLdyM255CY2MjAI/+dwlaShZaSib3/6d/pcvKyso9vU3KEKSSu/KzNHPxn5h5dX5ILDExkWIRTQ0RlPaZlTN98UPBpA+BcgozFj/I2k8/JQ8Hxp5Z+GFIcnGyceNGAN6+42qm42AaDt6+4+qQtq4/7Tj8q17jugW9D4YlJycT0VqD7u1G93oIa64iKyuT7u5u0HZa7thooqWljc7OTjrsKWgWO5o5Ck/MsJC58wUlpTz7VSFfrt+E8vOikrui9HHq7X/mM1KYe3NvfR2LxUKJKQEHRloxsS0iUDs/fdQounb6J9SFgezsbBoaGsiVbVjwY8FPjmyjoaF3rP29fz3Oqe3rWfGP0DLO159zMnpdOXr9dv7v9NkAJCQkYGyuQvcElmjUvR60hnLy8nJ46LX30RLTg8cbkjNDKl0u2bgdY/YEPixvQfl5UcldUXZyTv7D/WJzb36Qgp5yCvNuDJRDTkxMpFiLoaPnQSoHRkpMcVgsFrb+5Tay6a1hMxInm/9yW3A7o7GQibSS0VLSr63RFh85YR7C+iyV9/vz5vYuvN5QznVnnBB4QQvUweklQAv8s37x/U+hp2yCSMrgH29+QF+PL3mPB18NLZegDB0quSvKAHmmnIrhmIUhsVNveyw45bIQW3AevhsNb59/Xl40PASS8Fv5VwVv0Obi4O380Bu+ts/+R/zqF/u1n2Hswl9fToq3LbjW5/ULZuPvqZUDgcR/5ezD8Xq9lLhNaJGB4SQtIpJ6oz04ZNPU1ITDkkB37HA2FRb3a0v56VPJXVEG6MhTTmPKrP7F05pyZrCGOJyH9L525OIHggXSoHeRk6qqKnJxYiEwh92Cn1wcVFUF6tUvefYZcnGSi4MX/vZ4SDsXnHw8KZ1VXLag9+neyMhIwlqr0bs60N2diIYK4uPjaW9vD5l5A0B4JFVVgRIIf1+5Hi1hOIaYJN7Y0r9G/Z1/e3Yv3x3lx0Yld0UZpBPOvxR95tkce+Z5wZjFYqEsagQtmGjBxHZrYFy8oaEBU8hSJhCGTnVhoEZ9atkXpNHJCLrIrg1dExYgfOPH/WK/u+CMwOyb+u3cdPEZAMTHxxPpqAs+FSt1P6bmSnJzR7L8s9XIpMDyhBAYsvnPipXB8937zxcx5E7lrn+rNWZ/ylRyV5R9YNqxJ/SLzbvhLgqxU4SdudcHqmMedthhFGEP1rTvRqMAG4cfdxyv5v+WPBzBSZd5OHm9z5DNkjuu5SgaWJb/235tTYkzkWPyhMQWzT8O2VPwTG+o4NrTAt8sNtQ50azRwf00cxQVPdPznU4nenIGhugEtOQMtm3b9sPeEOWgU8ldUfaj6LlXYp97ZUgssLJVYMimCCvTrwssbp5CNzF9npK14yWZwAwZh8NBnmwljU5ycOBwhNaeP3HWkZxzyvEhMZPJRF6EF39zDcOkE5MpUHZh7vjM4ENUALqjmcNTA/cNHn3jo+DsGy1xBC+sKwo55z3/eYO7//f2D3szlANKJXdF2Y9GT5rE6EmT+sVLwhIpwUqxKRGbLZBYK+zpVNM7Tl5LBNvCAwXGvnr49+QGb8I6Wfdw6MNZK/Kv4v38X/dr58zjZ5LirOQXJx8bjB2Sl0N4cxXS70dKiWjYznHTJrFt2za0xHQ0Y+BDQAgNLSmD518JDM9s2LAZkjLQhmXz0ltqls2P3YCSuxBijhCiUAhRIoS4cRevpwkhVgoh1gshNgohTt73XVWUoWPBTffzlSGF02/uXZN24bU3U4gVPwIdKMTO+X+4i2+++YYcnJh6HpYy9Dws9e7rgbLERUVF5NBOLk7WftK/PvylC07pF/u/047DX1+G3ljBb04I1NXPzs5Gul0h+8lOJ6fNCQw5vVlUgxaXimaLp9hv7nfOV99+74e9Gcp+scfkLoQwAE8CJwFjgIVCiDE77XYL8LKUciJwLvCXfd1RRRlqzr+1/yLl4xfdQzFRFGMl+dxrABg5ciQuQp9Q7cDIEccGrsYb//cgmbhIw4V/5Qv9zrmrcXOTyUSmqZv47raQEgzhzRXozjYAdLcLWb8dq9XKky+9gZaSFbwJqyVmcN/zS4LHrfhsFYW6pd/i4crBM5Ar96lAiZSyVErpAV4E5u+0j4Tgcvd2oAZFUfZafHw8xdgpwcKoUaMAsNlsFIoY2ntKFTsxUoQdm83GssfuIZf24NqzeThYdt8fguf7bs3n1Dx/PyuXvNSvrfNPmMWv5oVO7Vx8yUL0+rLA+rJ127nlkrMBaJUmRKQtuJ8WEYnP0ntTdm2jF8PwPBojQhcPVw6egST3YUDfykNVPbG+8oELhBBVwHKg/+18RVEGZG7+45yS/9eQ2Om3P0Jhn6Jm8/IDc+DjWstDFh+JwUuSuzG47Vr+LEfSgHXjwIdMjhkeh7/4a4Z523r7NDodvbn3mk13NJETFrj5+/ALy9CSA0/Caom9i4fvsHFrIW9+qsoRH2gDSe5iFzG50/ZC4N9SyuHAycDzQoh+5xZCXCGEWCeEWLejop2iKAPTcsixfEECNWmTgzFn9lRqiQhuNxJGY3weAG89nB+8qs/Dwdv3hlas3LRpE58uf6NfOzOmH8ZZEzK55OzeL+iHHjoW6rcHKllKHb2mjHNOPRG3202nPRnN3FOx0hQGiels2rQ1eOybBXVsbAev19uvLWX/GUhyrwJG9NkeTv9hl8uAlwGklKuBCCB+5xNJKZ+WUk6WUk5OSEj4YT1WlJ+pOWeej+Gky5h3ae+smDkX/pIC7D1liQPryJ66aDGdnZ1kOLYT2zO10oqPLE9jSMXI1lf/TMSaN3fZVl5eXr/YdWecgF6/Hb2hgt+ceDgAbrebftdxmoazKzA08/y7KxFJ6YikdJ5Y1v9mr7L/DCS5rwVyhBCZQogwAjdMl+20TwVwHIAQYjSB5K4uzRVlHzv88MP7xXbUod9GFGmX3AxAbW0tUfhC9rPjZd2qwGLcL913E6NoJw8HS/KvGVDbZrOZmM5GjM3VxMbGAoHFw8Naq9HdgQ8N3edF1pcxfcpEvF4v5boFzRyFZgqj057ar7b8HU8+s3dvgDJge0zuUkofsAhYAWwlMCtmsxDiTiHEvJ7drgcuF0JsAF4AfiF3LAmvKMp+taM6ZYmwk54eeAApOzubYqx4e0ZVA1MrbcycHahLM9pdSwIe7HjJo4329vaQc67/ov/i3ABXnTOf358fOp9i8XnzQypW3nB6YOrkY69/iCGptxyxFpvCf9YUBrfv/cd/MOZN5o5/vfzDf3hltwY0z11KuVxKmSulzJZS3tMTu01Kuazn/7dIKWdIKQ+VUk6QUqoJr4pyAJ1622PMuT10HdkZv3soWLGyGCvjFt0NwDv5vyanTzniXByseaT38ZW1n3yI+71/s/yfTw64/XEWib+2lGhXIxERgXsA0RFGZE8NegB0HZPe+21CT8zEEJeKMSWL0tLSgf+wyoCoJ1QVZYiKjIykzJxKNWZKDLHExwdug4UhCetTvMyIJKKnSiWAf+ULTKORlMqvB9zW/NmzSO2sY9HZc4OxX849HtlzRQ/gry/j/3rq29z57NLeNWET0/hfnyt6gLVr1/Lov/838B9W6Ucld0UZwk79/b2s0lI55dbeFZ8mX/unkHLEpUQRc2ZgGcA3/nRTsHhZLg7euuP/BtzWJWfO6xc7Ni0ava0JvdNJlqkbk8lEaWkphqQ0tLDAFb4QGlpyJo/887ngcSvKWuiIHtHvfMrAqeSuKEPc2bc9GLJtt9spwoYTI10YKCKKQw45BJfLRVZXbbB4mQU/ebI1ZHnAFflXsTI/tBDa95l+2HgMjduRdWWcd8IsALKyspDe7pD9ZHcnx0waDwTG4rXkLLTkDO547tUf9DMrKrkrys/S/PzHKcRGMVZO6nlgqqmpCQuhc9Et+Nj4xacAbFi1ilzaGU07rz/1aL9z7s5vT53JxYfvNLWyrgzd1VPmwOPGV1fGhAkTAtuJWWjWGLRwM8akTLZu3RpyaHd36AeDsmsquSvKz1TNiMPYFjk8uJ2enk4RtmCt+R0zbI4/7UwAXO8/SwYuknGTXvfdgNuJjIxk+PDQh9pvufx89NodZQ7Kub1nkZHAWHxacD8tIY3XNlQEt7u7u3ng1fdYuXrNXv+8PzcquSvKz9S8y65iwe/uCokd1Wd5wGKsjP3NnQAsve8PjOp52hUgh/Z+i4a8mn91vymV3+dQq4a/dCOGxu0DPubBpR9iGDWVVXVdAz7m50old0VRgnYsD1hBJEVaLImJiQDEupuJ6VPDJgo/KfQ+7fpG/m85mnq+fOQP/c65O3PnHEeeqZs//PL8YOy2ixeg15cHt/XGCs44NHAl/+GqNYikTIRmQEvO4M+vqEVDvo9K7oqihJh3w118bkhl7m294+rhM0+nAktwu55wquJzAGhvbycXB/F4GIWDT5cvH3BbZ83vv/SD1lCG7mxF7+7CV1fK6NGjAVjd4EaLDpQt0SIsOC0JIePvT7+0hLufVeu+7qCSu6Io/Zx36wMh29OOnUMhVjw9C4lsxc6CRYEHn75+5Hfk9jwUlYYL05qlIce63W7q6uoYqJt+eQF6XSl63XZuv/gsIDDWLsxRIfsJWyzLPvg4uN0QkYBIyqCsrGzAbQ1lKrkrijIg06+/nyJsbMNK7hW3A1BRUUEGnRh6CsUKIBsnzz/e++HwxX3XUfbULXvV1omZsUS19dahCQ8PR7RUo/t6Z/Po9RWcdcqJANz971fRkjLQEkfw3zUFP/RHHFJUclcUZUCsVivFpgRKsJGamgpAWloa7YSF7NdEOPMuugKA1SveIo82RuHgvSfuHXBbU6ZM4ZpfnBcSu/6ME9AbAuPx/pZa5uemAFBXV4dIzkQLN/c8EJXFX18M/fbQ1fXzuwFr3PMuiqIoAQtufqBfrCw2m5SWTpJx046JImIY07N0X9jqpQwjkFiHNRXhdruDtWf2Vnh4OImeNpqcLYj67Yw7LlDq4B8frsEwelpwP80WR3NLbHC7q6uLh5Z+SF50OGedPPsHtf1TpK7cFUUZlNOvvilYU74QK6flB27EvvvQLeTiCO6Xg4PP/xS6YMiyh+/cq7auWDAHir/h+jNOCMYifV3Izt52dG83ekdrcPuhJR9gyJtCoSd8r9r6qVPJXVGUQcu69CY+IoXGUbOCsTBnC5Y+NeXDkETJ3vVVP/vf00x2bOWjBwc+fRLgpsvOJTy8N1Ffd/E5wQeiAPT6cm678DQA3vzwY0RqdmD6ZFIG9/1n6S7PORSp5K4oyqClpaVxfP5fOOXci4Kxw665l+I+BcoqMWM+4RfB7ZiiL0jFTXpHFS0tLYNqf3Z6InpzNbqrjYiWqmB8g0NgiA7M1dciIvHHDQ9pq6SkhCf+OzTr16jkrijKfhEdHU15ZCodGPEiKBIxHHrEkQB8dN8NwZryWXSw5fGbB9XW4VMPxV+3HX9VMTdcfDYQGGvvN33SGsdrKz4Obr/49TbabKmDavvHSiV3RVH2mxN+dx9FPQXKZvz+IQA6OjpIczcQ3lNTXgC5spU17/U+/PT63dezIv83e9XWbReexrWnHhXcNpvNyKYqdG/vk7V6w3YuX3g6AH/+zytoKVloSRnc+dzQG65RyV1RlP2q67A51MSPCs6SiYqKohNDyD7thDHmiJlAIPnn+JoZhYPVH67Yq7aiokKv1HeePjkzpXeYyGFNDVSfNIVhSMli1ep1e/2z/Zip5K4oyn41Y95ZHL8o9Kap69ATaOyZH+/CQEV0djAxr37wd+TiIA0X4rNXBtW22WzG5qxHd7Sg15Yxc/oUAO58bilacp/1XeNSWVndFnLsHU89j9Pp5KdKJXdFUQ646QsWUihikUARNo67JvDE64fLXmUUbZiQCCAPB6/f+/tBtXX1wtPQi9dxwxm9c9w13Q+6Hrqjv3epwYeefwVj3mQeXbZyUG0fTCq5K4pyUIz57T18TiL6EacFY4ZvPmAEvU+TxuAlzdMU3O7o6GBF/lV7PVxzyy/Pw2w2927/4kz0hu3Bbb2xknMnZQe3u+ypGKIT0JIyeO/DT/eqrR8LldwVRTkoYmNjGXv1H5l0Qu/aq52Zh1FL7xOsToxUGXrHyVc/eAPHUDvo4RqARHcTuqMZ3ePGX1fOyJEjAbjz30t6F++OTWFNq/f7TvOjpZK7oigHTWxsbMj2yRdfEXzaFQIrQc3rWdz78/eWk4eTMCR5OFj6x8EN11xxzunotaXodWXcdvECAJxOJ4akEX0W7xZoyRk88I/ng8f99413uecnUFpYJXdFUX5URl+ZTzFWqjHTOmpmMB72xRJG9CwQEoOX3O56Ojo6BtXWL4+eSJq3t1SB1WpFdocWGZOuduYdNTW4XSYjISWboqKiQbW9v6nkrijKj0pycjKFIoZC7Mw+92IgMNYeS3dwmT+AVLp4/e9PBLffzl/Ex/m/2uu2LjpzXkgsyd2M3tYIEFgwpL6MvLzAAt/3PvdaoLRw/DBe3lDe73w/Jiq5K4ryozPv9sc4Nv+vwe2oqCiqsdB3fkspUVxwbWDBkPLycvJoZyxtvP3EHwfV9uXnLkCvK0XqOnp9BbdfFFi8u6mpCZmQhhYRGRiuScrkyZdeH1Rb+5NK7oqi/CTkXZlPSU+tmloiqM88PPhaxb/uIZsOEvAwvGnwwyWXzpqIv/hrotqrg7G/vrMKLbHP3HhrNK0RofcM7vrHCz+a2vEquSuK8pOQnJxMgYjBgZEC7Jx8cWBBkLeeeIBRtAeHbHJxsjz/t4NqKzU1lUtnHso1F53dG4vUkH1KCeteD9LRu/3kS29gyJnEQ0s/HFTb+8qAkrsQYo4QolAIUSKEuHE3+5wthNgihNgshPjfvu2moihKYLhmJclMueHBYCy8qYx4euvHmPGT1HPjFQIFxFbkX8W6Tz7aq7Z2rDa1w2VnzA0M1+woLdxQzvU9D0Z1dXXRGpmAZotFpGTx+vsH/+GnPSZ3IYQBeBI4CRgDLBRCjNlpnxzgD8AMKeVY4Jr90FdFURTm5z8eUkMm/bxrKKV3u4kwqu0Zwe3P7r+Bo6nDv/K/g2774iMOQW+oQHe1E9VeS2RkJAAPv/YeWlKgTUN0Ips6Dv6gyEB6MBUokVKWSik9wIvA/J32uRx4UkrZCiClbNi33VQURdm13NxcirDThYYECrEz79pbAfhuzSryZDvh6IzCyfKHbhtUWyNGjICGcvxVhVxz/um9L8Slopl615LVktL583MvBbefe3Upd/z9wA5oDCS5DwMq+2xX9cT6ygVyhRCrhBBfCiHm7KsOKoqi7MlJ+U9QjI0yLCSc17uUn2v5v0nDBYAdL+nOikHf8Lz5otO59dyTQ2KyM7TAmHQ0ccGpvbVsKjQ7xhF5bN68eVBt742BJHexi5jcadsI5ABHAwuBfwghovudSIgrhBDrhBDrGhsb97aviqIou7U9ZiSFxJCbmwsExsHjcIcksGF08s6//xbcXpJ/DR/sZd34XZmZasXfUguA7u7E0FgZfPr2zr//Dy0pEy0xjaXfVQy6rYEaSHKvAkb02R4O1OxinzeklF4pZRlQSCDZh5BSPi2lnCylnJyQkPBD+6woitLPvP+7mZPyHw9um81mKrDg77NPGVZO/3XglmB7ezt5tDGaNpb+/XEGY+b0Kei1Zeg+L3rDdm68MFDOoLW1FS05Ey3SGpgbn5LFfU8/N6i2BmogyX0tkCOEyBRChAHnAst22ud14BgAIUQ8gWGa0n3ZUUVRlL11xO8foQgbEJgb3zr26OBrax65kVwcDKOLEdXfDrqtG86Yjb94HdmG3mGfx5d9jJacEdzWbHH4EjP6H7wf7DG5Syl9wCJgBbAVeFlKuVkIcacQYsdzuyuAZiHEFmAlsFhK2by/Oq0oijIQZrOZsohk2jFRgJ1jz7oQgLdffI5RtGPqGWHOw8Hrg5wbbzabufW8uSw89cRgzNDtgi5XcFvqfnC1D6qdgRrQfB0p5XIpZa6UMltKeU9P7DYp5bKe/5dSyuuklGOklOOklC/uz04riqIM1Mk3/omVJHPo1fcGY2EFX4bUjbfiIx1XyHFL8q8e9EpMN19xAXp9We/c+Ppyrjr5yEGdc6AO/mRMRVGU/ey0/D+HlBf2jJpGJb2LdzgxUo4luL307sXMop61D93AYB2TGoneVI3e5cJXt52YmJhBn3MgVHJXFOVn55RzL6KAaLw9c2kKsXFaz81Yp9NJrq+RODzk4WT5v58aVFszZszAX1eKv7qI2y89e88H7CMquSuK8rM09do/UoyVWiKoHDYhGP/yocXk4ABgGF0kbl876LZuu+h0Th+Tuucd9yGV3BVF+Vmy2+0UEMNmollweeBmqtPpJJ1Owvo8ypODk//+8ebg9vpVq3jtj7sssfW9xo4dO/hO7wXjAW1NURTlR+T0/EdDtq1WK1sxhcTqiGDeot5k3vX+s4zGQ0dHR0iNmx8bdeWuKIrSh2PCCcGbrR0YKSIaqzVQR/71+29hFO3k4eDLBwd/s3V/UsldURSlj+NPO4cC7HgRFGJjbv6fg69ld1YRiwcDktE4eP+1Fw5iT7+fSu6Koig7mXb9/XxCMjUjJgVjK/KvIofeee/D6CL6uw9Cjlv24uDLCu8rasxdURRlJ1arlePz/xIS6zaE4/FrRPSs5KoDnX1S6NatW0kqWMlr+Ws5Y6ex/INBXbkriqIMwLxbH6awp04NwDas5F15R3C76aVHmEozo2ijra3tYHQxhEruiqIoA9Q27niqMePCQCE2kpOTAXjlT7cE13HNwcHaR/d+quS+ppK7oijKAM0+YyFbsbOFaE7NfyIYz+2qJqFnHdcwJHk4eeflg3uzVSV3RVGUvTDthgdwTTstJBa20/pFFny0F28Ibi+/+zo+zv/VAenfDiq5K4qi7IWoqCiOnnNqSKwEC86em6sSKMDOuTffB0BTUxPZvibG08Zbj9yx8+n2G5XcFUVRBmlu/pPBRUHKsBB2yuXB1zY9cQs5OInFQ3p72QHrk0ruiqIo+8C2+FGUEkUBNqZMmQLABy88Sx7twUSbi5N38686IP1RyV1RFGUfOHvRYlaTwMl95sd7C78iCXdwOxydFDoPSH9UclcURdlHzs9/OGR7yqI72YY1uN2KiUrL8APSF5XcFUVR9pP4+HiKDbG4MCAJLApy6uK7DkjbKrkriqLsRyff+ihF2KgkkvDZFx6wdlVyVxRF2c+aMqewmWgmzph1wNpUhcMURVH2s9kX//qAt6mu3BVFUYYgldwVRVGGIJXcFUVRhiCV3BVFUYYgldwVRVGGIJXcFUVRhqABJXchxBwhRKEQokQIsdslRoQQZwohpBBi8r7roqIoirK39pjchRAG4EngJGAMsFAIMWYX+1mBq4Gv9nUnFUVRlL0zkCv3qUCJlLJUSukBXgTm72K/u4D7oU8JNEVRFOWgGEhyHwZU9tmu6okFCSEmAiOklG9934mEEFcIIdYJIdY1NjbudWcVRVGUgRlIche7iAUXDBRCaMAjwPV7OpGU8mkp5WQp5eSEhISB91JRFEXZKwNJ7lXAiD7bw4GaPttW4BDgYyHEdmAasEzdVFUURTl4BpLc1wI5QohMIUQYcC6wbMeLUsp2KWW8lDJDSpkBfAnMk1Ku2y89VhRFUfZoj8ldSukDFgErgK3Ay1LKzUKIO4UQ8/Z3BxVFUZS9RpxNtAAAIABJREFUN6CSv1LK5cDynWK37WbfowffLUVRFGUw1BOqiqIoQ5BK7oqiKEOQSu6KoihDkEruiqIoQ5BK7oqiKEOQSu6KoihDkEruiqIoQ5BK7oqiKEOQSu6KoihDkEruiqIoQ5BK7oqiKEOQSu6KoihDkEruiqIoQ5BK7oqiKEOQSu6KoihDkEruiqIoQ5BK7oqiKEOQSu6KoihDkEruiqIoQ5BK7oqiKEOQSu6KoihDkEruiqIoQ5BK7oqiKEOQSu6KoihDkEruiqIoQ5BK7oqiKEOQSu6KoihD0ICSuxBijhCiUAhRIoS4cRevXyeE2CKE2CiE+FAIkb7vu6ooiqIM1B6TuxDCADwJnASMARYKIcbstNt6YLKUcjzwKnD/vu6ooiiKMnADuXKfCpRIKUullB7gRWB+3x2klCullJ09m18Cw/dtNxVFUZS9MZDkPgyo7LNd1RPbncuAdwbTKUVRFGVwjAPYR+wiJne5oxAXAJOBWbt5/QrgCoC0tLQBdlFRFEXZWwO5cq8CRvTZHg7U7LyTEOJ44GZgnpSye1cnklI+LaWcLKWcnJCQ8EP6qyiKogzAQJL7WiBHCJEphAgDzgWW9d1BCDER+BuBxN6w77upKIqi7I09JncppQ9YBKwAtgIvSyk3CyHuFELM69ntASAKeEUI8a0QYtluTqcoiqIcAAMZc0dKuRxYvlPstj7/f/w+7peiKIoyCOoJVUVRlCFIJXdFUZQhSCV3RVGUIUgld0VRlCFIJXdFUZQhSCV3RVGUIUgld0VRlCFIJXdFUZQhSCV3RVGUIUgld0VRlCFIJXdFUZQhSCV3RVGUIUgld0VRlCFIJXdFUZQhSCV3RVGUIUgld0VRlCFIJXdFUZQhSCV3RVGUIUgld0VRlCFIJXdFUZQhSCV3RVGUIUgld0VRlCFIJXdFUZQhSCV3RVGUIch4sDtwoHk8HgwGAwaD4WB3RdlJd3c322vrMQiNzOEp6nfUh7uzk6bCjWidDnSzlbi8cZgtUQB4urtp3FYAEuIyc4iIjARASkljxXa87U0YoqJJyhyJECJ4Tl3XAdC00Gs8Xdfp7OzEbDYP6Heg6zp1JQXgbEGarSTljsVo/P7U4vF4+K6knJrmNuLsVsZnjyDKYtmr92RntQ2NeLxeRqQk9/uZdkVKSUNFGT5PN0mZOSF99nm9NFZXYo9PIDLK2hv3+dhWWYNfwojEWKxRgd9Bl6uD5i3r0Tpa0MMisWSPJSY5dVA/z2AJKeVBaXjy5Mly3bp1B6w9R3Mj7RtWE+FqwieMeBLSGDFl5oD+CJT9r7KugTXffodV7wIErnArR04cT0Js9MHuGgB+v5/tVbWgCTKHpfT7u5FShiTOPWmuraa7pZHwmHjiUocH4011tWzdsB6AvHETSExNxdPdTf3HbzAiTA/uV+0RxB11Kp2tLXg2fEJShAEhBPVdHgxjjyIuLYOP/vkYcQ3FmIXELaE+Oo3jfrUYv9/PVwWl1JSXI5EkjxjB1LwsIs1m6oo3U//pO5g7GnBF2EmYMYfhh0zC7/dT/c0XaI0VoOvocakkH3YkRpOJ7SvfJF26MBg0pJRUeI2kzJpLWEQEbreb0poGdAnpSYFk6Pf7+e+Hq3FFxWMINyO9HgyORs4+Yjy2nmTpdrvRdZ3Ing+qHZwdHdQ3txFttRAfGxOMvf/ZaoQxHKFpdHd1cMRhExiRmrzb99/R2swrdy1Gi7ShG4zI1nqmXfgbDpkyne3frmP7ey9h7XbgEmFETz6GcScuoKXdwaqtpRi7nGi6j85wK+PSU8kalkzh0n8RWfYtPmcbWng4emou8SdfRHRSyoD/JgZKCPG1lHLyHvf7OSR3KSWVK14mLbz3Z9V1naroDNImHXFA+nCg1dQ34uxykxhtIybavsf9Hc2NOIq/Q+vuRLdEEz9mIhGRg7uSGigpJa8vXcpY0U64MXCl6PL4KItM4ZSTTjogffg+dU3NbKhpJSIuCYDulnompMaRGBdDWXUdpS0duKUgQkiyYqPIHLb7pCKlpPCDZYSXrMXsc+M2RtCVPYlRs09j0zfr2LRlK7bYeJDQ3tbC2NyRxJmNDGss7vfhURWTCU3VDDd4QuMeQYWwEPfNO0Rbe686OzpdVGRNx5+YSXhNASPMgQ+omk4/7QnZTB2bQ92/7ibL4MZsMtLt81PhNRJ59nV011Vi2LIKo9uJQOILt9KVeSjWjFySKjZgMGg79S0L4/BsNtQ5MMcmIISgq62FkVYjtY1NfNHkxW8Iw2C24Hd3YtT95JjcnDB5LJtf/jsxLeUYgFZLAsNPvZCEYSP46rsCNjY6MZit+D1djAiXnDB1AsuWv4upsYKYrmYMAhxhNurMSVyw8KzdfuA++n+XY54ym4ik4Qgh6G5vpeWzN7jsxnzWP3Ad2VYDToMFs89NW2cX5lN+SbWwYC5bj90ISOj2+amKzWRCWgqdrz5ChC0WGWEBbze6o5n23BkcfsGVlFbWsKmkFJ/XR1pqChNHjxzUt9KBJvefxbBMfXkZqUYf0PuGapqGobny4HVqgDau/Yry7eX4pSTcpHHIhEmMyMza7f5+v5/PNxXjsyUSFhFLRYOD+MYWJuZk7vYYR3MTnrXvMTy85/1xdlDxaTWpx5+xx6/X+0J1TQ2JnY2E283BmCXMiKmuFJ/Pd0D6sDtSSjbXthKZkBIcxjDHp7C5phYpJds6ITw+hbCe/bd1OIhqaSWh56pyZ6Ubv8by9dskaD40JDqCxm8aKE0Yxvpv1jM8JQWTFmgnMtrGhg0bOWbcSOoam6itrkTzefEbTCQNG4bPGENUZxtYQ69uo3U3H3/zLdnR1pB4VKSFxoKNWDs7yYkOC8aHWYy4aopYX7KOWaZuuvyC6k5JrAGyw3U+f/dlrLqXCVF+hDWi5ygfm7euoSsyql9iB9BcbWytayUyrvfK1RwdS0lzPTU1DfhtaWiRUUg0NFME+L2UVhew6eW/k+aqwRVhwY8gyedg+5J/4D7j13xR0YQ9IRnh92GIsFDc4cK+cSvO4o0cHtGF7moD3U+MpQuPu4uiwkLyRo2iw9FOY0UZtvhE4nqGSjqSsolOTkMnkPxN9ljCx8/i8Vuv45hh0WxJOxSzxYLH60VUFeD+YAne4WNItIfT5ZN4fH7sliiiaov5dO0HTLUlICMiMGoCvykcGZNC9fovWD/hKL7YUoopyg7CSENJOWXbyzjr1DkD+wMchAH9qxFCzAEeI5Ad/yGlvG+n18OB54BJQDNwjpRy+77t6g8ndR3BLj7BD86XlgHbvOFbqhpbiB6eEYx9tXYdsQmJWHq+vu5sS1klImE4YT1XLBFWGy1dJmobmkhJjN/lMY5tm3oTe48RYTo1RVsYNmb8vvlhekgpKauupdPjwx4ZzvCkRKTXS7TmBcwh+0b6uvZp2z9ER0cHXcJEV0UJhi4nIPCbrWC2sq2ukfC44bhdnXi7XIRFWgiPslHZ0rjb5F6zagXjPR24PG6MAnwS7GERrP7gDYwJIzH1SZRGg0ZYRASbK+sYvr2ErOhIdlyg1FSU4YjOJM0Q1q8Nly7wamFAd7/XOqXGMI8DCP1bSNY8lNeV8114FE3JYzDboynrcGCt2QpdDYSZoLLDjcEXOKffEIY9IpIGtw+p9R+S8oWZ6dQFtp3aN1pjqKlbg5Y4BjRTT9SAD4HT2YWrooS6lGG4vDoSMJssGNvqePuDT4jKHIu/w4Hf50UzGIgMi2BjWRVJjaWE2zTCwiMQmglfZzOx7mZaG+r4rnwrEVtWYRE67bqkLCmHwxZeiceaEEjsUgISKTTMqel829BGw7Rj6IiMp1tqGIyS6BHjcXz7GdaOVtZ125COFsKFjjPCRm6UkZpWB/7oOCwGDZBoBoFRE9R4NEpXf40tbyKGsMDvSdMl27cXUt/QSFJiwi7/RvaVPSZ3IYQBeBKYDVQBa4UQy6SUW/rsdhnQKqUcKYQ4F/gTcM7+6PAPkZSRRXXBGkb0yR1SSvyxw4LbPp+P7u5uIiMj92rsdH+qKC/HmhA6Zpc4LI1vvlzNUcfP3uUxDh/9+h9mNtPobCYlcdftiO7O/jEhEN2uH9bx3fB6vXy6pQQtNhWj2Uh9VzcVm4uZmpdJdbefqCjY8RksdYkh0rrHq/bymjoaOtwADIu2kLqP/8GEh4fTXroVu6aDv2f4o6Oddl0QPzKH+u0ldDsdYAoDr4cIm52IWOtuz+eorQLZhdVkwCc1zOh0ebpwuerQ7Kk46mswORpAgseWgMEvcRvMmKOsSOkL/G6lJMJiobqrG196NqXrPyK8uwMAT1gUHDID+2g7JZs/YmR07x99hdONIX0S+Fr69auz20OHPYW6+GSslsA3gYgoG86MSTSUFaE5qxgTqyFERPCYr1scpI8/jIr1n5Ie5g/Ga7slcZMPxbS9oV87XpeTsDAjLpcTsz2GHb9wf7cbqXuo8RnB7ae7uxshdbrDI/DJCFoaaohJSiNCSMyawOf343Z56GppINzjIsKcFPzbMUWYiXK14OzuxPjdp2CNwW0KQ/f7iW0qY+N7r+Nsb6fR2YkmA9+SdKHRXl+DPXs0LeZ44kwaCUYNn67T7LFQHR6PqbWLY4xVZNsjEEBzZyPvNUXiMdsplRZyPZ1Ehhnx6zolLp2uSBtdhnBiTGH4fYH3R9M0rCnprPzkE84968w9/PUNzkCu3KcCJVLKUgAhxIvAfKBvcp8P5Pf8/6vAE0IIIQ/WgP5ONE3DOukYKjeuItrbQbcucMUMY9jE6UgpqVr/JcbaEszSR3VYFObRU4gbkXGwu41X7//2CU3Ds4v4DkYknp1iUkqM3/N5Ja1x0OoIiXl8fgwxSfj9fr4rraDNIxECkiJN5KUP/0EfgAXlNRjjh9PU2IjH6yPSHI5mS6SyvpERhx+N69tPMRmMCAFun5/sI0783vNt2lZBgyEKU8+48hanC5e7mpy0Ybs9xuvxUPvN5xiaa0Bo+OOHM2zSjN2Ogfr9fsILvsR2yCSEIfDPRdd9uAu/odtioqnbRGRC4Ku+lJLGxhpSvG2Qu+thsG6vlzq/IDHKjjAY6Pb7aWxpRUfgLttKhj2McHMguXobCtnS6iZj2iwMlhwa2pow+rrxG8MIi04gTPcj/V7ioiIRmi/QB7OZVt3HafPm8teqSupbK0gOhwYPVEam8euFCyld+xmurWtBaIHfo+4nKn0s/9/eucbGlZ6H+fnOmZlz5n4jOZzh/SaSS1GitN7NXizt2nLtGHVqN4nRRRLUKAoYBeIiBVIUSX4EaND8yJ82RX8UMOK0Qeu6CdzEcQLXycabjXcTZ7V3aXWlxDs5HHJmyOHc51y+/JhZSdSSEiNL4np4HoDgnDPn8Lx853zv996+M6lwP2s3LkPDxC3AkFCyVSLPfY7Q239KXW7jsW2EgLoUBCNRvF4fwbNfYOXaBZRyAVv3Ezs2jS8Yose/TabewK15bukyJhokOuIsmnWqq3N4bANDKCj+MLFQiOuGh/78KkN+N0KBzHaO12oBMOZRBsbwxOIAuFWBMOqUr72F7Y9hmwYI0fyxbapakBvnX+eZeARsC6tRBymxvSE2r75PcS1PX3cHqVTzXtkubLF48xJR3U/QLdBdzQjKpShEPZI1b4DB8jIjIQ3RCvnjXg8n62Xe9ibYUX3M+qK4qiUMlwerI4i3PMdOvU69XsfcXEaxLGQ8Sa1YpCewvwPwsDiIce8B7kxOrwA/td8xUkpTCFEA4kD2YQj5MIgkkoQ/83MUCwUCuk6H3vRA1q5cILk1j8vnBtxEsMhc/CG1eNetlrLDwufzYdv2rs6MnZ0io/39+57THw/ywVYBPXi7iFrLZRgd79v3nK7JGeb/ZoV+pY6qKtQNk1VvJ0MDQ/zo8g3MaBI10DTm6YaBcXOJ6dEBcssLVOc+QKmVsP0xQhOnCHXs7zkXGibX1ubQ4klcPg/5WoXs0hLhRIjTT5xkK56gsnITFJXYwBih1kDeC9M0WalaoFSoba6BEKiBKAuVKqP36FxZe+MV4tk57HIBEKjGDivnDQaePbfn8dVqlafULfJzb5L3diCQxCtZeihwPZ9F94QpZTPokRi17TwBq0Zlu7av3Fr3IKVGkHKliFsamELBig/gUUMkCxk0XwTcGgAeIUiVy+iRTszsPHqsqVsXYBkm7lAMz8Yi4a4kcDvCa+RXMQyDX/7a13j34iWuzy8w2NvLF0+dQAhBMNZJSVpQzDW7fAJh9M4uLF+I8snnKS1eR1bLCE3H1ztKh8cm2j9MrZAmv5VFSvCFo3TEUxiNBsXsBsvn/wZjcxk10oWp+Rk8PsPUcD/68hrp7W2klHTpLiYnRpBmg+xrrxMNBhD+CLJWorj0Pv1TJ7mGjeYPstWKRBRvgBBuvNUcfR/8f3ITL2B7Qwijhnf2PCeUArX+p1gtrhIzy6gK5ISX7XiCRqGKaTXArWFLEAoIy2SjWOdk1MPxxirrs+vYQmWQOp1dHt5eSsP2JtXOJNI0EIqKVasyolv01CxMl9709qXEVlQmOjWubEE4fQ0jlqTsi6JUy0Q35uiKJFkrbuN/4ztMJiIoikL6ygf8XUHhzL/9N/veIw+Lgxj3vUbJ3a7jQY5BCPFV4KsA/fcwUPfDsiwuzS1RMJseaV8kQG/3PjmH3dcnFNndWic3FnHd1daW8HpYnb9Oz9TMA8v4MDjzwgv82Z9/D384SsDnJbddIOASjE9O7HtOsrMD295kLpehYYPfBdMDXXg8H83NfohH0xj4zD8nc/MaslrCHe1kqHeAYqlEUfXhu8NQujxu0jsGvetr7Jz/K7JSo+by4C+mqWfTeD775X0nxfWNDXzJiVuG16P7MNUk2c0FGBskmugmmti/0+ROtgsFKsUSUauEq+V1G9kdspYL0zRxu90fOadaqSBvvIdm7dzKbTc2d6jni1hPv7in967rOju6n1M+G2ilGQIwK4JYepBUKMjOVp7yjUW6gkFC0RiN2v7ttVbfBL78dWx/EGnbeBQFl+ZlR0kwQpVQMNj0QgFFC2CaBp1DI9zIrNBdLBEIBiiVSqSlzvOfP0Ppr74F7P5fdUVSr9XQNI1T01Ocmp669Z6UEmv+A8aGd0cW6eVr9D0/xs2bGRqpcQzZjAIVq8ZwV5zsQhzDMLFDvSCgZjaoSB99SGZ//7c55qoT110Uclvc+NYNlK/8Gv3HJhnpSzFylw6Sbptz3iKGXaO8ehPd78cbVFHVKnmjwLarH+HrACGwG3X6jG2uqRpn3QU2Ln2Hoh5Cq5cZ1CXnO/txj5/CWtWpCwvTMnG5NQy9G9teYra4xljYRqWZXs83bObx088GIY+bsLf5mUtbI+yG2UCQ/s3LFDZvYAciiFoVf72Aa+w0dj2PSjOiloCKzWapweT0aTquZKk3NvA0MphSYLsVEslOZEXQXVOoFbZAQEgoPBtRyWTzRCKPts33IMZ9BbjT7esF1vY5ZkUI4QLCwEcSe1LKrwNfh2Yr5IMIDPB3l28g4z0IITCBq6US5lqGwVTiQf/kxxJN0/i5n/0SV65eJZfL8/TMNKnU/ftmexKd9CT+cblnRVFIjk3u2rdTKuPxf7Rwa0jB6gfvkNa60ePNSbUM5NbmUa9eYPD0M3teIxKOsFqv4dLvKH4YdSLR2D9KVoCA349cncXVc7tH3K2qKOkFVPVJtjNpSrMXm1GFL0R4YgYTBXcxizt4O2/sURWU7QyWZe1p3H0+H8bQSbbXr6KZzdpEw+2HsSnCoQ621tfo0N10aM1IKZfP0pHqQUrJ2uX3YbMV9Hb2k3riBL3Tp3nz1Rzj3goet5uGYXDN0Bl88ilyr66QcrngjjrDhuJjKBDg3L/4l8xfu8LGyhKx0dOcm5hCCEHWFwN2RwrbrgC9obtLmS11GwaaUQFt9wQcViyyhQJWo0G9sYMhBSYSj9LMFS9Hh1FKBv1KFVURLFlBih1jbHznmzzpqhB2KwjbJOaSnFQsXvuzb9L/q/9pTxnUyg69bhMrt4JHVTBKeWx/mJqsU7TB7fPh9jbbcM2Gh7VcFjU1xrXCZQbcVZKyQM0Fi4aHrnOf59jTz/Cj90NcXZwD2yTQ3cunTk3zjf/9Ld5UurlWsdA9bgzDoGCBolnUNq+h0gdWs3CrAGvLyzz9zD/B9fofcioahFoRLItSvUTeo1EaOUV2/g1i/ub9a1gmV5QYz40cI1BPoxQ2qRkmmiqwvCGKqT46r8+iC4u6tJAouG2DkVgIYycP7N/19jA4iHF/ExgTQgwBq8BLwC/cdcx3ga8APwJ+HnjlUeXbN3J56v4Y2h3epOYPsJhffzDj3tmPmb60y3vPVBvEh449DHF/bIQQPDE5ef8DHwGpRBeXL83j6tjtTYdcsFqs4+venerRkoMsb2YZ3OfvRfw6tlsjXypjSnArkIj48ZrWPmfsT6VYZNTIslmOoLUmoHqxwGB9k63NDeS7rzQ7gFSgnmX9jb9EHj9DRX40yGzQXHyzH6nnP0fuLR1fcQMpoBrqpucTL6BeuUCpUqCmd6HYNraiolU2SYlOlt/+W1Lbi7eiCnP9EsvVEqq/i+rxF7lQK6FVt6l7I1jeIEGPZDE+RK66QtzbjLK2qg3ysQFisebkNzQ+ydD47nshdOJZlt/8AT3NTA5rNYn/1Cf3TUu53W7qHj93B9YF6SLXsEkMDnP3KJrbWMf0RQg89zNc30gjLZNwsg9ftUb5L/4nYb9y63pCCDQFXNmVffWZL5U4Vt3CE7q9jkJKg/eyWdZCA5xUXWA37wlVESz6enjxuTMYF0w21q5iFUsomk4l1sPE+BSKovD8qeNw6vjuCxU2CSQnUDt7qSJQkQRLBYyLP6SrtsXm/A3CqT4Ul0p5I42eX2XryjvEu/vIGAZKvY6tuiHai0zfRDn7ElfCSXw33sFlN9jqGiZ86iyGp4YS7UKLdkBpB1XTCfqDlKIJtjdfJ9qbwvthJClhbfEmpz/36PtN7mvcWzn0rwF/QXOo/L6U8pIQ4reAt6SU3wW+AfwvIcQNmh77S49K4EKpgub9aJtZY49BexBSkydYqZZxZ+bQbYOSJ4B+/Myh59s/DiiKwrF4gKu5TXyxDqSU1PMZTvd28Per8Y+syrRsGzW8f3psuCvGVnqHno7bnno1u87Y2P4F0P0Ix2LUIwG6SgukCy4EkgmPTb2rk8rSLH13tXZ26wqLmyvYiWGWsoskNYEtJesNgdo/cc+0lT8cwX/ui+xsbyGEQme46aXrssFnulzMFtapKh58doOxhEbarOHZWmvVcZq4FAV3Zo7aSJKeqI/NbZu6148LSTLix1QNXvzs53j17Yv4ihkEUI4lOHNq6p7F63BnguBPv0Rm/gZS2iSHxu65QEYIgWd0hp3Z84S0pnzlhoEcmL7V8303NgIhbYQQhBO3l9RbjRqWN4BlF3Cpu8+tu7R9ZQhqGum6YOAO65OpmvhTftTB47zlEXSWMyjSIu/txJrqpbaV5YXRfhjrxzAMXC4XilBYufEBwafO7nmdiK6hBPx4NBeC5nRm2jqGV6NneIREZZOVq+cxbOgN68jeLt70eIl0RJqF2Tu4mKvgQpA4+SycfBZoNu5KKbGtbQrJSfxrV4nGu6gaJgsiRP/0J6i+/reIRgVsDSlAtU0qkRRrq6vED5iCfFAO1Ocupfwe8L279v3mHa9rwJcfrmh7k+yIMr+UxxvZHcoHHnDBlxCCviefwzSfpl6v0/MxaoX8ODCYStAdq7GQ3kBVFIafGEJVVXoH+lnKFQmYFdwulZphUdECnOjZvwgai4SZsSU3NzLUbYFPhZODCXRd3/ec/VBVFQanCSy+x+mWkdqumcjRk5iZpT3PcVsGnpPPE1jwky8VUYQg4g9QG3vqQJ95KLLbqZDBOO5yhqn4h46AC9u2qWsBQtLk7ly4V5pI0yQcTxC+K9/qKmfp6+7iZz/1LAvrzT6EgUT8QM9bURSF5MjBI82ukXG2AmFWl2+AlGipQVI9fZhr68zW6nj024bZsiwSuhu3MCjfUdyXUuK3Kgye+xne/+P/xlTIhe5SMSyL6zsWiU/uXaAGcHl9dIxOsrK+hmLUsFU30YFhrGiMUbePqr+DbHUYCXg8HjqMCr1aA1FrdnR53LcnYqX20TbeD0lMzuDKZaltGdgeH4rRIGQUsfuHcfuHCS68wfFYA6RE9Whc8nSTmDjD8sVX6QvevkalYVLqGqVnj1JKNZ+l91gKT18v5aFx1tLLaKEIQ8mmw+JKDrGGhV5Io1gWZT2Gd3gUS3n0C/N+4laoBvx+Up4s6XIJ3R9ASkktl+ETfXsv0DkoLpfrUFdCfpzRdZ2Jod0F8CcGe8lV52hoXdSMOsLtIW4UGey5d02gMxZ5aM+LSU5Ok492sLo6B0IhcGKMrngHK9UKdmVjV5eRYZoo8STdw2PkwjHM1XkQAlffKIkH9KC6x48zv75En7WDW1VpmBYrrjDDM58gnVsiwu50U0kLMN6b4K31LfTw7YmiVthiqrupE7/Px9TwgzcbHJS9itf9qW6y1+fINjS8oQi1UpGgUWRschQpJRduLpKt29hA1A0z40NIe4DrC1e4PHcBe6eA1EP4p6cYO7v3OgyA2Mgk26vX6R0YvLWvUDfx9h/jmZrNu/k6hjeKBDRp0a9IAoEAxtwq7ruiEjuw/7104sRxXj7/HpFGGbtcQagKhi/E+EAvM1MTXHzZh5h7D0yTWucAM1/6JXLbO7xSKFJJXyZglKkpbjLxEY5Nz9DfFeed1XW88QRCCCqFbQaDrltRnz8Uwh+a2iWDPxDAHwyhpJqfaQhYzWxw7uyjf+zJT+yzZTbzW6TzO7gUwWhv9z3DaodHg23bzK2kqRoWYa+HvmTiYxH12LbNwg+/T7Kew+txU64bbIZSDDz76Ycun5SSjYWbWMUt1GCMrsFhhBDklhcwLrxGwtt0GDJVE/d7VWnIAAAFPklEQVSJM8T7BlnP5pjdKFCzQVdgpDNEqvPHc04eJoVikc18gWgoQDx6/4m4WiqRu/IuSqWArQcIj00TvEcbK0BhM0Px6jso5W1sLYA+cpyO/mYHz/zqOuliFVtCTFOZHGrWduZf+z59jTxuVcW2bZZMD6kXvoDnHpHf+7Pz3MwW0TWNeqNOzOvmzPT4PR8Y+NbVm6wbKoqU2ELgs2t8cnIYj8dDvV7n5moGW0p6O6JEwnsXrj+kWCrx8ut/j6r5cKkqpeIOT06NMzr44BO48+AwhyNPdnWZRiGPHusi1v3wn853P+rVKtm56wB0DB9D83rvc4bDvWhOpHNYhU3wBkiMTh7oAVylcpn17NauJ0nej2x+i81CCb/m/rGdFiklK+sZGobJQKr7x84QOMbdwcHBoQ05qHF3Hmbu4ODg0IY4xt3BwcGhDXGMu4ODg0Mb4hh3BwcHhzbEMe4ODg4ObYhj3B0cHBzaEMe4Ozg4OLQhjnF3cHBwaEMObRGTEGITWDyUize/Hfhj8y1Rh4SjA0cH4OgAfvJ0MCClvO8XNhyacT9MhBBvHWSFVzvj6MDRATg6gPbVgZOWcXBwcGhDHOPu4ODg0IYcVeP+9cMW4GOAowNHB+DoANpUB0cy5+7g4ODQ7hxVz93BwcGhrWlr4y6E6BNC/LUQ4ooQ4pIQ4lda+2NCiJeFELOt3wd7gv9PIEIIXQhxXgjxfksH/7G1f0gI8UZLB38ohGj7r7ISQqhCiHeFEH/e2j6KOlgQQlwUQrwnhHirte/IjAcAIURECPFtIcTVlm14th110NbGHTCBX5VSTgLPAL8shHgC+DXgB1LKMeAHre12pQ58Wkp5EpgBfloI8QzwO8B/aelgC/jXhyjj4+JXgCt3bB9FHQB8Sko5c0f731EaDwD/Ffi+lHICOEnznmg7HbS1cZdSpqWU77ReF2l+iD3AF4E/aB32B8CXDkfCR49sUmptuls/Evg08O3W/rbWAYAQohf4p8DvtbYFR0wH9+DIjAchRAg4C3wDQErZkFJu04Y6aGvjfidCiEHgFPAGkJBSpqE5AQBdhyfZo6eVjngP2ABeBm4C21JKs3XICs1Jr535XeA/AHZrO87R0wE0J/a/FEK8LYT4amvfURoPw8Am8D9aKbrfE0L4aUMdHAnjLoQIAP8P+HdSyp3DludxI6W0pJQzQC/wNDC512GPV6rHhxDiC8CGlPLtO3fvcWjb6uAOnpdSngY+TzNNefawBXrMuIDTwH+XUp4CyrRBCmYv2t64CyHcNA37N6WUf9zanRFCJFvvJ2l6tG1PK/x8lWb9ISKE+PBr2HuBtcOS6zHwPPDPhBALwP+lmY75XY6WDgCQUq61fm8Af0Jzsj9K42EFWJFSvtHa/jZNY992Omhr497Kq34DuCKl/M93vPVd4Cut118B/vRxy/a4EEJ0CiEirdde4DM0aw9/Dfx867C21oGU8tellL1SykHgJeAVKeUvcoR0ACCE8Ashgh++Bj4LfMARGg9SynVgWQgx3tp1DrhMG+qgrRcxCSE+CbwGXOR2rvU3aObd/wjoB5aAL0sp84ci5CNGCHGCZoFIpTmZ/5GU8reEEMM0vdgY8C7wS1LK+uFJ+ngQQrwI/Hsp5ReOmg5a/++ftDZdwP+RUv62ECLOERkPAEKIGZqFdQ8wB/wrWmODNtJBWxt3BwcHh6NKW6dlHBwcHI4qjnF3cHBwaEMc4+7g4ODQhjjG3cHBwaENcYy7g4ODQxviGHcHBweHNsQx7g4ODg5tiGPcHRwcHNqQfwDrPyNKzmZPUgAAAABJRU5ErkJggg==\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "plotfit(logit_smoker_age)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "-371.38650786619064"
+      ]
+     },
+     "execution_count": 20,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "logit_smoker_age.llf"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Intercept        6.250847\n",
+       "smoker[T.Yes]   -0.408103\n",
+       "age             -0.092403\n",
+       "dtype: float64"
+      ]
+     },
+     "execution_count": 21,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "logit_smoker_age.params"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>0</th>\n",
+       "      <th>1</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>Intercept</th>\n",
+       "      <td>5.331126</td>\n",
+       "      <td>7.170568</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>smoker[T.Yes]</th>\n",
+       "      <td>-0.777754</td>\n",
+       "      <td>-0.038451</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>age</th>\n",
+       "      <td>-0.109478</td>\n",
+       "      <td>-0.075327</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                      0         1\n",
+       "Intercept      5.331126  7.170568\n",
+       "smoker[T.Yes] -0.777754 -0.038451\n",
+       "age           -0.109478 -0.075327"
+      ]
+     },
+     "execution_count": 22,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "logit_smoker_age.conf_int()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<table class=\"simpletable\">\n",
+       "<caption>Logit Regression Results</caption>\n",
+       "<tr>\n",
+       "  <th>Dep. Variable:</th>      <td>outcome</td>     <th>  No. Observations:  </th>  <td>  1071</td>  \n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Model:</th>               <td>Logit</td>      <th>  Df Residuals:      </th>  <td>  1068</td>  \n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Method:</th>               <td>MLE</td>       <th>  Df Model:          </th>  <td>     2</td>  \n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Date:</th>          <td>Fri, 28 Sep 2018</td> <th>  Pseudo R-squ.:     </th>  <td>0.1776</td>  \n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Time:</th>              <td>15:40:45</td>     <th>  Log-Likelihood:    </th> <td> -371.39</td> \n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>converged:</th>           <td>True</td>       <th>  LL-Null:           </th> <td> -451.59</td> \n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th> </th>                      <td> </td>        <th>  LLR p-value:       </th> <td>1.469e-35</td>\n",
+       "</tr>\n",
+       "</table>\n",
+       "<table class=\"simpletable\">\n",
+       "<tr>\n",
+       "        <td></td>           <th>coef</th>     <th>std err</th>      <th>z</th>      <th>P>|z|</th>  <th>[0.025</th>    <th>0.975]</th>  \n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Intercept</th>     <td>    6.2508</td> <td>    0.469</td> <td>   13.321</td> <td> 0.000</td> <td>    5.331</td> <td>    7.171</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>smoker[T.Yes]</th> <td>   -0.4081</td> <td>    0.189</td> <td>   -2.164</td> <td> 0.030</td> <td>   -0.778</td> <td>   -0.038</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>age</th>           <td>   -0.0924</td> <td>    0.009</td> <td>  -10.606</td> <td> 0.000</td> <td>   -0.109</td> <td>   -0.075</td>\n",
+       "</tr>\n",
+       "</table>"
+      ],
+      "text/plain": [
+       "<class 'statsmodels.iolib.summary.Summary'>\n",
+       "\"\"\"\n",
+       "                           Logit Regression Results                           \n",
+       "==============================================================================\n",
+       "Dep. Variable:                outcome   No. Observations:                 1071\n",
+       "Model:                          Logit   Df Residuals:                     1068\n",
+       "Method:                           MLE   Df Model:                            2\n",
+       "Date:                Fri, 28 Sep 2018   Pseudo R-squ.:                  0.1776\n",
+       "Time:                        15:40:45   Log-Likelihood:                -371.39\n",
+       "converged:                       True   LL-Null:                       -451.59\n",
+       "                                        LLR p-value:                 1.469e-35\n",
+       "=================================================================================\n",
+       "                    coef    std err          z      P>|z|      [0.025      0.975]\n",
+       "---------------------------------------------------------------------------------\n",
+       "Intercept         6.2508      0.469     13.321      0.000       5.331       7.171\n",
+       "smoker[T.Yes]    -0.4081      0.189     -2.164      0.030      -0.778      -0.038\n",
+       "age              -0.0924      0.009    -10.606      0.000      -0.109      -0.075\n",
+       "=================================================================================\n",
+       "\"\"\""
+      ]
+     },
+     "execution_count": 23,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "logit_smoker_age.summary()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.5"
+  },
+  "toc": {
+   "base_numbering": 1,
+   "nav_menu": {},
+   "number_sections": true,
+   "sideBar": true,
+   "skip_h1_title": false,
+   "title_cell": "Table of Contents",
+   "title_sidebar": "Contents",
+   "toc_cell": false,
+   "toc_position": {},
+   "toc_section_display": true,
+   "toc_window_display": false
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/bootstrapping In Python Statistics.ipynb b/bootstrapping In Python Statistics.ipynb
new file mode 100644
index 0000000..90ba374
--- /dev/null
+++ b/bootstrapping In Python Statistics.ipynb	
@@ -0,0 +1,578 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Python statistics essential training - 04_03_bootstrapping"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Standard imports"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import math\n",
+    "import io"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "\n",
+    "import matplotlib\n",
+    "import matplotlib.pyplot as pp\n",
+    "\n",
+    "%matplotlib inline"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import scipy.stats\n",
+    "import scipy.optimize\n",
+    "import scipy.spatial"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "pop = pd.read_csv('grades.csv')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>grade</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>3.648651</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>5.959915</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>7.387370</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>4.047515</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>2.846912</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "      grade\n",
+       "0  3.648651\n",
+       "1  5.959915\n",
+       "2  7.387370\n",
+       "3  4.047515\n",
+       "4  2.846912"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "pop.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<matplotlib.axes._subplots.AxesSubplot at 0x1a180255c0>"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXQAAAD8CAYAAABn919SAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDIuMS4yLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvNQv5yAAAEcJJREFUeJzt3X9sXWd9x/H3t0kjkjgkHYWbzu3iIqFoKJkGN2JAtQ43FBVaAUP7oxUgQEieNsYKA5GyaUL7Y1rRJgbSpk2oLe1EF4/1x8YMYq2osw5Eu8VpWVLSDAZZiWmaotI0LpFCmu/+8PVwg+v70/ecPLxf0pXvvX7uOR8/1/nk+PE915GZSJLOfedVHUCSNBgWuiQVwkKXpEJY6JJUCAtdkgphoUtSISx0SSqEhS5JhbDQJakQq4e5swsvvDDHxsaWHfPss8+yfv364QTqgrm6V9ds5upOXXNBfbMNOtfMzMwPM/OlbQdm5tAuzWYz25menm47pgrm6l5ds5mrO3XNlVnfbIPOBezNDjrWJRdJKoSFLkmFsNAlqRAWuiQVwkKXpEK0LfSIuCUijkXEgSU+99GIyIi4cGXiSZI61ckR+q3AVWffGRGXAFcCjw04kySpB20LPTPvB55a4lN/CXwM8G/YSVIN9LSGHhFvBWYz85sDziNJ6lFkB38kOiLGgKnM3BYR64Bp4E2ZeTwiDgM7MvOHL/DYCWACoNFoNCcnJ5fd19zcHCMjI918DUPx85Tr0NETnHruTN/baayFJ05295g1q85j6+YNfe97OXV7Lhfmu5f56kenc123+VqsrtkGnWt8fHwmM3e0HdjJ6aTAGHCgdX07cAw43LqcZn4dfXO77Xjq/+CtRK4tu6YGsp1esg1q38up23O58DUPO1enc123+VqsrtmqOvW/6zfnysz9wMsWbrc7QpckDUcnL1vcDXwD2BoRRyLi/SsfS5LUrbZH6Jl5XZvPjw0sjSSpZ54pKkmFsNAlqRAWuiQVwkKXpEJY6JJUCAtdkgphoUtSISx0SSqEhS5JhbDQJakQXb85l7SSRjetZeyGL63oPj6y/TTvPWsfo5vW8vUbrljR/eqnLrvxPmaf7v+9gpd6LpdT+vNsoatWhvGPbc+ePRx+5xued99K/yei55t9+iSHb7y67+0s9Vwup/Tn2SUXSSqEhS5JhbDQJakQFrokFcJCl6RCWOiSVAgLXZIKYaFLUiEsdEkqRNtCj4hbIuJYRBxYdN+fR8SjEfFfEXF3RGxa2ZiSpHY6OUK/FbjqrPvuBbZl5q8A/w18fMC5JEldalvomXk/8NRZ992TmadbNx8ALl6BbJKkLkRmth8UMQZMZea2JT73L8A/ZObnX+CxE8AEQKPRaE5OTi67r7m5OUZGRtpmGrYqch06eoJTz51ZdkxjLTzR/5vWPc+aVeexdfOGvrdzLj2X+2ePs310YyV5FvY97Pnq9GteiVyDmu9usw3reR70nI2Pj89k5o62AzOz7QUYAw4scf8fAXfT+o+h3aXZbGY709PTbcdUoYpcW3ZNtR1T1/nKrG+2pXJ1MtcrZWHfw56vTr/mlcg1qPnuNtuwnudBzxmwNzvo2J7fPjci3gNcA+xs7VCSVKGeCj0irgJ2Ab+RmT8ebCRJUi86ednibuAbwNaIOBIR7wf+CtgA3BsRD0fE365wTklSG22P0DPzuiXuvnkFskiS+uCZopJUCAtdkgphoUtSISx0SSqEhS5JhbDQJakQFrokFcJCl6RCWOiSVAgLXZIKYaFLUiEsdEkqhIUuSYWw0CWpEBa6JBXCQpekQljoklQIC12SCmGhS1IhLHRJKkTbQo+IWyLiWEQcWHTfL0TEvRHx7dbHC1Y2piSpnU6O0G8FrjrrvhuAr2bmK4Cvtm5LkirUttAz837gqbPufhtwW+v6bcDbB5xLktSlXtfQG5n5OEDr48sGF0mS1IvIzPaDIsaAqczc1rr9dGZuWvT5H2XmkuvoETEBTAA0Go3m5OTksvuam5tjZGSk0/xDU0Wu/bPH2T66cdkxdZ0vqG+2pXJ1MtcrZWHfw56vQ0dPcOq5M23HNdbCEycHu+81q85j6+YNfW+n2zkb1vM86OdyfHx8JjN3tB2YmW0vwBhwYNHtQ8BFresXAYc62U6z2cx2pqen246pQhW5tuyaajumrvOVWd9sS+XqZK5XysK+z6X5qotusw3reR70nAF7s4OO7XXJ5YvAe1rX3wP8c4/bkSQNSCcvW9wNfAPYGhFHIuL9wI3AlRHxbeDK1m1JUoVWtxuQmde9wKd2DjiLJKkPnikqSYWw0CWpEBa6JBXCQpekQljoklQIC12SCmGhS1IhLHRJKoSFLkmFsNAlqRBtT/2Xfh6MblrL2A1fqmzf0iBY6BLw9RuuqDqC1DeXXCSpEBa6JBXCQpekQljoklQIC12SCmGhS1IhLHRJKoSFLkmFsNAlqRB9FXpEfDgiHomIAxGxOyJeNKhgkqTu9FzoETEK/D6wIzO3AauAawcVTJLUnX6XXFYDayNiNbAO+EH/kSRJvYjM7P3BEdcDfwqcBO7JzHcuMWYCmABoNBrNycnJZbc5NzfHyMhIz5lWShW59s8eZ/voxmXH1HW+oL7ZzNWduuaC7rMdOnqCU8+dWcFE8xpr4YmTz79vzarz2Lp5Q0/bGx8fn8nMHW0HZmZPF+AC4D7gpcD5wD8B71ruMc1mM9uZnp5uO6YKVeTasmuq7Zi6zldmfbOZqzt1zZVZ32xL5erk3/MLAfZmB73cz5LLG4HvZeaTmfkT4C7g9X1sT5LUh34K/THgtRGxLiIC2AkcHEwsSVK3ei70zHwQuAPYB+xvbeuzA8olSepSX3+xKDM/AXxiQFkkSX3wTFFJKoSFLkmFsNAlqRAWuiQVwkKXpEJY6JJUCAtdkgphoUtSISx0SSqEhS5JhbDQJakQFrokFcJCl6RCWOiSVAgLXZIKYaFLUiEsdEkqhIUuSYWw0CWpEBa6JBWir0KPiE0RcUdEPBoRByPidYMKJknqzuo+H/8Z4CuZ+VsRsQZYN4BMkqQe9FzoEfFi4HLgvQCZeQo4NZhYkqRu9bPk8nLgSeBzEfFQRNwUEesHlEuS1KXIzN4eGLEDeAC4LDMfjIjPAM9k5h+fNW4CmABoNBrNycnJZbc7NzfHyMhIT5lWyqGjJ7hgzRmeODnc/a5ZdR5bN29Ydkwd52tBXbOZqzt1zQX1zbZUrv2zx9k+urGn7Y2Pj89k5o62AzOzpwuwGTi86PavA19a7jHNZjPbmZ6ebjtm2Lbsmqplrsx6zteCumYzV3fqmiuzvtmWyrVl11TP2wP2Zge93POSS2YeBb4fEVtbd+0EvtXr9iRJ/en3VS4fBG5vvcLlu8D7+o8kSepFX4WemQ8D7dd1JEkrzjNFJakQFrokFcJCl6RCWOiSVAgLXZIKYaFLUiEsdEkqhIUuSYWw0CWpEBa6JBXCQpekQljoklQIC12SCmGhS1IhLHRJKoSFLkmFsNAlqRAWuiQVwkKXpEJY6JJUCAtdkgrRd6FHxKqIeCgipgYRSJLUm0EcoV8PHBzAdiRJfeir0CPiYuBq4KbBxJEk9arfI/RPAx8DzgwgiySpD5GZvT0w4hrgLZn5uxHxBuCjmXnNEuMmgAmARqPRnJycXHa7c3NzjIyM9JRppeyfPc6lG1fVLhfUc74W1DWbubpT11xQ32xL5do/e5ztoxt72t74+PhMZu5oOzAze7oAfwYcAQ4DR4EfA59f7jHNZjPbmZ6ebjtm2Lbsmqplrsx6zteCumYzV3fqmiuzvtmWyrVl11TP2wP2Zge93POSS2Z+PDMvzswx4Frgvsx8V6/bkyT1x9ehS1IhVg9iI5m5B9gziG1JknrjEbokFcJCl6RCWOiSVAgLXZIKYaFLUiEsdEkqhIUuSYWw0CWpEBa6JBXCQpekQljoklQIC12SCmGhS1IhLHRJKoSFLkmFsNAlqRAWuiQVwkKXpEJY6JJUCAtdkgphoUtSIXou9Ii4JCKmI+JgRDwSEdcPMpgkqTur+3jsaeAjmbkvIjYAMxFxb2Z+a0DZJEld6PkIPTMfz8x9resngIPA6KCCSZK6E5nZ/0YixoD7gW2Z+cxZn5sAJgAajUZzcnJy2W3Nzc0xMjLSd6ZB2j97nEs3rqpdLqjnfC2oazZzdaeuuaC+2ZbKtX/2ONtHN/a0vfHx8ZnM3NF2YGb2dQFGgBngHe3GNpvNbGd6errtmGHbsmuqlrky6zlfC+qazVzdqWuuzPpmWyrXll1TPW8P2Jsd9HFfr3KJiPOBO4HbM/OufrYlSepPP69yCeBm4GBmfmpwkSRJvejnCP0y4N3AFRHxcOvylgHlkiR1qeeXLWbm14AYYBZJUh88U1SSCmGhS1IhLHRJKoSFLkmFsNAlqRAWuiQVwkKXpEJY6JJUCAtdkgrRzx+4GKrLbryP2adPVrLv0U1rK9mvJHXjnCn02adPcvjGqyvb/549eyrbtyR1wiUXSSqEhS5JhbDQJakQFrokFcJCl6RCWOiSVAgLXZIKYaFLUiEsdEkqRF+FHhFXRcShiPhORNwwqFCSpO71XOgRsQr4a+DNwCuB6yLilYMKJknqTj9H6K8BvpOZ383MU8Ak8LbBxJIkdaufQh8Fvr/o9pHWfZKkCvTzbouxxH35M4MiJoCJ1s25iDjUZrsXAj9ccoef7CrfoL1grorVNRfUN5u5ulPXXFDfbEvm6qPDtnQyqJ9CPwJcsuj2xcAPzh6UmZ8FPtvpRiNib2bu6CPXijBX9+qazVzdqWsuqG+2qnL1s+Tyn8ArIuLSiFgDXAt8cTCxJEnd6vkIPTNPR8TvAf8KrAJuycxHBpZMktSVvv5iUWZ+GfjygLIs6Hh5ZsjM1b26ZjNXd+qaC+qbrZJckfkzv8eUJJ2DPPVfkgpRm0KPiFsi4lhEHKg6y2IRcUlETEfEwYh4JCKurzoTQES8KCL+IyK+2cr1J1VnWiwiVkXEQxExVXWWxSLicETsj4iHI2Jv1XkWRMSmiLgjIh5tfa+9rgaZtrbmaeHyTER8qOpcABHx4db3/YGI2B0RL6o6E0BEXN/K9EgVc1WbJZeIuByYA/4uM7dVnWdBRFwEXJSZ+yJiAzADvD0zv1VxrgDWZ+ZcRJwPfA24PjMfqDLXgoj4A2AH8OLMvKbqPAsi4jCwIzNr9drliLgN+PfMvKn1qrF1mfl01bkWtN7qYxb4tcz834qzjDL//f7KzDwZEV8AvpyZt1acaxvzZ8y/BjgFfAX4ncz89rAy1OYIPTPvB56qOsfZMvPxzNzXun4COEgNzojNeXOtm+e3LrX43zkiLgauBm6qOsu5ICJeDFwO3AyQmafqVOYtO4H/qbrMF1kNrI2I1cA6ljgHpgK/DDyQmT/OzNPAvwG/OcwAtSn0c0FEjAGvAh6sNsm81rLGw8Ax4N7MrEUu4NPAx4AzVQdZQgL3RMRM6yzmOng58CTwudYy1U0Rsb7qUGe5FthddQiAzJwF/gJ4DHgcOJ6Z91SbCoADwOUR8ZKIWAe8heeffLniLPQORcQIcCfwocx8puo8AJn5XGb+KvNn6b6m9SNfpSLiGuBYZs5UneUFXJaZr2b+XUI/0Frqq9pq4NXA32Tmq4Bngdq8HXVrCeitwD9WnQUgIi5g/o0ALwV+EVgfEe+qNhVk5kHgk8C9zC+3fBM4PcwMFnoHWmvUdwK3Z+ZdVec5W+vH8z3AVRVHAbgMeGtrrXoSuCIiPl9tpJ/KzB+0Ph4D7mZ+vbNqR4Aji37CuoP5gq+LNwP7MvOJqoO0vBH4XmY+mZk/Ae4CXl9xJgAy8+bMfHVmXs78EvLQ1s/BQm+r9cvHm4GDmfmpqvMsiIiXRsSm1vW1zH+TP1ptKsjMj2fmxZk5xvyP6fdlZuVHTwARsb71i21aSxpvYv7H5Epl5lHg+xGxtXXXTqDSX7qf5TpqstzS8hjw2ohY1/r3uZP5321VLiJe1vr4S8A7GPK89XWm6CBFxG7gDcCFEXEE+ERm3lxtKmD+iPPdwP7WejXAH7bOkq3SRcBtrVcfnAd8ITNr9RLBGmoAd893AKuBv8/Mr1Qb6f99ELi9tbzxXeB9FecBoLUWfCXw21VnWZCZD0bEHcA+5pc0HqI+Z4zeGREvAX4CfCAzfzTMndfmZYuSpP645CJJhbDQJakQFrokFcJCl6RCWOiSVAgLXZIKYaFLUiEsdEkqxP8Bz5rYewVzBuQAAAAASUVORK5CYII=\n",
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x1a17a1cb00>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "pop.grade.hist(histtype='step')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>grade</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>count</th>\n",
+       "      <td>100.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>mean</th>\n",
+       "      <td>5.508561</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>std</th>\n",
+       "      <td>1.984988</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>min</th>\n",
+       "      <td>1.160899</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>25%</th>\n",
+       "      <td>3.921372</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>50%</th>\n",
+       "      <td>5.688527</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>75%</th>\n",
+       "      <td>7.272162</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>max</th>\n",
+       "      <td>9.120705</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "            grade\n",
+       "count  100.000000\n",
+       "mean     5.508561\n",
+       "std      1.984988\n",
+       "min      1.160899\n",
+       "25%      3.921372\n",
+       "50%      5.688527\n",
+       "75%      7.272162\n",
+       "max      9.120705"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "pop.describe()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>grade</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>count</th>\n",
+       "      <td>100.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>mean</th>\n",
+       "      <td>5.436984</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>std</th>\n",
+       "      <td>2.043781</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>min</th>\n",
+       "      <td>1.160899</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>25%</th>\n",
+       "      <td>3.620426</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>50%</th>\n",
+       "      <td>5.860997</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>75%</th>\n",
+       "      <td>7.132170</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>max</th>\n",
+       "      <td>9.120705</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "            grade\n",
+       "count  100.000000\n",
+       "mean     5.436984\n",
+       "std      2.043781\n",
+       "min      1.160899\n",
+       "25%      3.620426\n",
+       "50%      5.860997\n",
+       "75%      7.132170\n",
+       "max      9.120705"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "pop.sample(100,replace=True).describe()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "bootstrap = pd.DataFrame({'meangrade': [pop.sample(100,replace=True).grade.mean() for i in range(1000)]})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<matplotlib.lines.Line2D at 0x1a17fc5b00>"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x1a17fc5d68>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "bootstrap.meangrade.hist(histtype='step')\n",
+    "pp.axvline(pop.grade.mean(),color='C1')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(5.127586404418329, 5.907604515299203)"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "bootstrap.meangrade.quantile(0.025), bootstrap.meangrade.quantile(0.975)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[<matplotlib.lines.Line2D at 0x1a187cf7f0>]"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYQAAAD8CAYAAAB3u9PLAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDIuMS4yLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvNQv5yAAAIABJREFUeJzt3Xl81fWV+P/Xyc3GkhCyEgiQQMISZJMICooLi7hi695N5+uMM52xnaltZ9qZqZ1xZn7TzrczdnOsttraVqvWVqUKoqCILCJhEQhrEpZshOwJ2ZN7fn/cG7/XGMgNJPnc5Twfj/vg3s96PiL33PcuqooxxhgT4XQAxhhjAoMlBGOMMYAlBGOMMV6WEIwxxgCWEIwxxnhZQjDGGANYQjDGGONlCcEYYwxgCcEYY4xXpNMBDERycrJmZmY6HYYxxgSVXbt2VatqSn/HBVVCyMzMJD8/3+kwjDEmqIjISX+OsyojY4wxgCUEY4wxXpYQjDHGAJYQjDHGePmVEERklYgcEZFCEflWH/sfFpGDIrJPRDaKyGSfffeJyDHv6z6f7QtEZL/3mj8WERmcRzLGGHMh+k0IIuICHgduAHKBe0Ukt9dhe4A8VZ0DvAz8l/fcROC7wCJgIfBdERnrPecJ4EEgx/taddFPY4wx5oL5U0JYCBSqarGqdgAvAKt9D1DVd1W1xfvxAyDD+/564G1VrVXVOuBtYJWIpAPxqrpdPUu2/Rq4bRCexxhjzAXyZxzCBKDE53Mpnl/85/IAsO48507wvkr72G7MgHV0uTlV20JFQysV9W1kjB3BFVOTsFrIwHOyppm3CiqZMHYEcycmMH5MrP09BRB/EkJff1t9LsQsIl8A8oCr+zl3INd8EE/VEpMmTeovVhNm9pyq46Hn91BW3/qJ7QszE/nG9dNZmJXoUGSmh6ry/rFqfrXtBO8eOYPvMu4pcTH8040zuW2+/R4MBP4khFJgos/nDKC890Eishz4J+BqVW33OfeaXudu8m7P6LX9U9cEUNWngKcA8vLy+kwaJvyoKk9vOc731h1m3JhY/u8dc5iUOJL0MSN471gVP9l4jLue3M5Nc9L54d3ziHJZhzqn/OCtIzz+bhHJo2P4ynU53Lkgg5rmDvaV1vPqnjL+7sW9FFWd5WvLpxERYaUFJ4nq+b9jRSQSOAosA8qAncDnVLXA55j5eBqTV6nqMZ/ticAu4FLvpt3AAlWtFZGdwFeAHcBa4CequvZ8seTl5alNXWHcbuWrL+zh9X0VXD8rjf+6Yy5jRkR94pi2zm5+9l4RP9xwjLvyMvj+7XOsasIBP33nGD946yj3LpzIv9w6i5hI1yf2d3S5+edX9/NSfik3zUnnv++cS2yU6xxXMxdKRHapal5/x/VbQlDVLhF5CFgPuIBnVLVARB4F8lV1DfB/gdHA773/6E6p6q3eL/5/w5NEAB5V1Vrv+y8DvwJG4GlzWIcxfnh6y3Fe31fBwyum8ZXrsvv8oo+NcvF3y6fhdis/fqeQ9DEj+NqKaQ5EG75+8X4xP3jrKJ+dP4H/uG12n7/+oyMj+P7tc8hOHc1/rjvMiCgXP7hzrgPRGvBzcjvvL/e1vbY94vN++XnOfQZ4po/t+cAlfkdqDLCvtJ7/Wn+Y62elnTMZ+PraimmUN7Txo43HGJ8Qy92XWTvUcHjzQAX//sYhbpw9jv+6Y855q4JEhAeXTqWxtYufvlvIytw0Vs4aN4zRmh5WsWqCRlNbJ1/53R5SRsf4XQUkIvznZ2dzVU4y33m1gJM1zcMQaXhrauvkkdcKyE2P54d3zyfSz/abry7LITc9nn98ZT81Z9v7P8EMOksIJmg88loBpXWt/Pje+SSMjPb7vChXBD+4cy5RLuHfXj80hBEagP9+6yhVZ9v5/z47m+hI/79ioiMj+J+759LY2sU/vrKf/to3zeCzhGCCwq6Tdbyyp4y/uTabvMyBdyVNi4/lK8ty2HCokk1HzgxBhAY8VXq/3n6CL14+mXkTEwZ8/oxx8Ty8chrrCypZ81GfHQ/NELKEYILCY28fJWlUNH+5dMoFX+P/LMliSvIoHv3TQTq63IMYnQHodiv/9MoBkkfH8I3rp1/wdf7iqinkpsfz2NtH6eq2v6fhZAnBBLwPimvYUljNl6+ZyqiYC1/kLzoygkduyaW4uplnth4fxAgNwIs7S9hf1sAjt+QSHxvV/wnn4IoQ/nZ5DidqWvjTPislDCdLCCagqSr/89ZR0uJj+MLlk/s/oR/XTE9l+cw0frLxGPUtHYMQoQHo6nbzxHuFzJ2YwE2z0y/6eitmpjFjXBw/eaeQbre1JQwXSwgmoG0prObDE7X8zbXZgzZg6esrp9Hc0c1zO04NyvUMvLG/gpLaVv76mqmDMgAwIkL46rIciquaeWN/xSBEaPxhCcEELFXlv986yoSEEdx92cT+T/DTzPR4rspJ5pdbT9De1T1o1w1XqsoTm4rITh3Niplpg3bdVbPGkZM6mp9sPIbbSgnDwhKCCVi7T9Wxt6SeL18z9VNTHlysv1w6leqz7by6p2xQrxuONh2p4vDpJv7q6qmDOhdRRITwlWU5HDtzlrUHrJQwHCwhmID13I5TjI6J5DNDMBPmkuwkctPj+fn7x+3X50V6YlMR48fEcuvc8YN+7Ztmp5OZNJJfbT0x6Nc2n2YJwQSk+pYOXt9XwWfmT7ionkXn4pkuYQqFZ86y6aiNS7hQ+Sdq+fBELX+xdMqABqH5yxUh3LtwEvkn6yg80zTo1zefZAnBBKQ/7C6jo8vN5xYN3dxDN81JZ/yYWJ58r3jI7hHqfrXtBGNGRA1qG09vty/IIDJCeOHDkv4PNhfFEoIJOKrKcztOcumkBGamxw/ZfaJcEfzZkix2HK/l8OnGIbtPqKpr7uCtgko+M38CI6MHvxTXI3l0DCty0/jD7lLrBDDELCGYgLPjeC3FVc18btHFjzvoz+0LMohyCb/PL+3/YPMJr+wpo6PbPaSlgx73LJxEXUsnbx+sHPJ7hTNLCCbgPL/jFPGxkdw85+IHOPUncVQ0y2em8eqeMpvOYgBUlRd3ljB34tCW4npcmZ3MhIQRVm00xCwhmIBS19zBmwdOc/uCjGFbOeuuvInUNHfwzmFrXPbX3pJ6jlQ2cc8wlA7A07h8V95EthRWU1LbMiz3DEd+JQQRWSUiR0SkUES+1cf+pSKyW0S6ROQOn+3Xishen1ebiNzm3fcrETnus2/e4D2WCVbrDpymo9vNHQsy+j94kFyVk0xqXAy/z7dfn/56Kb+EEVGuYSnF9bgzL4MI8cyZZIZGvwlBRFzA48ANQC5wr4jk9jrsFHA/8LzvRlV9V1Xnqeo84DqgBXjL55Bv9uxX1b0X/hgmVLy+r5wpKaPIHYZqiB6RrghuX5DBpqNVnGlsG7b7Bqvm9i7W7C3n5jnpxF3EJHYDNT5hBEuyk3ntozJbK2GI+FNCWAgUqmqxqnYALwCrfQ9Q1ROqug84XyXsHcA6VbXynunTmaY2Piiu4eY54wdlPpyBuHNBBt1u5Y82crlfb+yroLmjm3sWDk91ka9b5oynpLaVA2XWK2wo+JMQJgC+ZbRS77aBugf4Xa9t/yEi+0TkMRGJuYBrmhCybv9p3Aq3DGM1RI8pKaPJmzyWl/JL7NdnP17ZU8aUlFFcOmnssN975aw0IiPEJrwbIv4khL5+qg3oX4yIpAOzgfU+m78NzAAuAxKBfzjHuQ+KSL6I5FdVVQ3ktibIvL6vnBnj4shJi3Pk/nfmZVBc1cxHpQ2O3D8YnGls44PjNdw6d/hLcQAJI6NZkp3MG/vLLXEPAX8SQingWzbMAAa6asVdwCuq2tmzQVUr1KMd+CWeqqlPUdWnVDVPVfNSUlIGeFsTLMrrW9l5om5YGyl7WzUrnSiX8IYtynJOb+yvQBVunjP48xb566bZ6VZtNET8SQg7gRwRyRKRaDxVP2sGeJ976VVd5C01IJ6fGbcBBwZ4TRNC1nqrAJz8ohkzMoqlOSm8sa/CJrw7hz99VE5uejzZqaMdi6Gn2uj1/Za4B1u/CUFVu4CH8FT3HAJeUtUCEXlURG4FEJHLRKQUuBN4UkQKes4XkUw8JYz3el36ORHZD+wHkoF/v/jHMcHqT/sqmD1hDJnJoxyN46Y56ZQ3tLGnpM7ROAJRSW0Lu0/Vc8sQzGo6ED3VRmv3V1i10SDzawISVV0LrO217RGf9zvxVCX1de4J+miEVtXrBhKoCV0ltS18VFLPt2+Y4XQorMhNIzoygtf3VbBgcqLT4QSUNz4uxTlXrdfjpjnp/P3L+9hf1sCcjASnwwkZNlLZOK5nfppVl4xzOBKIi43immkprN1v1Ua9/emjcuZPSmBi4kinQ2FlrvU2GgqWEIzjNh6uJCd1NJOTnK0u6nHTnHQqG9vJP2nVRj2Kqs5SUN7ILQ628fhKGBnN4uxk1h847XQoIcUSgnFUY1snO4prWTaIa/FerOUz04iNiuB16230sdc/qkDEkywDxYqZqZyoaaGo6qzToYQMSwjGUe8dqaLLrazITXU6lI+NionkuhmprN1/mm6rNgJg3YEKLpucSFp8rNOhfOzaGZ7/Z945ZJMSDhZLCMZRGw5VkjgqmnkTh3/U6/ncNHs81Wfb+fB4rdOhOO5kTTOHTzdxfQC08fjKGDuSGePi2HjY1kgYLJYQjGO6ut1sOlLFtdNTcUUM/6jX87lmegrRkRG8ddDqqNcXeP4brMwNnGq9HstmprLzRB0NLZ39H2z6ZQnBOCb/ZB0NrZ0BVV3UY1RMJEtzknmroDLs+7q/eeA0s8bHB0Tvot6um5FGt1t575hNazMYLCEYx2w4WEm0K4KrcgJzSpKVueMoq2+loDx8p0g409jG7lP1rJoVWNVFPeZNTCBpVDTvHLJqo8FgCcE4QlXZcKiSK6YmMSpm6BZovxjLZqYSIfBWGK/j2/PsgdZ+0MMVIVwzPZV3j1TR1W1LoF4sSwjGEUVVzZyoaWH5zMCrLuqRNDqGvMxE3ioI33aE9QWnyUoeRY6Dcxf1Z9nMVBpaO9l9qt7pUIKeJQTjiE1HPF0Fr5keuAkB4PpZ4zh8uomTNc1OhzLsGlo62V5Uw8pZaY5Mde2vq3KSiXIJG63a6KJZQjCO2HysmikpowKyodJXT8+atwrC78vmnSOVdLmV6wO0/aBHXGwUi7KSeOewjUe4WJYQzLBr6+xmR3ENV08LzMZkXxMTR5KbHh+W3U/XH6gkNS6GeUEwedzV01I4duYs5fWtTocS1CwhmGH34fFa2rvcLA2ChACe+ffzT9ZR1dTudCjDpq2zm83Hqliem0ZEgI0R6ctV05IB2HKs2uFIgpslBDPs3jtaRXRkBJdnJTkdil+unzUOVcKqjnp7cQ0tHd2sCMDBaH2ZnhZHalyMjUe4SJYQzLDbfLSKhZmJjIh2OR2KX2aMi2NCwgg2hNGcORsPVTIy2sUVU4IjaYsIV+WksLWw2uafugh+JQQRWSUiR0SkUES+1cf+pSKyW0S6ROSOXvu6RWSv97XGZ3uWiOwQkWMi8qJ3eU4T4srrWzl25ixLvUX8YCAiLJ+ZypbCKto6u50OZ8ipKhsOnuGqnGRio4IjaQMsnZZMfUsn+8sanA4laPWbEETEBTwO3ADkAveKSG6vw04B9wPP93GJVlWd533d6rP9+8BjqpoD1AEPXED8Jsi87y3SXz0tsLub9rZsZhptnW62FoZ+HXVBeSOnG9tYHkBTkvvjyuxkROD9o1ZtdKH8KSEsBApVtVhVO4AXgNW+B6jqCVXdB/g1VFA8nZqvA172bnoWuM3vqE3Q2ny0mnHxsUxLC9yBTn1ZNCWR0TGRYVFttOFQJSL/b3rpYJE0OoZLxo9hs7UjXDB/EsIEoMTncyl9rJF8HrEiki8iH4hIz5d+ElCvql0XeE0ThLq63bx/rIqrcpIDeqBTX2IiXSydlszGQ5Uhv7TmhkOVXDppLMmjY5wOZcCuyklm96l6mtps9tML4U9C6Otf7kD+RUxS1Tzgc8APRWTqQK4pIg96E0p+VZVl/mD2UWkDjW1dQdPdtLflM9M409TOgfLQraOuaGjlQFlj0FUX9Vg6LYVut7KtqMbpUIKSPwmhFJjo8zkD8HttQVUt9/5ZDGwC5gPVQIKI9Mxqds5rqupTqpqnqnkpKcH5RWI8thZWI+Kp6w1G1073THa3IYQnu+upEgvkOabO59JJYxkV7fq4rcoMjD8JYSeQ4+0VFA3cA6zp5xwARGSsiMR43ycDS4CD6plg/l2gp0fSfcBrAw3eBJcthdXMGh/P2FHB2aFs7Kho8iYnhnQ7wsZDlUxOGkl2AE9mdz7RkRFcMTWJzUdDv/F/KPSbELz1/A8B64FDwEuqWiAij4rIrQAicpmIlAJ3Ak+KSIH39JlAvoh8hCcBfE9VD3r3/QPwsIgU4mlTeHowH8wElpaOLvacqmPJ1OAsHfRYNjOVgxWNlIXgFAnN7V1sK6xh2YzAnsyuP0uykzlV20JJbYvToQQdvyaiV9W1wNpe2x7xeb8TT7VP7/O2AbPPcc1iPD2YTBjYeaKOzm5lSZBWF/VYNjON/1x3mI2HKvnSFZlOhzOo3j9WTUe3m+UBuILdQPT8P7atqJq7Eyc5HE1wsZHKZlhsLawm2hXBZZmJTodyUaamjCIreVRIVhttPFRJXGxk0P8d5aSOJiUuhq2F1rA8UJYQzLDYWljNpZMTgma6inMREZbNSOWDohrOtnf1f0KQcLuVd4+c4ZrpqUS5gvtrQURYPDWJbUU1Yb8e9kAF99+8CQq1zR0UlDcGfftBj2Uz0+jodrMlhHqy7C2tp/psR9D2LuptydRkqs+2c7TyrNOhBBVLCGbIbff2CV+SExoJIS9zLPGxkbx9MHSqjTYcrPSsTxxkU4qcy+Jsz6R84TDVyGCyhGCG3JbCauJiIpkzYYzToQyKKFeEd2H3MyEzs+bGQ2e4LHMsY0ZGOR3KoMgYO5LMpJFsK7KEMBCWEMyQ21ZUzaIpSUQGed20r+W5adQ2d7C3pM7pUC5aSW0LRyqbgnZ08rkszk5mR3EtXd1+TbFmsIRghlhJbQsna1pYkh0c8+r76+ppKURGSEj0NupZ+GdZiCWEJVOTaWrvYp9Nh+03SwhmSPUU2YN9/EFvY0ZEcVlmYkhMY7Hx8BmmeLvThpIrpnp+hGyzdgS/WUIwQ2p7UQ3Jo2PICdKpEM5n2cxUjp05y6ma4B0R29jWyQfFNawIsdIBQOKoaHLT4208wgBYQjBDRtUz6+TiqUlBPRXCufSsN/x2EK+1/N6RKjq7NWjWTh6oJdlJ7DpZFxYr3Q0GSwhmyBRVNXOmqf3jonuomZw0imlpo3n74GmnQ7lgbx2sJGlUNPMnjXU6lCGxeGoyHd1udp8M/sb/4WAJwQyZ7cWeovriEE0I4Ckl7DxRR11zh9OhDFhHl5tNh8+wbGYqrojQK8EBXJaViCtCbH0EP1lCMENme1E148fEMilxpNOhDJmVuePodivvHA6+3kY7jtfQ1N7FitxxTocyZEbHRDInY8zHP07M+VlCMEPC7VY+KK7liqnBt1zmQMyeMIa0+BjeCsJqo7cPVhIbFRG0Cxb564opSXxUUk9zCM09NVQsIZghcaSyidrmjpCuLgKIiBBW5Kax+Wh1UDVcqiobDlZyVU5K0E842J8rpibR5VZ2nqh1OpSAZwnBDImeOttQbVD2tTJ3HK2d3Ww5Fjz93QvKGylvaAvZ3kW+8iYnEuWSj+fUMufmV0IQkVUickRECkXkW33sXyoiu0WkS0Tu8Nk+T0S2i0iBiOwTkbt99v1KRI6LyF7va97gPJIJBNuLashMGsn4hBFOhzLkLp+SRFxMJG8H0SC1tw5WEiGwbEZoTGZ3PiOiXcyfONbaEfzQb0IQERfwOHADkAvcKyK5vQ47BdwPPN9rewvwJVWdBawCfigiCT77v6mq87yvvRf4DCbAdHW72VFcExalA/Cs43vNjFQ2HKoMmsnu3j5YyYLJY0kaHeN0KMPi8qlJHChroKG10+lQApo/JYSFQKGqFqtqB/ACsNr3AFU9oar7AHev7UdV9Zj3fTlwBkgZlMhNwCoob6SpvYsrQmT9A3+syE2jprmD3acCv7/7yZpmDlU0sjKEexf1tnhqEm6FD49bO8L5+JMQJgAlPp9LvdsGREQWAtFAkc/m//BWJT0mIn3+VBGRB0UkX0Tyq6pCZ0GSUNZTNL98SnAvxTgQ10xPIcolrD8Q+L2N1nljXHVJ+CSE+ZMSiImMsOmw++FPQuirz+CAysUikg78BvgzVe0pRXwbmAFcBiQC/9DXuar6lKrmqWpeSooVLoLBtqIaclJHkxoX63QowyY+Noors5NZd+B0wC/buO7AaeZkjGFiCI8P6S0m0sWCyWOtYbkf/iSEUmCiz+cMoNzfG4hIPPAG8M+q+kHPdlWtUI924Jd4qqZMkOvsdpN/ojZs2g983Tg7nbL6Vj4qDdzplkvrWviopJ4bLkl3OpRht3hqEodPN1Fztt3pUAKWPwlhJ5AjIlkiEg3cA6zx5+Le418Bfq2qv++1L937pwC3AQcGErgJTPtK62np6OaKKeGXEFbmjiPKJazdX+F0KOf0pre66IYwqi7q0fMjZYe1I5xTvwlBVbuAh4D1wCHgJVUtEJFHReRWABG5TERKgTuBJ0WkwHv6XcBS4P4+upc+JyL7gf1AMvDvg/pkxhE9RfJFYZgQxoyMYkl2Mm/sqwjYaqN1B06Tmx5PZoitfeCPORkJjIx2WbXReUT6c5CqrgXW9tr2iM/7nXiqknqf91vgt+e45nUDitQEhe3FNcwYF0fiqGinQ3HEjbPT+fsj+9hX2sDciQn9nzCMTje0setkHd9YOc3pUBwR5YrgssxEG49wHjZS2Qya9q5u8k/UhWX7QY+VuWlERgRmtdGbBzwx3TA7/NoPelwxNYnCM2c509jmdCgByRKCGTR7TtXT3uVmcRiNP+gtYWS0p9pof+BVG609cJrpaXFMTQm91ev81dO2ZaWEvllCMINme1ENEQILs8Jn/EFfbpqdTmldKwfKGp0O5WOnG9rYeaKWG2aHX2Oyr1nj44mLjeQDSwh9soRgBs324hpmjR/DmBFRTofiqJWzPNVGr+/zu3f2kFvzURmqsHregMeUhpRIVwSLshKtYfkcLCGYQdHW2c3eU/Vh3X7QI2FkNFdPS+G1veUBM7fRH3eXMW9iAllh2Luot8unJHGipoXy+lanQwk4lhDMoNh1so6ObndYjj/oy2cvzeB0Y1tA/BI9VNHI4dNNfPbS8C4d9Oj50RIIfzeBxhKCGRTbiqpxRQiXhXn7QY9lM1OJj43kD7tLnQ6FV/eWERkh3BTGvYt8zRwXT8LIKGtY7oMlBDMothfVMCdjDKNj/BraEvJio1zcPHc8bx44zVkHl27sdiuv7Snn6mkpYTPVdX8iIoTLs5KshNAHSwjmop1t7+Kj0oaQXy5zoG6/dAKtnd0fTxfhhB3FNZxubOMzVl30CYuzkyirb+VUTYvToQQUSwjmou08Xku3W8N6/EFfLp00lslJI/nDLueqjf64p4y4mEiWzwz9pTIHoufHy/Zimw7blyUEc9G2FVUTHRnBgsljnQ4loIgIn52fwfbiGkrrhv+XaGuHp3Ryw+xxxEa5hv3+gWxqymhS4mLYWmjVRr4sIZiLtrWwhgWTxtqXTh96eva8uqds2O/92t4yzrZ3cceCif0fHGZEhMVTk9hWVBNwI8qdZAnBXJS65g4OVjRa+8E5TEwcyeVTEvndhyXDOiZBVfn19pNMT4vjskwrufVl8dQkqs+2U3jmrNOhBAxLCOai9EwBsDjbEsK53L84k7L6VjYcqhy2e+4+Vc/Bika+eMVkPEuOmN562ry2WW+jj1lCMBdlW1ENI6NdzMkIrKmeA8nymWmMHxPLs9tODNs9f7P9BHExkXxmvvUuOpeJiSOZmDiCrYXWsNzDr4QgIqtE5IiIFIrIt/rYv1REdotIl4jc0WvffSJyzPu6z2f7AhHZ773mj8V+xgSlbUXVLMxKJMplvy3OJdIVwRevyGRbUQ1HTjcN+f2qz7azdv9pbl+QwSgbF3Jei6ck80FxTcBMMeK0fv8Vi4gLeBy4AcgF7hWR3F6HnQLuB57vdW4i8F1gEZ41k78rIj0Vmk8ADwI53teqC34K44jKxjaKqpqt/cAP91w2kZjICH41DKWEF3eW0NHt5guXTx7yewW7xdlJNLZ1cbA8cGamdZI/P+sWAoWqWqyqHcALwGrfA1T1hKruA9y9zr0eeFtVa1W1DngbWOVdTzleVberp4n/13jWVTZBpGekp40/6N/YUdHcNm8Cr+wppaGlc8ju09Xt5rkPTrJ4ahLZqeG77oG/euY12lZk1UbgX0KYAJT4fC71bvPHuc6d4H1/Idc0AWJrYTXxsZHMTI93OpSgcN/iTNo63byYf2rI7vH6vgrKG9r40hWZQ3aPUJIaF0tO6mi2WsMy4F9C6Ktu398Kt3Od6/c1ReRBEckXkfyqqio/b2uGmqqytbCaxVOTcUVY848/csfHsygrkV+8f5zWju5Bv35Xt5sfbTzGjHFxrMy1kcn+Wjw1iZ3Ha+no6l3BEX78SQilgO/IlgzA35U/znVuqfd9v9dU1adUNU9V81JSUvy8rRlqx6ubKW9oY0mOVRcNxNdXTudMUzvPbj8x6Nf+454yjlc38/CKaURYkvbb4uxkWju72XOqzulQHOdPQtgJ5IhIlohEA/cAa/y8/npgpYiM9TYmrwTWq2oF0CQil3t7F30JeO0C4jcO6emqd1W2JYSBWJiVyLXTU/jfdwsHtS2ho8vNjzceY07GGFZY6WBALp+SRIRg3U/xIyGoahfwEJ4v90PAS6paICKPisitACJymYiUAncCT4pIgffcWuDf8CSVncCj3m0AXwZ+ARQCRcC6QX0yM6S2FFYzIWEEk5NGOh1K0Pnm9TNobOviyc1Fg3bN3+8qobSula+tmGYD0QZozIgo5k5M4H1LCPjVSVlV1wJre217xOf9Tj5ZBeR73DPAM31szwcuGUiwJjB0u5VtRTXceEm6fflcgNwO3Ir+AAAYzUlEQVTx8ayeN55nth7n/sWZpMbHXtT12ru6+ek7hcyflMA106xa9UJcmZ3M4+8W0tjWSXxs+K4JbqOJzIDtL2ugqa3L2g8uwsMrptHVrTy24dhFX+vHG49R0dDGN1ZOtwR9ga7MTsattqymJQQzYD11rUtsQNoFm5w0ii9dkcnvPjzFe0cvvPfcrpN1PLGpiDsXZLDE2nMu2PxJYxkZ7WLLsfCuNrKEYAbs/WNV5KbH25KMF+nvV01nelocX39pL1VN7QM+v6Wji6+/tJf0MSN45JbekweYgYiOjGBRVmLYNyxbQjAD0tLRxe6T9Vxp1UUXLTbKxU8+N5+mti4efmkv7gHOp/Ofaw9zsraF/75rLnFhXO89WK7MSaG4upmy+lanQ3GMJQQzIDtP1NHR7eZKq54YFNPS4njkllzeP1bNk5uL/T7v9/kl/OaDkzywJIvLp1jV3WC4yvsjZ8ux8B0AawnBDMjWwmqiXRFclpnodCgh43MLJ3Hj7HF8/83D/GD9kfOWFFSVn71XxDdf3seS7CS+cf30YYw0tOWkjiY1LoYtYbysps2NawZk89EqFkwey4hoWy5zsIgIj909j9ExB/jpu4UcqWzyfv7kP89ut/Kfaw/xiy3HuXlOOv9911xiIu3vYbCICFdmJ7PpaBVut4blaG9LCMZvlY1tHD7dxLdumOF0KCEnJtLF92+fw4xx8fz7Gwe5/rHNXD09hcunJJE0Kpr1BadZd+A0VU3t3L84k0duzg3LL6yhdmVOMn/cU8bBikYumTDG6XCGnSUE47fN3u6RV9vgpyEhIvyfK7OYPi6On79fzJq95Ty/wzMzakxkBNfNSGX1vAlcPyvNxhsMkZ7OEpuPVVlCMOZ83jtaRWpcDDPGxTkdSkhbkp3MkuxkurrdFJQ3cqapncVTk2z1s2GQGhdLbno87x2p4q+vyXY6nGFn/4cZv3S7lfePVbMi136dDpdIVwRzJ9pa1cPtmukpPLW5mKa2zrDrzmu9jIxf9pXW09DayVKrLjIh7uppKXS5la1h2NvIEoLxy3tHqxCx6a5N6Lt08lhGx0Re1JQiwcoSgvHL5qNVzMlIYOyoaKdDMWZIRbkiWJKdxOajVXiWfA8flhBMv+pbOthbUm+9i0zYuHpaKmX1rRSeOet0KMPKEoLp15bCatxq3U1N+Lh6uuf/9XCrNvIrIYjIKhE5IiKFIvKtPvbHiMiL3v07RCTTu/3zIrLX5+UWkXnefZu81+zZlzqYD2YGz+ajVcTHRjI3I/z6ZZvwNCFhBDmpoy0h9CYiLuBx4AYgF7hXRHrPtfsAUKeq2cBjwPcBVPU5VZ2nqvOALwInVHWvz3mf79mvqmcG4XnMIHO7lXePVHFVTgqRLitQmvBx9bQUdhTX0tLR5XQow8aff+ELgUJVLVbVDuAFYHWvY1YDz3rfvwwsk093Vr8X+N3FBGuG34HyBqqa2lk20wpwJrxcPT2Fjm53WK2i5k9CmACU+Hwu9W7r8xhV7QIagN5z8t7NpxPCL73VRd/pI4GYALDh0BkiBK6ZbgnBhJeFWYmMinax8XD4VF74kxD6+qLu3RfrvMeIyCKgRVUP+Oz/vKrOBq7yvr7Y581FHhSRfBHJr6oKr/q8QPDO4UounTSWROtuasJMTKSLq3JS2HioMmy6n/qTEEqBiT6fM4Dycx0jIpHAGKDWZ/899CodqGqZ988m4Hk8VVOfoqpPqWqequalpFgvl+F0uqGNA2WNXGfVRSZMLc9No7KxnQNljU6HMiz8SQg7gRwRyRKRaDxf7mt6HbMGuM/7/g7gHfWmVBGJAO7E0/aAd1ukiCR730cBNwMHMAHlHW9RefnMNIcjMcYZ105PQQQ2HKp0OpRh0W9C8LYJPASsBw4BL6lqgYg8KiK3eg97GkgSkULgYcC3a+pSoFRVfdcHjAHWi8g+YC9QBvz8op/GDKqNhyqZmOjpfmdMOEoaHcOlk8ay8XB4JAS/ZjtV1bXA2l7bHvF534anFNDXuZuAy3ttawYWDDBWM4xaO7rZUljNvQsn2eymJqwtn5nG9988TEVDK+ljRjgdzpCyjuWmT9uLq2nvclt3UxP2lnv/DWw8FPq9jSwhmD5tOHSGUdEuFmYlOh2KMY7KTh3N5KSRbAyDdgRLCOZT3G5l46FKlk5LsUXcTdgTEZbNSGNrUU3Ij1q2hGA+ZU9JPZWN7Vw/a5zToRgTEJbPTKWjy83mo9VOhzKkLCGYT3nzQAVRLrHxB8Z4XZaVyJgRUbxVcNrpUIaUJQTzCarKugOnuTI7mfgwW0/WmHOJckWwMjeNtw9V0t7V7XQ4Q8YSgvmEgvJGSutaueGSdKdDMSag3Dg7naa2LraF8FrLlhDMJ6w7UIErQliea6OTjfG1ODuJuNhI1u6vcDqUIWMJwXysp7poUVaiTWZnTC8xkS5WzEzjrYOVdHa7nQ5nSFhCMB87duYsxVXN3HCJ9S4ypi83zE6nobUzZNdIsIRgPrZu/2lEsO6mxpzDVTnJjIp2se5AaFYbWUIwH1t3oIIFk8aSGh/rdCjGBKTYKBfLZqaxvqCSrhCsNrKEYAA4VtnE4dNN3DjbehcZcz43zh5HbXMHHx6v7f/gIGMJwQDw6t4yIgRunmsJwZjzuXpaKiOjXfxpX+91woKfJQSDqvLa3nKWZCeTGmfVRcacz4hoF9fPGsfr+ypo6wytQWqWEAy7TtZRWtfKbfMmOB2KMUHhM/Mn0NTWxbuHQ2tKbL8SgoisEpEjIlIoIt/qY3+MiLzo3b9DRDK92zNFpFVE9npfP/M5Z4GI7Pee82OxVVgc8+reMmKjIrjeupsa45fFU5NIiYvhlT1lTocyqPpNCCLiAh4HbgBygXtFJLfXYQ8AdaqaDTwGfN9nX5GqzvO+/spn+xPAg0CO97Xqwh/DXKiOLjdv7Ktg+cw0Rsf4tYCeMWEv0hXB6rnjeffIGeqaO5wOZ9D4U0JYCBSqarGqdgAvAKt7HbMaeNb7/mVg2fl+8YtIOhCvqttVVYFfA7cNOHpz0TYfraKupdOqi4wZoNvmT6CzW3kjhKay8CchTABKfD6Xerf1eYyqdgENQJJ3X5aI7BGR90TkKp/jS/u5phkGr+4tY+zIKJZOS3E6FGOCyqzx8UxLGx1S1Ub+JIS+fumrn8dUAJNUdT7wMPC8iMT7eU3PhUUeFJF8EcmvqqryI1zjr8a2TjYcquSmOelER1r/AmMGQkS4bf4Edp2s42RNs9PhDAp/vgVKgYk+nzOA3h1wPz5GRCKBMUCtqrarag2Aqu4CioBp3uMz+rkm3vOeUtU8Vc1LSbFfsYPptT1ltHW6uStvYv8HG2M+paeq9Y+7Q6OU4E9C2AnkiEiWiEQD9wBreh2zBrjP+/4O4B1VVRFJ8TZKIyJT8DQeF6tqBdAkIpd72xq+BLw2CM9j/KSqPP9hCbnp8cyeMMbpcIwJSuMTRnBVTjK/zy+h291nJUdQ6TcheNsEHgLWA4eAl1S1QEQeFZFbvYc9DSSJSCGeqqGerqlLgX0i8hGexua/UtWe8d5fBn4BFOIpOawbpGcyfthX2sChikbuXTQJ6/FrzIX73MJJlDe0selI8I9J8KufoaquBdb22vaIz/s24M4+zvsD8IdzXDMfuGQgwZrB87sPTzEiysXqeeOdDsWYoLY8N42UuBie23GKZTODe2Epa0kMQ2fbu1jzUTk3z0m3dZONuUhRrgjuzpvIpiNnKKtvdTqci2IJIQyt2VtOS0c39y6a5HQoxoSEexZORIEXPzzldCgXxRJCGHph5ymmp8Uxf2KC06EYExIyxo7kmmkpvLCzJKiX17SEEGb2nKpjX2kD9y6caI3Jxgyizy2azJmmdjYeCt7GZUsIYeYX7x8nLjaSO2zsgTGD6trpKYwfE8uz2044HcoFs4QQRkpqW1h3oILPLZpkE9kZM8giXRHcvyST7cU17C9tcDqcC2IJIYz8cusJIkS4f3Gm06EYE5LuXTiJuJhIntxc5HQoF8QSQphoaO3kxZ2nuGXueNLHjHA6HGNCUlxsFJ9bNIm1+ysoqW1xOpwBs4QQJl748BTNHd08cGWW06EYE9L+bEkWrgjh6S3HnQ5lwCwhhIHObje/2naCK6YkcYnNW2TMkBo3JpZb507gxZ0lQbd4jiWEMPDyrlIqGtp48OopTodiTFh4cOkUWju7+c0HJ50OZUAsIYS49q5ufrLxGPMnJXCNLYJjzLCYPi6OZTNSeXrLcRpaO50Ox2+WEELcCx+WUN7QxtdXTLeBaMYMo6+tmEZDayc/31zsdCh+s4QQwlo7uvnpu4UsykpkSXZS/ycYYwbNJRPGcPOcdJ7Zepyqpnanw/GLJYQQ9tsPTlLV1M7XV1rpwBgnPLxiGu1dbv53U6HTofjFEkKIOtvexRPvFXFVTjILsxKdDseYsDQlZTR3LsjguQ9OUVoX+OMS/EoIIrJKRI6ISKGIfKuP/TEi8qJ3/w4RyfRuXyEiu0Rkv/fP63zO2eS95l7vK3WwHsrAT945Rm1zB19fOd3pUIwJa19dlgMCP9xwzOlQ+tVvQvCuifw4cAOQC9wrIrm9DnsAqFPVbOAx4Pve7dXALao6G8+ay7/pdd7nVXWe9xW8UwQGmMIzZ3n6/ePcuSCDeTbFtTGOGp8wgj9bnMnLu0rZdbLO6XDOy58SwkKgUFWLVbUDeAFY3euY1cCz3vcvA8tERFR1j6qWe7cXALEiEjMYgZu+qSr/sqaAEdEu/uGGGU6HY4zBU0oYFx/LP796gK4AXi/Bn4QwASjx+Vzq3dbnMaraBTQAvbu13A7sUVXf5vZfequLviPnaPUUkQdFJF9E8quqqvwIN7y9eeA0Wwqr+fqKaSSPttxrTCAYFRPJd2/J5VBFI7/eHriD1fxJCH19UetAjhGRWXiqkf7SZ//nvVVJV3lfX+zr5qr6lKrmqWpeSooNrDqf1o5u/u31g8wYF8cXLp/sdDjGGB+rLhnHNdNT+J+3j1LZ2OZ0OH3yJyGUAr6rqWQA5ec6RkQigTFArfdzBvAK8CVV/XhOWFUt8/7ZBDyPp2rKXITvrTtEeUMb/3bbJUS6rAOZMYFERPjXW2fR0e3mX/9U4HQ4ffLnW2MnkCMiWSISDdwDrOl1zBo8jcYAdwDvqKqKSALwBvBtVd3ac7CIRIpIsvd9FHAzcODiHiW8bTpyhme3n+SBK7O4LNO6mRoTiCYnjeJvl+Wwdv9pXtlT6nQ4n9JvQvC2CTwErAcOAS+paoGIPCoit3oPexpIEpFC4GGgp2vqQ0A28J1e3UtjgPUisg/YC5QBPx/MBwsntc0dfPPlfUxPi+Ob11s3U2MC2V9dPZWFmYl859UCTtY0Ox3OJ4hq7+aAwJWXl6f5+flOhxFQVJW//M0uNh2p4rWHljAzPd7pkIwx/Sirb+WGH25mSspofv9XVxA1xFW8IrJLVfP6O84qmoPcbz44yVsHK/nG9dMsGRgTJCYkjOB7t89hb0k9P9xw1OlwPmYJIYhtOVbNv/7pIMtmpPLnV9paB8YEkxtnp3N33kQef7eIN/ZVOB0OYAkhaBVXneWvn9tFdspofnTvfCIibPI6Y4LNv66eRd7ksXztpb3sPuX8KGZLCEGooaWTP382n0hXBL+4L4/RMZFOh2SMuQCxUS6e+lIe6WNi+Ytn8ympdXYCPEsIQaahtZMvPbODkroWnvziAiYmjnQ6JGPMRUgcFc0z919Gl1u5/5cfcqbJuUFrlhCCSENLJ198egcHKxp54vMLbLyBMSFiaspofv6lPMrr27jnyQ+oaGh1JA5LCEGioaWTLzy9g8MVTfzsCwtYnpvmdEjGmEG0MCuR3zywkDNN7dz15HZHqo8sIQSBoqqzfOZ/t3LkdBM/++KlLJtpycCYUJSXmchv/3wRDS2d3PXkdg6UNQzr/S0hBLh3j5zhtse3Ut/ayW8eWMh1MywZGBPK5k1M4IUHrwDg9ie28YddwzfFhSWEANXZ7eZHG47xwK92kjF2JGseWsKiKb1nFDfGhKLc8fH86StXMn9SAl///Ud897UDdA7DOgqWEAJQQXkDq3+6lcc2HOXWueP5w5evIGOs9SYyJpwkj47htw8s4s+vzOK5Hac4XNE05Pe0DuwBpKGlk/99r5Cn3z9OwshofvaFBay6ZJzTYRljHBLpiuCfb87lC5dPJjN51NDfb8jvYPrV2tHNL7cd52ebimhq7+Kz8zP4zs0zSRgZ7XRoxpgAMBzJACwhOKqktoXffnCSF/NLqG/pZNmMVL5x/XSbpM4Y4whLCMOstrmDtw+e5vV9FWwprCZChJW5aTxwZRZ5NtDMGOMgvxKCiKwCfgS4gF+o6vd67Y8Bfg0sAGqAu1X1hHfft4EHgG7gq6q63p9rhoqOLjcfldazvaiGbUXV7DxRR7dbmZQ4kq9cm829iyaRPmaE02EaY0z/CUFEXMDjwAo8ayfvFJE1qnrQ57AHgDpVzRaRe4DvA3eLSC6eJTdnAeOBDSIyzXtOf9cMKm63UtHYxonqZoqrznKwoomC8gYOn26io8uNCMwcF89fLp3CjbPTmTU+HhGbodQYEzj8KSEsBApVtRhARF4AVgO+X96rgX/xvn8Z+Kl4vu1WAy+oajtw3LvE5kLvcf1dc9ipKl1upb3LTVtnN60d3bR0dNPc0UVTWxdNbZ00tnZR19JBzdkOaprbOd3QxunGNioa2ujo+n/9hMeMiOKSCfHcvziTSyeN5fIpidZIbIwJaP4khAlAic/nUmDRuY5R1S4RaQCSvNs/6HXuBO/7/q45aP7xlf3sKK7BrdDt1o9fXW6ly+2mq1vp6HbT2e3G3xVFR0W7SBwdTXr8COZmJLBqViyTkkaSlTyKrORRjIuPtRKAMSao+JMQ+vpW6/21ea5jzrW9rwFxfX4Vi8iDwIMAkyZNOneU5zEhYQQz0uOJEMElEBEhREVE4HIJLhGiXBFERQrRrghiIiOIiXQRHRnBiGgXo6IjGRntIi42krjYKOJHRDJ2ZDSxUa4LisUYYwKVPwmhFJjo8zkDKD/HMaUiEgmMAWr7Obe/awKgqk8BTwHk5eX5+fv9k/7m2uwLOc0YY8KKP1NX7ARyRCRLRKLxNBKv6XXMGuA+7/s7gHdUVb3b7xGRGBHJAnKAD/28pjHGmGHUbwnB2ybwELAeTxfRZ1S1QEQeBfJVdQ3wNPAbb6NxLZ4veLzHvYSnsbgL+BtV7Qbo65qD/3jGGGP8JepvK2oAyMvL0/z8fKfDMMaYoCIiu1Q1r7/jbLZTY4wxgCUEY4wxXpYQjDHGAJYQjDHGeFlCMMYYAwRZLyMRqQJOXuDpyUD1IIYTDOyZw4M9c+i72OedrKop/R0UVAnhYohIvj/drkKJPXN4sGcOfcP1vFZlZIwxBrCEYIwxxiucEsJTTgfgAHvm8GDPHPqG5XnDpg3BGGPM+YVTCcEYY8x5hEVCEJFVInJERApF5FtOxzOURGSiiLwrIodEpEBE/tbpmIaLiLhEZI+IvO50LMNBRBJE5GUROez9+77C6ZiGmoh8zfv/9QER+Z2IxDod02ATkWdE5IyIHPDZligib4vIMe+fY4fi3iGfEETEBTwO3ADkAveKSK6zUQ2pLuDrqjoTuBz4mxB/Xl9/CxxyOohh9CPgTVWdAcwlxJ9dRCYAXwXyVPUSPFPn3+NsVEPiV8CqXtu+BWxU1Rxgo/fzoAv5hAAsBApVtVhVO4AXgNUOxzRkVLVCVXd73zfh+ZKYcP6zgp+IZAA3Ab9wOpbhICLxwFI8a5Ggqh2qWu9sVMMiEhjhXZlxJOdYaTGYqepmPOvK+FoNPOt9/yxw21DcOxwSwgSgxOdzKWHwBQkgIpnAfGCHs5EMix8Cfw+4nQ5kmEwBqoBfeqvJfiEio5wOaiipahnwA+AUUAE0qOpbzkY1bNJUtQI8P/qA1KG4STgkBOljW8h3rRKR0cAfgL9T1Uan4xlKInIzcEZVdzkdyzCKBC4FnlDV+UAzQ1SNECi89eargSxgPDBKRL7gbFShJRwSQikw0edzBiFYzPQlIlF4ksFzqvpHp+MZBkuAW0XkBJ4qwetE5LfOhjTkSoFSVe0p/b2MJ0GEsuXAcVWtUtVO4I/AYodjGi6VIpIO4P3zzFDcJBwSwk4gR0SyRCQaTyPUGodjGjIiInjqlQ+p6v84Hc9wUNVvq2qGqmbi+ft9R1VD+pejqp4GSkRkunfTMjxrl4eyU8DlIjLS+//5MkK8Id3HGuA+7/v7gNeG4iaRQ3HRQKKqXSLyELAeT6+EZ1S1wOGwhtIS4IvAfhHZ6932j6q61sGYzND4CvCc94dOMfBnDsczpFR1h4i8DOzG05tuDyE4YllEfgdcAySLSCnwXeB7wEsi8gCexHjnkNzbRiobY4yB8KgyMsYY4wdLCMYYYwBLCMYYY7wsIRhjjAEsIRhjjPGyhGCMMQawhGCMMcbLEoIxxhgA/n9z3lfJ680HjwAAAABJRU5ErkJggg==\n",
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x1a183952b0>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "n1 = scipy.stats.norm(7.5,1)\n",
+    "n2 = scipy.stats.norm(4,1)\n",
+    "\n",
+    "x = np.linspace(0,10,100)\n",
+    "pp.plot(x,0.5*n1.pdf(x) + 0.5*n2.pdf(x))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def draw():\n",
+    "    while True:\n",
+    "        v = n1.rvs() if np.random.rand() < 0.5 else n2.rvs()\n",
+    "        if 0 <= v <= 10:\n",
+    "            return v"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "7.13196783815238"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "draw()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def dataset(n=100):\n",
+    "    return pd.DataFrame({'grade': [draw() for i in range(n)]})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x1a17b9a940>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "for i in range(5):\n",
+    "    dataset(100).grade.hist(histtype='step',density=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "means = pd.DataFrame({'meangrade': [dataset(100).grade.mean() for i in range(1000)]})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<matplotlib.axes._subplots.AxesSubplot at 0x1a17ea1898>"
+      ]
+     },
+     "execution_count": 19,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x1a17ea1278>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "means.meangrade.hist(histtype='step')\n",
+    "bootstrap.meangrade.hist(histtype='step')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.4"
+  },
+  "toc": {
+   "base_numbering": 1,
+   "nav_menu": {},
+   "number_sections": true,
+   "sideBar": true,
+   "skip_h1_title": false,
+   "title_cell": "Table of Contents",
+   "title_sidebar": "Contents",
+   "toc_cell": false,
+   "toc_position": {},
+   "toc_section_display": true,
+   "toc_window_display": false
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/cholera.xls b/cholera.xls
new file mode 100644
index 0000000..78e8300
--- /dev/null
+++ b/cholera.xls
@@ -0,0 +1,251 @@
+deaths,lat,lon,x,y,closest
+3,51.513418,-0.13793,-0.08730123377777677,0.008559124508608074,0
+2,51.513361,-0.137883,-0.08404991999999961,0.0022231492235895156,0
+1,51.513317,-0.137853,-0.08197461333333278,-0.002667779067043685,0
+1,51.513262,-0.137812,-0.07913836088888743,-0.008781439430335158,0
+4,51.513204,-0.137767,-0.07602540088888815,-0.015228572176217314,0
+2,51.513184,-0.137537,-0.060114716444443106,-0.01745172139901696,0
+2,51.513359,-0.1382,-0.10597899377777625,0.0020008343010725627,0
+2,51.513328,-0.138045,-0.09525657599999926,-0.0014450469943853572,0
+3,51.513323,-0.138276,-0.11123643733333322,-0.0020008343002828055,1
+2,51.513427,-0.138223,-0.10757006222222226,0.009559541658749449,1
+2,51.513381,-0.138337,-0.1154562275555539,0.004446298446389163,1
+1,51.513462,-0.138563,-0.13109020444444308,0.013450052798451462,1
+3,51.513216,-0.138426,-0.12161297066666538,-0.013894682642695444,1
+1,51.513169,-0.138378,-0.11829247999999926,-0.01911908331670914,1
+4,51.513116,-0.138337,-0.1154562275555539,-0.025010428757483716,0
+1,51.51324,-0.138645,-0.13676270933333187,-0.011226903574861946,1
+1,51.513164,-0.138698,-0.1404290844444428,-0.019674870621816665,1
+1,51.513178,-0.137924,-0.08688617244444302,-0.018118666165777897,0
+4,51.513111,-0.137865,-0.08280473599999832,-0.02556621606259124,0
+3,51.513055,-0.137811,-0.0790691839999984,-0.031791033886746256,0
+2,51.513441,-0.138762,-0.14485640533333227,0.011115746114788216,1
+1,51.513592,-0.138799,-0.14741595022222181,0.027900522747834056,1
+2,51.513402,-0.139045,-0.16443346488888821,0.006780605130052408,1
+2,51.51338,-0.13897,-0.1592451982222221,0.0043351409847358635,1
+2,51.513411,-0.138863,-0.15184327111110935,0.007781022280193783,1
+1,51.513641,-0.138752,-0.1441646364444427,0.03334723834357489,1
+1,51.513693,-0.138808,-0.14803854222222054,0.03912742632348587,1
+3,51.513745,-0.138856,-0.15135903288888858,0.04490761430260709,1
+1,51.513676,-0.138887,-0.15350351644444435,0.03723774948327685,1
+1,51.51359,-0.139239,-0.17785378133333266,0.027678207825317214,1
+1,51.513663,-0.139321,-0.18352628622222145,0.03579270248889149,1
+1,51.513502,-0.139316,-0.18318040177777664,0.017896351244840625,1
+2,51.513583,-0.139616,-0.20393346844444296,0.026900105596902923,1
+2,51.513541,-0.139719,-0.21105868799999988,0.02223149222878662,1
+1,51.513298,-0.140074,-0.23561648355555503,-0.004779770828979846,1
+1,51.513291,-0.139094,-0.16782313244444333,-0.005557873056604323,1
+1,51.513013,-0.139697,-0.20953679644444279,-0.03645964725486256,1
+1,51.512965,-0.139327,-0.18394134755555516,-0.04179520538973974,1
+2,51.512893,-0.139317,-0.18324957866666564,-0.04979854259245048,1
+8,51.512964,-0.139187,-0.17425658311111067,-0.0419063628513931,1
+2,51.513025,-0.139036,-0.1638108728888876,-0.035125757721340745,1
+1,51.513027,-0.139209,-0.17577847466666582,-0.03490344279882379,1
+1,51.512831,-0.138427,-0.1216821475555544,-0.05669030518336643,0
+1,51.512885,-0.138624,-0.13530999466666568,-0.05068780228172831,1
+1,51.512526,-0.138096,-0.09878459733333228,-0.09059333083204885,0
+1,51.512465,-0.138035,-0.0945648071111097,-0.09737393596210125,7
+4,51.512428,-0.137984,-0.09103678577777669,-0.10148676202432017,7
+1,51.512415,-0.138065,-0.09664011377777654,-0.10293180901949539,7
+1,51.51251,-0.138194,-0.1055639324444444,-0.09237185021060451,7
+1,51.512378,-0.137818,-0.07955342222222112,-0.10704463508171425,7
+1,51.512447,-0.137656,-0.06834676622222147,-0.09937477026238406,0
+4,51.512491,-0.137584,-0.0633660302222222,-0.09448384197254062,0
+1,51.512374,-0.13765,-0.06793170488888772,-0.10748926492595828,7
+1,51.512339,-0.13745,-0.054096327111109566,-0.11137977606645005,0
+1,51.512364,-0.137376,-0.04897723733333237,-0.10860083953775301,0
+1,51.512319,-0.137327,-0.04558756977777728,-0.11360292528924976,0
+1,51.51254,-0.13698,-0.021583189333331865,-0.08903712637601008,0
+2,51.512649,-0.13718,-0.03541856711111008,-0.07692096311108049,0
+1,51.512692,-0.137052,-0.026563925333333016,-0.07214119228210064,0
+1,51.512957,-0.137695,-0.07104466488888889,-0.042684465079017575,0
+1,51.512765,-0.137533,-0.059838008888887295,-0.06402669761852636,0
+2,51.51278,-0.137419,-0.051951843555555655,-0.06235933570162405,0
+1,51.512726,-0.137368,-0.04842382222222075,-0.06836183860326217,0
+1,51.512681,-0.137325,-0.04544921599999935,-0.07336392435475897,0
+2,51.512914,-0.137531,-0.05969965511110936,-0.04746423590799742,0
+2,51.513046,-0.137562,-0.06184413866666516,-0.03279145103688769,0
+1,51.513074,-0.137466,-0.055203157333332864,-0.02967904212481015,0
+2,51.513087,-0.137386,-0.04966900622222198,-0.02823399513042474,0
+3,51.513122,-0.137306,-0.04413485511111109,-0.024343483989932968,0
+1,51.513187,-0.137089,-0.029123470222220615,-0.017118249015636522,0
+4,51.513214,-0.136996,-0.02269001955555522,-0.014116997565212397,0
+15,51.513249,-0.136859,-0.01321278577777757,-0.010226486424720571,0
+3,51.513271,-0.136778,-0.007609457777777717,-0.007781022279403971,0
+4,51.5133,-0.136705,-0.0025595448888875993,-0.004557455906462893,0
+5,51.51316,-0.136493,0.012105955555556158,-0.02011950046685046,0
+2,51.513016,-0.13633,0.02338178844444483,-0.036126174871482064,0
+1,51.512921,-0.136424,0.01687916088889041,-0.04668613368037294,0
+2,51.51289,-0.136523,0.010030648888889326,-0.05013201497583092,0
+1,51.512859,-0.136599,0.004773205333334252,-0.053577896271288894,0
+1,51.51283,-0.136699,-0.0021444835555538555,-0.05680146264422997,0
+1,51.512782,-0.136819,-0.010445710222221127,-0.062137020779107155,0
+1,51.512729,-0.136973,-0.021098951111111097,-0.06802836621988173,0
+1,51.512868,-0.136358,0.021444835555555875,-0.05257747912114752,0
+1,51.512723,-0.13663,0.0026287217777784533,-0.06869531098664267,0
+1,51.512654,-0.136584,0.005810858666666752,-0.07636517580597296,0
+1,51.512713,-0.136423,0.016948337777779376,-0.06980688559843745,0
+1,51.512615,-0.136345,0.02234413511111233,-0.08070031679070877,0
+1,51.512491,-0.136437,0.015979861333333956,-0.09448384197254062,0
+1,51.512449,-0.136377,0.02013047466666762,-0.09915245534065692,0
+1,51.512465,-0.136197,0.03258231466666667,-0.09737393596210125,0
+1,51.512413,-0.136142,0.03638704355555544,-0.10315412394122242,5
+2,51.512358,-0.136102,0.039154119111111885,-0.10926778430451395,5
+1,51.512271,-0.13603,0.04413485511111109,-0.118938483424127,5
+1,51.512355,-0.13631,0.024765326222223993,-0.10960125668789439,5
+4,51.511991,-0.13594,0.05036077511111159,-0.15006257254411232,5
+2,51.512083,-0.135858,0.05603328000000035,-0.13983608611939177,5
+1,51.512031,-0.1358,0.06004553955555614,-0.14561627409851297,5
+4,51.51197,-0.135717,0.06578722133333381,-0.15239687922856535,5
+4,51.511882,-0.135119,0.10715500088889052,-0.1621787358090419,5
+1,51.51205,-0.135144,0.1054255786666684,-0.1435042823365768,5
+4,51.51225,-0.135394,0.0881313564444462,-0.12127279010779018,5
+1,51.512162,-0.135409,0.08709370311111181,-0.13105464668905656,5
+1,51.512212,-0.135472,0.08273555911111125,-0.1254967736316625,5
+2,51.512573,-0.135765,0.06246673066666769,-0.08536893015803515,0
+1,51.512575,-0.135871,0.05513398044444584,-0.08514661523630812,0
+2,51.512672,-0.135976,0.04787040711111101,-0.07436434150490034,0
+3,51.512727,-0.136033,0.043927324444446136,-0.06825068114239868,0
+1,51.512794,-0.136115,0.03825481955555543,-0.06080313124558534,0
+4,51.512846,-0.13618,0.03375832177777888,-0.05502294326567431,0
+1,51.512879,-0.136083,0.04046848000000014,-0.05135474704848919,0
+1,51.512939,-0.136139,0.03659457422222234,-0.04468529937930038,0
+7,51.512765,-0.135329,0.0926278542222227,-0.06402669761852636,0
+3,51.512844,-0.135122,0.10694747022222356,-0.055245258188191204,0
+8,51.512532,-0.134645,0.13994484622222392,-0.08992638606528791,4
+1,51.512198,-0.134522,0.14845360355555615,-0.12705297808770122,4
+1,51.512215,-0.134967,0.11766988800000061,-0.125163301248282,4
+5,51.513154,-0.135098,0.10860771555555665,-0.02078644523361145,0
+8,51.513056,-0.134394,0.1573082453333332,-0.031679876425882714,4
+2,51.513165,-0.134505,0.14962961066666658,-0.019563713160953122,4
+1,51.513098,-0.134437,0.15433363911111186,-0.027011263057766466,4
+1,51.513238,-0.134594,0.143472867555557,-0.011449218497378844,4
+2,51.513293,-0.13464,0.14029073066666686,-0.005335558134877183,0
+1,51.513379,-0.134709,0.1355175253333345,0.004223983523872321,0
+2,51.513431,-0.134756,0.1322662115555573,0.01000417150299343,0
+2,51.513475,-0.135244,0.09850788977777836,0.014895099793626687,0
+3,51.513422,-0.134897,0.12251227022222377,0.009003754352852056,0
+1,51.513528,-0.135158,0.10445710222222299,0.020786445234401263,0
+2,51.513481,-0.135344,0.0915902008888903,0.015562044560387567,0
+2,51.513594,-0.135063,0.11102890666666831,0.028122837669561196,0
+3,51.513227,-0.135801,0.059976362666667116,-0.012671950570037172,0
+1,51.51318,-0.135762,0.06267426133333459,-0.017896351244050812,0
+2,51.513132,-0.13574,0.06419615288888969,-0.023231909378927995,0
+1,51.513048,-0.135645,0.07076795733333502,-0.0325691361151606,0
+1,51.513006,-0.135602,0.07374256355555636,-0.03723774948327685,0
+1,51.512883,-0.135501,0.08072942933333344,-0.050910117203455396,0
+1,51.51327,-0.135832,0.05783187911111132,-0.007892179741057326,0
+3,51.513459,-0.136049,0.04282049422222284,0.013116580415071022,0
+3,51.513431,-0.13614,0.036525397333333376,0.01000417150299343,0
+3,51.513402,-0.136228,0.030437831111112756,0.006780605130052408,0
+3,51.512593,-0.134999,0.11545622755555579,-0.0831457809352355,4
+1,51.512585,-0.134793,0.12970666666666775,-0.08403504062451334,4
+2,51.512555,-0.134896,0.12258144711111274,-0.08736976445910777,4
+1,51.512521,-0.135,0.11538705066666688,-0.09114911813794624,4
+1,51.513137,-0.133483,0.22032839111111258,-0.022676122073030602,4
+1,51.513228,-0.133265,0.23540895288889008,-0.012560793109173629,4
+2,51.513152,-0.133296,0.23326446933333433,-0.021008760156128292,4
+1,51.513258,-0.132933,0.2583756800000011,-0.009226069274579196,4
+1,51.513544,-0.133998,0.18470229333333377,0.022564964612956928,4
+1,51.513626,-0.134042,0.18165851022222346,0.031679876426672526,4
+2,51.513637,-0.134156,0.17377234488888982,0.032902608499330854,4
+2,51.513524,-0.134091,0.17826884266666831,0.020341815389367413,4
+1,51.51382,-0.134272,0.16574782577777847,0.05324442388869827,0
+1,51.513724,-0.13422,0.1693450240000004,0.0425733076189439,0
+1,51.513704,-0.134704,0.13586340977777922,0.040350158395354385,0
+1,51.513831,-0.134782,0.13046761244444438,0.05446715596135654,0
+1,51.513915,-0.13501,0.11469528177777921,0.06380438269679928,0
+1,51.513597,-0.134923,0.12071367111111275,0.02845631005294169,0
+1,51.514032,-0.134885,0.12334239288888937,0.07680980565100676,0
+5,51.513891,-0.134212,0.16989843911111202,0.06113660362975559,0
+1,51.513758,-0.134135,0.175225059555556,0.046352661297782316,0
+1,51.514065,-0.134364,0.15938355199999998,0.08047800186898163,0
+2,51.514146,-0.134447,0.1536418702222223,0.08948175622104393,0
+2,51.514201,-0.134479,0.1514282097777795,0.09559541658433546,0
+1,51.51423,-0.134658,0.13904554666666746,0.09881898295727648,0
+1,51.514319,-0.134367,0.15917602133333508,0.10871199699940637,0
+1,51.514377,-0.134179,0.1721812764444457,0.11515912974607834,0
+1,51.514357,-0.13416,0.17349563733333406,0.11293598052248882,0
+2,51.514382,-0.134069,0.17979073422222347,0.11571491705118586,0
+2,51.514402,-0.134085,0.17868390400000012,0.11793806627398562,0
+5,51.514522,-0.133821,0.19694660266666775,0.13127696161157354,0
+1,51.514497,-0.133922,0.18995973688888879,0.12849802508287644,0
+1,51.514472,-0.13385,0.19494047288888994,0.12571908855417935,0
+1,51.514504,-0.133725,0.2035875840000001,0.1292761273112908,0
+1,51.514546,-0.133745,0.20220404622222277,0.13394474067940698,0
+4,51.514561,-0.133676,0.20697725155555713,0.1356121025963093,0
+1,51.514594,-0.133563,0.2147942400000017,0.13928029881428416,0
+2,51.514581,-0.133467,0.22143522133333393,0.13783525181910894,0
+1,51.514606,-0.133393,0.22655431111111113,0.14061418834780604,0
+1,51.515834,-0.134474,0.15177409422222232,0.2771155506326034,0
+1,51.515195,-0.135259,0.09747023644444591,0.20608593296150768,0
+1,51.515149,-0.135395,0.08806217955555723,0.2009726897491474,0
+1,51.514818,-0.136022,0.04468827022222277,0.16417957011011453,0
+3,51.514843,-0.136804,-0.009408056888888683,0.16695850663881162,0
+1,51.514914,-0.136583,0.005880035555555663,0.1748506863798689,0
+1,51.514496,-0.135653,0.07021454222222334,0.1283868676220129,0
+2,51.514743,-0.135578,0.0754028088888894,0.15584276052481316,0
+1,51.514467,-0.13486,0.12507181511111132,0.12516330124907182,0
+1,51.514453,-0.13469,0.13683188622222275,0.12360709679303306,0
+1,51.514845,-0.134818,0.1279772444444457,0.16718082156132852,0
+1,51.514389,-0.135704,0.06668652088889027,0.11649301927960015,0
+1,51.514399,-0.135561,0.07657881600000171,0.11760459389060512,0
+2,51.514335,-0.135649,0.07049124977777915,0.11049051637796203,0
+1,51.514224,-0.135415,0.08667864177777806,0.09815203819051554,0
+1,51.51422,-0.135576,0.07554116266666733,0.09770740834627156,0
+2,51.514145,-0.135357,0.0906909013333338,0.08937059876018039,0
+3,51.514108,-0.135475,0.0825280284444444,0.08525777269796148,0
+2,51.514359,-0.136226,0.03057618488888869,0.11315829544500577,0
+1,51.514326,-0.136328,0.023520142222222706,0.1094900992270309,0
+1,51.514544,-0.136222,0.030852892444444557,0.13372242575689008,0
+1,51.514569,-0.136117,0.038116465777779385,0.13650136228558707,0
+1,51.514586,-0.13603,0.04413485511111109,0.1383910391250064,0
+1,51.514612,-0.136266,0.027809109333334248,0.14128113311456691,0
+2,51.514575,-0.136421,0.017086691555557254,0.13716830705234806,0
+3,51.514507,-0.136935,-0.01847022933333259,0.12960959969467123,0
+3,51.514274,-0.136931,-0.018193521777776778,0.10370991124790968,0
+1,51.514293,-0.136799,-0.009062172444443906,0.10582190300984579,0
+1,51.514058,-0.13678,-0.007747811555555595,0.07969989964056734,0
+3,51.514148,-0.136696,-0.0019369528888888987,0.08970407114356077,0
+1,51.513961,-0.136712,-0.0030437831111103097,0.06891762590994938,0
+1,51.514027,-0.136123,0.03770140444444564,0.07625401834510936,0
+1,51.514076,-0.135958,0.04911559111111219,0.0817007339416399,0
+1,51.514096,-0.135883,0.05430385777777835,0.08392388316443966,0
+2,51.514134,-0.135788,0.060875662222223625,0.08814786668752211,0
+2,51.514033,-0.135849,0.05665587200000094,0.0769209631118703,0
+4,51.513996,-0.136008,0.045656746666668135,0.07280813704965139,0
+5,51.51396,-0.136099,0.03936164977777873,0.06880646844829608,0
+2,51.513945,-0.13617,0.034450090666666544,0.06713910653139371,0
+5,51.513821,-0.135485,0.08183625955555673,0.053355581349561865,0
+5,51.513999,-0.135374,0.08951489422222347,0.07314160943303183,0
+3,51.513795,-0.135582,0.07512610133333364,0.05046548736000123,0
+3,51.513766,-0.135679,0.06841594311111232,0.047241920986270336,0
+1,51.513726,-0.135814,0.059077063111112604,0.042795622540670986,0
+5,51.513692,-0.135905,0.05278196622222314,0.03901626886183257,0
+4,51.513672,-0.135992,0.0467635768888896,0.03679311963903281,0
+4,51.513603,-0.136217,0.03119877688888939,0.02912325482049244,0
+1,51.513482,-0.136579,0.006156743111111529,0.015673202022040977,0
+4,51.513458,-0.136675,-0.0004842382222207675,0.01300542295420748,0
+1,51.513429,-0.136764,-0.0066409813333322965,0.009781856581266402,0
+3,51.513404,-0.136877,-0.014457969777776858,0.007002920052569361,0
+2,51.513359,-0.136953,-0.019715413333331933,0.0020008343010725627,0
+1,51.513378,-0.13723,-0.03887741155555413,0.004112826063008723,0
+2,51.513855,-0.136651,0.0011760071111123205,0.05713493502840028,0
+1,51.513875,-0.136503,0.011414186666666548,0.05935808425119993,0
+1,51.513565,-0.137367,-0.04835464533333178,0.024899271296620118,0
+2,51.513616,-0.137422,-0.05215937422222067,0.030568301814877796,0
+3,51.513742,-0.137472,-0.05561821866666661,0.04457414191922665,0
+1,51.513918,-0.1383,-0.1128966826666663,0.06413785508017977,1
+1,51.513772,-0.137363,-0.04807793777777786,0.04790886575382103,0
+4,51.513502,-0.137995,-0.0917977315555552,0.017896351244840625,0
+2,51.513712,-0.138139,-0.10175920355555557,0.04123941808463222,1
+2,51.513644,-0.138239,-0.10867689244444367,0.03368071072695533,1
+1,51.513711,-0.138272,-0.11095972977777735,0.041128260623768675,1
+5,51.514061,-0.138083,-0.09788529777777771,0.08003337202394778,1
+3,51.514748,-0.137912,-0.08605604977777742,0.1563985478299207,2
+2,51.514794,-0.137707,-0.07187478755555449,0.16151179104307078,2
+3,51.514526,-0.137108,-0.030437831111110814,0.13172159145581752,0
+2,51.514706,-0.137065,-0.027463224888887527,0.1517299344618045,0
+1,51.512311,-0.138474,-0.1249334613333335,-0.11449218497852759,7
+1,51.511998,-0.138123,-0.10065237333333227,-0.14928447031648787,7
+1,51.511856,-0.137762,-0.07567951644444332,-0.16506882979860255,7
diff --git a/fitting Models To Data.ipynb b/fitting Models To Data.ipynb
new file mode 100644
index 0000000..cedddc1
--- /dev/null
+++ b/fitting Models To Data.ipynb	
@@ -0,0 +1,525 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# The Engineering World - A Place For Learning And Exploring\n",
+    "\n",
+    "## Fitting model To Data"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Standard imports"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import math"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import matplotlib\n",
+    "import matplotlib.pyplot as pp"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%matplotlib inline"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import statsmodels\n",
+    "import statsmodels.api as sm\n",
+    "import statsmodels.formula.api as smf"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "gapminder = pd.read_csv('gapminder.csv')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "gdata = gapminder.query('year == 1985')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "size = 1e-6 * gdata.population\n",
+    "\n",
+    "colors = gdata.region.map({'Africa': 'skyblue', 'Europe': 'gold', 'America': 'palegreen', 'Asia': 'coral'})\n",
+    "\n",
+    "def plotdata():\n",
+    "    gdata.plot.scatter('age5_surviving','babies_per_woman',\n",
+    "                       c=colors,s=size,linewidths=0.5,edgecolor='k',alpha=0.5)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "plotdata()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model = smf.ols(formula='babies_per_woman ~ 1', data=gdata)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "grandmean = model.fit()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<statsmodels.regression.linear_model.RegressionResultsWrapper at 0x1cbfeaba0b8>"
+      ]
+     },
+     "execution_count": 19,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "grandmean"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def plotfit(fit):\n",
+    "    plotdata()\n",
+    "    pp.scatter(gdata.age5_surviving,fit.predict(gdata),\n",
+    "              c=colors, s=30, linewidths=0.5, edgecolor='k', marker='D')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "plotfit(grandmean)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Intercept    4.360714\n",
+       "dtype: float64"
+      ]
+     },
+     "execution_count": 24,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "grandmean.params"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "4.360714285714285"
+      ]
+     },
+     "execution_count": 25,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "gdata.babies_per_woman.mean()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "groupmeans = smf.ols(formula='babies_per_woman ~ 1 + region', data=gdata).fit()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "plotfit(groupmeans)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Intercept            6.321321\n",
+       "region[T.America]   -2.663139\n",
+       "region[T.Asia]      -1.545744\n",
+       "region[T.Europe]    -4.285639\n",
+       "dtype: float64"
+      ]
+     },
+     "execution_count": 28,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "groupmeans.params"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "groupmeans = smf.ols(formula='babies_per_woman ~ -1 + region', data=gdata).fit()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "region[Africa]     6.321321\n",
+       "region[America]    3.658182\n",
+       "region[Asia]       4.775577\n",
+       "region[Europe]     2.035682\n",
+       "dtype: float64"
+      ]
+     },
+     "execution_count": 30,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "groupmeans.params"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "region\n",
+       "Africa     6.321321\n",
+       "America    3.658182\n",
+       "Asia       4.775577\n",
+       "Europe     2.035682\n",
+       "Name: babies_per_woman, dtype: float64"
+      ]
+     },
+     "execution_count": 31,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "gdata.groupby('region').babies_per_woman.mean()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "surviving = smf.ols(formula='babies_per_woman ~ -1 + region + age5_surviving', data=gdata).fit()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXwAAAELCAYAAADawD2zAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDIuMi4yLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvhp/UCwAAIABJREFUeJzs3Xdc1dUfx/HXFy5T9hJREQeKirhwr9xa5sjSUlOzHD9TU8vMshzlbtowy5EjbTnT3Hsh4hYVFBAUZe99uff8/kDIGyigXEE4z8eDRz++9zvOvf16873ne87nKEIIJEmSpPLPoLQbIEmSJD0dMvAlSZIqCBn4kiRJFYQMfEmSpApCBr4kSVIFIQNfkiSpgpCBL0mSVEHIwJckSaogZOBLkiRVEKrSbsCDHBwchJubW2k3Q5Ik6Zly9uzZGCGEY2H7lanAd3Nzw8/Pr7SbIUmS9ExRFCW0KPvJLh1JkqQKQga+JElSBSEDX5IkqYKQgS9JklRByMCXJEmqIGTgS5IkVRAy8CVJzzQaDSFBQcTHx5d2U6QKrkyNw5ek8kYIwd6Na6hnkMLllCzcug3AtVbt0m6WVEHJO3xJ0qPs7GwsMxOoVcWJDnWqEnT5fGk3SarA5B2+JOmRSqUiyciS29GxhCWmU/O5vqXdJKkC03vgK4ryDjAaUICfhRBf6/uaklRWKIpCjyFvEHwjkLr2Djg6OZV2k6QKTK+BryiKJzlh3xLIAnYrirJTCHFDn9eVpLJEpVJRt36D0m6GJOm9D78+4COESBNCZANHgAF6vqYkSZJUAH0H/hWgo6Io9oqimAPPA9Uf3EFRlDGKovgpiuIXHR2t5+ZIkiRVXHoNfCHENWARsA/YDVwEsv+zz09CCG8hhLejY6HlnIskLi6OsZOmkpSUVCLnkyRJKg/0PixTCLFSCNFMCNERiAP02n8fFxfHm1M/wLr7EN54Z5oMfUmSpPv0HviKojjd/6cr8BKwUV/Xyg37xqM+wK6aGw1enypDX5Ik6b6nMfFqk6IoV4G/gbeFEHqZX/5g2JtaWgFQydZehr4kSdJ9T6NLp4MQooEQorEQ4oC+rrP0x5+p2nlAXtjnqmRrj32r7qxYs05fl5YkSXomlJvSCh9Pf4+s8weIDr6usz3i+kVMgs8xZcL4UmqZJElS2VBuAt/Q0JBlXywi+djWvNCPuH4RzfkDLF00D0VRSrmFkiRJpavcBD7ohv6VPZtk2EuSJD2gXAU+/Bv6z9e0lWEvSZL0gHJZLdPQ0JAhgweVdjMkSZLKlHJ3hy9JkiQVTAa+JElSBSEDX5IkqYKQgS9JklRByMCXJEmqIGTgS5IkVRDlclimJJWGkNAwDp+9hKmhAS8/3x0jI6PSbpIk6ZB3+GXArVu32HfwUGk3Q3pCfleuU7v1c6iq1ORWaGhpN0eS8pGBX8pCQkKYNGcRK/f78NfW7aXdHOkJeNSsToDPURJDrlGtatXSbk65kJmZye5fVxF07WppN6VckF06pSgkJIR35i6m5biZqIxN2LLlF2A7L/fvW9pNkx5Dowb1aVCvLgYGBrKkRwnJzs4mIymB1GS5nkVJUIQQpd2GPN7e3sLPz6+0m/FU/Dfsc13e8gsDmtWVoS9JUpEpinJWCOFd2H5PY4nDKYqi+CuKckVRlI2Kopjq+5rPgtFT3s8X9gCNBozkp007CA8Pf+ixGRkZ+m6eJEnlkF4DX1GUqsAkwFsI4QkYAq/q85rPig+nTOTi7z/y329Yt3wO0alxfao+pA949oIlvDhsFDeDgp5GMyVJKkeexkNbFWCmKIoKMAfuPoVrlnldOnXkf/26c2790rzQv+VziOqpd/jovSkFHjN7wRKiHOrQ6f3PeXf+lzL0JUkqFr0GvhAiHPgcCAPuAYlCiL36vOaz5MHQL2rYu3p3QGVkTIuxH8nQlySpWPTdpWML9ANqAi5AJUVRhv1nnzGKovgpiuIXHR2tz+aUSbmhX1cT89Cwn/fF13lhnys39KfO+4LQsDCd/Y+f9GHNxt/12m5Jkp49+u7S6QaECCGihRBqYDPQ9sEdhBA/CSG8hRDejo6Oem5O2dSlU0emTvjfQ183NjJCo87Mt11otShCi5Hq39G1x06c4qvftnPkdhI/rlqjl/ZKkvRs0nfghwGtFUUxV3IGJncFrun5muXOtElvUzMjkpBT+/O2qTMz8Fv+Gd/O+RAXFxcgJ+y//v1vvEdOoW73AfjGqmXoS5KUR999+KeBv4BzwOX71/tJn9cESEtL41pAQLkavvjB1HfyQv/BsHd1dQV0wz530k/dbv0LDP3MzEyOnTj51N+DJEmlS++jdIQQs4QQHkIITyHE60KI/H0TJUir1bJhxx6upihs2L4r37DHZ1lu6B9dMk0n7AE+nr+I5sPfyTfDs263/vy19zC5z0cyMzMZNWkqX2/dz+pfNz7V9kuSVLrKXS2d7OxsMKmEk0tVNCqTchX4kBP6u35fpxP2AF/Nn4vvzwvRarU62/23r2fUwD44OjrmhX31vm/RYsh4joTG64R+cHBwvuP1LSkpiYSEhKd6TUmqqMplaYVTfue4FRGNe1VnvJs2LoGWPRvOX7zEnB9W03LMDAwMDPDfvp7eDaoz5JWBOmFv41I975jru/6gUw1bnB0d+Pb37dSys2DponkYGOj/XuD8yWNkXDuDoQLaGg1p3bWn3q8pSeVRUUsrlMvAr8hyQ9+iiivPN3RlyCsDAXhzwjs49B6BrYtrvmNOrvmGtNhouk39jMiAS6jP7nsqoX9g9Xd0dXMA4ODNCLqMnqzX60lSeVVmaulIT1fTxl7MfnsUL3vXywt7gLEjhxO4c2O+LpuEe3e4deksnd6eCUDlel4YNe/OpOkf6b17R21oTLZGg0ajJdNAFm6VJH2Td/gViK/fWRas+o0Wb07DwMCAhHt32LH4AwYvXIGRiW5Nu8iASxj6H+XzT2frrT1JiYmc2bcTodHQrGtv7Bwc9HYtSSrPinqHL2+rKpCW3s2ZASxYuYR6fYYS9OcP1KruQnZWZr7Aj7hwiqHPtXnk+dZu+I0XenbH3t7+ofskJiZy+vxF0jKyqFGlMl6eDTA0NATAytqari8PeeL3VVIuXvEnLiGRjm1a5bVRksoT2aVTwbT0bs6MUa8S8fdK1i1bypqlX3Bp1SLSkxPz9jm38QeGPudNn14Pf4i68KulHAxP4a13ZxAbG1vgPjeDQ/jz8GkMXBtg37gNYcKcX7ftRK1Wl/j7elJxcXGcvx1Dik1VTp05W9rNkSS9kIFfAbX0bs4vy77F1NQUW1tbVn21iLPL55GenIjv+u8Y3qVVoWEfYuKER7f+NH5zRr7QT0lJITs7m+MX/Knboi0mZmYA2FV2xsGjGT5+5/T+HovLzMyMrKR4IoMCqewou5ak8kkGvoStrS3rvvuCCz/OYVT3NkUK+5ptugFgamGpE/pBQUG06N6H1t1fAHOrfBPBLG1tuRuXWNCpS5WZmRkj+vfm1a5tcK9dq7SbI0l6IfvwJSAn9LdtWPvIfY6fPIlveAIth+r2u5taWOI54j1GjJtASEQ0Az9bRkpcDEs+/YTvfttKckICvkcO0HPgYIQQZfYuw8TEBBMTk8J3lKRnlAx8qcjatWnDn9v/IeLaBZzrN8nbnq3Owm/VYoJuhTFo4Qos7ByxsHOk++S5jB/cHwOVCoda9bkdeove/QbQxL1mKb4LSaq4yurNllQGKYrC1ws+RVw6TMS1C0BO2J/8bjZB16/lhX0uC3tHtIoBA+f+QO93PuFuSib/rP2ZIydOMXnGx0+9jIMkVXQy8KVieTD0wy+fwffHz/h4/JsYm5qhKP/+3yklPoa/Zk1k8LwfMbe2BaDrmGncM7Rk5ZZ/UJp0ZcK0GTL0JekpkoEvFVtu6NvducSXH71Lm9at2Ll+JVtmvU1qfM5onY0fjGbQpz/khX2urmOmYWBiRvTtEExa9pahL0lPkQx8qciEEPz8zRfExsaiKApzPpxOndq1AahRowY716/kz5njSI2Pxa1JK05sWJ7vHHcDrxAXHop7my5Uruv50NAPDgnh/PkLJdr+tLQ0goKCciqqVhDyj6n0IBn4UpEIIZj//hSqnfubT0YNLnCyVY0aNRgzfCi/zxhNhP856lsacGD54rzX7wZeYfc3cxm6ZDUm5pUAcKzTgODIWGJiYvL2ux4QwLCpHzHy/U/47c+/SqT9UVFRzFjyLT/vOsYvf2wqkXOWdcnJyezaWjHeq1Q0eh2loyhKPeDB1bRrAZ8IIb7W53WfJSkpKWzacwitgULbRvWpV6d2aTcpn9yw75ToT/uatrTLVDNj1GDmrvo9X1mFNk0bk2X5HiJbzfBurfn1z03sW76Y+p2f5+8F7/PqwhV5Ya/Vajnz80IWTJuEk5MTkBP2oz6YwwsffolWk82iOZMAePWVlwkKDsZIpcq3FkBhNBoNmw8cx619T+yrVsdv0xqysrIwNjZ+5HGXr17jUlAoLvbWdG776DITZZGlpSUvvPRKaTdDKkP0vcRhgBCiiRCiCdAcSAO26POaz5qTZ85StVlb6rTuzNmrN0q7OfnohL2LBQBWJkYsaGBa4J2+haUlLpUdsLexxMjIiPcnT6KHRzVOLJvH8Z1buLL+a9KTEtBqtRz/fi6f/G8kTRt7Abphb6hSYWRiykuzlrJo1Qa+XLqUqQu+YuKcRYSEhBTrPaSmplLJoTLV7G1Ij7pLA68mJCUlFXrc2RshuHp34FZ8BqmpqcW65n+lp6ej0Wie6ByS9KSKXC1TUZS6wDSgBg98MxBCdCni8T2AWUKIdg/bpyJWy7wWeIPTIRFY2DlglhjBC906l3aTdOzduYOglfP4n5dzvtciUjKYe7cSP2zQ7Xa5FRqKqYkJzs75j0lISOCNye+TrTJh7sTReWGflpZG+xdfZuDCVRiqdL94qjMz+GXiq4z87g8UBc4sn8dXH73LD6vXUcetBsNfG4S5uflD34NWq2X1pu3UbNkJRVEIOn2EkQNeQKV69Bfcv3buIcvCgfTIMEYO7PvYBdV27jtItFpBnZJE/85tcXR0LPwgSSqGEl8ARVGUi8CPwFkg71ZFCFGkSlOKoqwCzgkhvnvYPhUx8AHuhIeTlJxC/Xp185UiKG1CCGZNGkff7GC8K1vkbU/Nymb65VQ+XrGRypUrF+ucCQkJxMTG5j3wzTXkzXGYNu1M3XZddbZf2LWZ9OQE2gwaBeSM/d/x6WQ8ur5IYvgtbl84TZ+unZj9wbSHXjMlJYVDJ08jgE6tvLG2ti60nVqtlsjISOzt7Qvt/nmYjIwMNh44SZ1mrdBqtSRcOU2/nt0e61xliUaj4fyly6RnZNKofj1sbGxKu0kVmj4C/6wQovljNsYYuAs0FEJE/ue1McAYAFdX1+ahoaGPcwlJj/4b+k8S9oV57c2xmDXtkhf6F3b9RXpyUl7Y58pWZ/H7R+OwdnKh9+TZhPgeplry7UeGfmnQaDSs2rwD9zadiYu4h7M2mbYtC/3vskzTarVs2LoDy9qemJqbE3bJjwGdWuMg1zMoNfpY8epvRVHGK4pSRVEUu9yfIh7bm5y7+8j/viCE+EkI4S2E8JZfdQsXFR3NuQuXnupwO0VRmLP0R7aranH0TqLewh5g48rlpJ8/SOCJA/gf2sm5zWtxqlo9337XDu9Gq9HQe/JsDFUq6rTtRph5NWYtWFzAWUuPoaEhAzq3I8nfFxeRQpsWj3XPVKaEhYWhcnbDzqky5haWuLfqyPGzJTuEVtKP4gT+CHL68E+S061zFihq/8trwMbiNU0qyI4jpwjKUnGmhMeoFyY39M/X7MTHKzZiYmLC8t82c/D4ySc677nTPhw/sE9n29ofvyPZbx+XNv/Cwa1/UDMrkpBT+/Nev7x/Oxd2b2LIopU6/f11O3Tnnk1N5n1R8CAwIYRe/1BqNBp+276L37bv0nlA6+DgQN+e3WjdonmZ67J7HEIInfdRHt5TRVHkYZlCiMeqeKUoijnQHRj7OMdLuhytLYgIvUm79i2e+rUVReGdj2YBOQuGaLQC9RNMYvI7dZK/F36ApUohKyuLjt17sufwMaJSsxg4eiJCCPadvYJ3s2YIv7OEnNpPVno6/rv+wNqpGlpNdr4HvFlpKVQyN8t3rezsbAYMe4OgW6H889ta3NzcHqvNKSkpHDt9Brfq1ahf113ntbS0NFJQIYQgLS0NS0vLx7pGWefq6srx8ztJsLTC1MyckAu+DOjYsrSbJRVBsda0VRTFE2gA5K2HJ4R4dE3dYqioD22fVf+90yuO3LCf3cQORVFYcjmOZM/OtBs6DvP/BGVSXBypwVcIDQnGxMSY59q2Yeq8L0jDkN6TZ+ctzxhwZBeGIRdZ8c3nOsfnhr374PGojE3YOf89/l63gvV/bGLMyNcLHE30MOu37qRKkzaEXb1MnxYN8o24uX7jJgAe7nUe52N5ZmRnZ+N3/iLpmZk0buCBnV1Re3clfSjxPnxFUWYB397/6QwsBvo+dgulZ15Rw16j0eiMY/9v2ANMa2SH6vw+Av1O5Dveys4O7KvS//leTBo7Gq9Gnnz50buQnsKfH49HnZlBwJFdZAVd5NMZ7+kc+2DYO7m5Y+fiygsffk6PwcO5obJn7AeziIiIKPJ71gqBysgIQ2OjApdq9HCv88iwT0lJISQkhKysrCJfsyxSqVS0btGczu3byrB/hhSnD/9loCsQIYR4A2gMyNUipELtP3qcnzbmjNUXQrDwvYk6YZ/rk2ZOHP3+M9LT8k9ycnarxYWAoLzfvRp5smrxHN4e8hLbPx6LQfAFFs2YSpUH7ta1Wq1O2Oeyc3HlpdlLOb1pHXX6jcwL/YnTPqBF556EhYU9dJLU8x1aE3fJh/p25ri4uBTrc4iKjmbDnsOciUxj/bZ/yuTavmVBZmYmZ44e4tzJ4xWq7tHTUJzSCulCCK2iKNmKolgBUeSUSpDKmPj4eDIzM4vVVaFPHVq1wMujLpDzrWDM9I/5Zt3XTG6oW0lz2fUEmr06FrP7pRcepCgK2f/pffSoVw+PevUYPWI4BgYF37vExMXTwCR/n76RsQlGpuYkRtyl+ZgP6TNiDBYuNWn40ht0f+0NDNSZrPruS5o1bqyzCpaDgwMDencv7kcAwOXrgdRq1gYTU1PCNdlERkZSrVq1xzpXeSWEYP+G1bRzMCJbq+XAn0H0fG1EaTer3CjOHb6foig2wM/kjNA5B/jqpVXSY4uPj+f3gyfZdeEGl69eL+3mAGBubk6VKlXyfu/Rtz8NXp/M1/7xedu+vxxFQrvBtH/59Yeex4CCnzc9LOwNDAw4uO1PDn35IfH37uRtT46JZNvCD2jcawB1WnfC2KwSPd6dT1JMBNeP7cO2ag1e+/pX3l3yA+1692Plul+L+5YLVNu1OrevXSYtNYXku2H56hBJOV1eTmRgY1EJBytLTFJjKc5zRunRihz4QojxQogEIcSP5Iy6GXG/a0cqQzIzMzGpZIVt5SqkpKSUdnMe6sHQXxWYQJJXNxp37fPQ/WMj7lHPtWqxr2NmZsaRvzflhX5yTCRbF0zHq0c/vHr0ByA9OZG938/HwNAIEDw/eTbGZpV4ccYSrGo1ZNuZqzqh/7hdMZWdHGlVyxnTyGBe7tYeM7P83zwqOnNzc6KzBBqNFnV2NmkGpkV+VnQjOIStu/c9sk5SdGQEZ08cq7B1jYpVLVNRFC/ALfc4RVHqCCE266Fd0mNydnbG2zWBlJQEWnk3K+3mPFKPvv0xMDAgNTmJYQMHsX77LkxbdMToP2UMMjMySAjyp9GAh/9BeJTc0O/04kBSMrJwr+6MXeWcbxzpyYnsWPIRoGBkZnw/7HPq8iiKQvfxH7Bv2UK2nbkK/ErHNq0Y9/5MenVqz7R3JhTp+tcunufOxTNYqFMxMjQgW6NwOSGKwNgUenXpJLt1HmBoaEjrga9z5Mg+FAMjOrzy8G98/3Xy0jVcm7Xl8Clf+j6kfMW53dupo0onwMKSBo2bFLhPeVac0gqrAC/AH8idvSKEEKMeflTxyGGZFVtKSgrbDxwh29wGh+puIATRYcGYZaXxYrdOT3xHrFarCQkJwd3dnRlzPiPGvg4RPvsIDLiGysIO9zad8pVwAAg5d4rwqxcxVrTEhd2k+3uLCPU9hLsmrtDQP7V/Dw7RN3F31u2+SU3PYE9oHD2Hj6VSpfzPLHKdvXgJ/9C7IARN3WvSqIHH4735CuCojy+37kXTsbkXbq75Z2cDXLtwlvDAq7R54aVHfu7PGn3U0rkqhGjwxC17BBn4EkBMTAw3gm+hKAoe7rX1UphLCMEPP69kyCsDyczMpHP/QWBiTv0OPWg5cHjefrfO+3DrvA+e3fpydPU39PvwcwyNjAAIPrE3X+j7+/tTuXJlHBwcuBd+h4h9f9K0RpV81wfIyMriZJopXQYMKvD1yMhIdp8PoFbjnHIMN/xOMbBjiyIVfpMqFn3U0jmlKIpeA1/Sv7S0NDZu/4f1f+/l0IlTpd2cAjk4ONCmpTetWzTXWxVGRVF4e8xb2Nra4uzszKGtf0BmGud3/YXvppy5hCHnTnHrvA9evV7KF/YAtdr14IahHV98twyAw0ePMWj8VLq+PJSIiAiu+RyjUTWnh7bB1NgYw9i7ZGZmFvh6ZEws1lX+7e6xcHIhLi6uJN6+VEEVpw9/DTmhHwFkAgo5XTpeemmZpBe7j5zAyas1xiYm3A68xq3QUNxq1CjtZpWK7OxsIiIiqFatGs7OzhzZ/hdzP/+K4yf2ERV0jaTIuwxevIqzG5djbvSQeyMhQMkJ+4mz5vPy3O8B6PnqCD4Z2JWdQclohWBAS88CD69qZkhUVBTVq+fvgqhRrSq+h3ywc3RCCEHinWAqNyrS8hPSAzIyMvDZswNNViZNO/fErgJX9SzOHf4q4HWgF/Ai0Of+P6VniForML4/rtzM2pbE5LI7kkefsrOzeaP3c8we1IP9u/4BwMnJifkzZ/DupLd5vkNr+j/fnZ0fj2FACw9+mv8Jp3/8DM0DI3SCj++hjjae5l6eTJw1n5dmf4uZlQ1mVjb0n/M9H/26k19C0vkr3pS2nyzjl8P5uyu1aB86CsXa2poe3g2JOH+CqAuneLF9i0cu9FKWbNz6N/uPHi/tZgBwYsdmWpmk8Zytwuntv5V2c0pVce7ww4QQ2/XWEumpaFKvNsd8T1DJ3omMiFDq9+1d2k166rKzs5n+1jBmepjjbufA+1/PwdHJicbNvUlPT6dT04a43h8R9MnkCXkrY30+YzLvLfiMVuNmEnr6IG5Z0bw8oC8vDB/NoHnLMbP6t/vJzMqGwYtW8tuHYxn+1XpSFGPWBwcTFLELv1sRrB4zAGc7G+5kQMdHTJBzrVYN12dwFE+nVt6YmZrm2y6E4PzJ48Td9MdQk4XayIw6LdtTq159vbVFZKRhZp+zeI+RpmLP3C1O4F9XFGUD8Dc5XToAyGGZz5Z6dWrjUtmJpKQkKrf2LHSZv/ImN+zHWcfjbpszSmNx6yrMnDOV6Lc/ZOu3izBGw/gvf8bY1Exnwlhdd3c+nzGZ/02fQocWzbAS6bi4uGBqqBB/77ZO4APEhYdhZm2LYmhIm0GjOP3XLxwMCqBqh368sWYPmoxUmjZuTJdy+O/ApUrBD6pP7tlJjZQ7NHPN+ayEEFzw2UOgWk1dz8J7hxPi47l21hcLWzs8m3kXaYx+7Zbt2XtoJ0YK2Hm2IOLePZwf0r7yrjijdFYXsFkOy5SeKR+MHsGb5hG42+p2jYQnpTNp71XW9WuMkYEB75y6R3qmGtuadVm0cj1GDzyszcrKwtjYGI1Gg6GhIRkZGbTp2YcO//sIl3qNcs537SLH1i9j0Kc/5M0EFkLw+0fjqNm8LQHH9/PKnG8J9TlIa0cTxo0q2fIBAZcvEh7gT02vZtSsWzaGcqalpXFu43La16rCuZC7nE/UoKgz6e/hjF+smu4jxz0ywBMTEji1cQUd3RyJT80gwND2oSOc/kuj0aDVatFoNBzcsY3nXx5cUm+rTCjxUTpCiDcK+CmxsJekwuzYe4BdBw8/0Tm8WrbGN1Z3puy95AzmHrnOun6NMTdSYWRowDdtqmCjTuYF7jL9zWE6s2tz17fNXdTc1NSUU3t2cGzZPO4GXCb82kV2fz2bV+Z+rxP2R9d8S6uBI6jWoAlOtephZmWDR4+X8InO5MdVa3TalJaWRnJyct7vy39ZV+SZ08nJyUT57KeLvQE3D+4oM0XawsPCcLPM+ewuJ2VTt3UnarXtyongCCy0GYVWEL1x5QJtq9thbmpCVXtrlNjwIpddMDQ0xMjICFNT03IX9sVRnPLI1RRF2aIoSpSiKJGKomxSFOXZ61yUnlmNG3jgVb/eE51jyOj/oW0/kBX+UUBOEE/Zc5mvejXC3OjfrhUjQwMWd2/I+sthjDCPyRf6QghuBAbm/Z4b+ieXL+TmlpX8uPgzTvy0CCFEXti7NvLG2LwSF3ZtpsfbH+Yd69HjJXxj1SxfnTMcVK1W8+LQN3h+yMi8stK9u3Qq9gNbIQSUodWozC0sSM7M6UM30WSSkpJC9N07OFmYkCmUQrsXrWwdiEpOA3LeWyaGcrWtYipO5+FqYAPwyv3fh93f9nilAyWpmKpXK34tnYL0GTyEuUFhrA70pbeLKbEG5uwNT6W/m+6EJp87cdSzt8CrsiXj4xP4cOwbLFm1Pm9R96ybF+jw1ru8MDCnW8HU1BS/Q3uAnEDac/IMR5YvIlOdjXvbLphUsmTPd/N5/et1+Qq+2bjWIeDSIdRqNW9OepemI6diYm7ByIlTsbGy5OrVa/z5y89FKslsaWlJ5TbdORTgj3uXF3W6o0qTS9WqXMwyoJ5WywBPN3xunMbFzJQ6Lo6czjTP+8b0MO4NGnIiLITbIbfIFApePfo9pZaXH8Xpw78ghGhS2LYCjrMBVgCegABGCSEKnPEj+/Clp0Gj0bBm03YC/C9z/eheFi1fxeFtf1HFfz/97of+sdAYTtyOY3o7dxRFYc2NREy7vcagkW8xa9I4+mpC8HaqxA/X4qkxaHxe6OcSQrByyz9kGZlz62YgJ44fg5QEqrfrRURIID0mzMweJ5duAAAgAElEQVQL/ajAK2T67eHLz2YzevI0Kvcahr1rLbRaLTu//JjmfQaTlZnByVVfsvu3tcWuw1+WxERF4rvtNzytjbGzMON2XDIhWlO6Dh6uU4ZaKh59lFbYD/zCv4uRvwa8IYToWshxa4BjQogViqIYA+ZCiISC9pWBLz0tmZmZ3AgKxtnJEYf7E3F+XDKfKv77qSTUHAmJYm7n+nlhb9Z9CC8OHsroYf2Y4KChdRWrvHM9LPTPXbzM2ZthKIpCVQsjenTtwkefzufElUBMTM3oMuUzYm5eJdNvD98umsfItyfrhP3e7+fRpPfLONfJGbIYeukMJ1Z+8cyHvkaj4ea1qyTFxeDsWpNqNWqgKApXAwK5eCMEUPBwrUJTr0al3dRnhj4C3xX4DmhDzp36SeAdIUToI46xAi4CtUQRLiQDXyptP3+5iLiYaMICrzOzhoa9EZmYdR/CoJFv8e7oEbyiukPrylb5jvviUjStJ86lXWfdmbBabU6dwQcf3gYHB5OcksoHi7+htosT3y6ah4GBAW+8PRmH7q9hW71mvrDPVV5C/7+Cb4VyLDCMWo1yKryGXfensbM1nk/4zKai0EctnSghRF8hhKMQwkkI0f9RYX9fLSAaWK0oynlFUVYoiqJTok5RlDGKovgpiuIXHR1djOZIUsnKzMxkwPA3mT7/c5as/YN54SZ5YQ/Qo9/LbL+VkG9kSFKmmuBsUzy8Guc7p4GBARqNhvdHj+DYof3ExMRQu3ZtmjT2Yu1XC/LCHuDnbz4neu8GooOuk5YQj61L/nILjjXqYGhhy/wvv9bDJ5BfaGjoU6kdfzngBjU9m+b97urRkMDQ23q/bkVTnDv8m0AkcAw4CpwQQiQWcow34AO0E0KcVhTlGyBJCPFxQfvLO3ypNP26dQcpwogXWzV66N3zkf17OP79PD70ylmTNylTzQz/DOau/r3AFazUajXT3xzGeNsEfjx/h9tZBsxZuRGPhgXX1snOzuatSe9SqVVvzmzbwAvvzsXEPGeWaFpiPLu+no2brRnrf/xe733eVwOvsvXodqpUrUznhp1xc3XT27V2HTiEUS0vTO7Pzs3Ozibp6hn6PaSuvaRLH+Pw65DTb3+ZnDo6FxVFuVDIYXeAO0KI0/d//wso26tySBWWk50NxpoMLC0tH7pPp2496fj2xyy4FF+ssK9ja86Szu40Ms9m/thhXPe/krffg+PPVSoVK5Z+QerpXVQxVdgxdxKZaSmPHfbp6emM/N8Erl0v/nKX125fo8cb3fDs7sn5G+eLdawQgq279hISGlbg62lpaTrfHDq1acWtM8dIjIslOTGBmz5H6NSq0PySiqk4d/jVgA5AJ6AxEAccF0IsKOS4Y8BbQogARVFmA5WEENMK2lfe4Uu51Go1N4NDqF+vbmk3pUDH9u9j5deL+WLNb0UK+1xCCOYdCyAwy4QPl68nMT6Or2dMYeDoibw8fGTeflqtFiEEsbGx9Bk+mkytQt2qDsUP+wlTqDlwHNc2r2The29T36Pos25Pnj3JbW6Trc7G09KTxg3zd1k9jEajYe2mbTStX5cmjfJ/m9m6cxeNGnhQu2bNvG0ZGRlcuOKP0Aq8GtYvVwuU6Js+HtpqgTPAfCHEtmI0pAk5wzKNgWByRvbEF7SvDHwpV2pqKsd8fOnVtXNpN+WxXDh7lu2zJvCJd/7CaHeT0/nsaADC0h5zY0M+b1WF1TcSseo1Qif0c8XHx7Nl+98MfXVwscO+9uAJWDk6o8nOxnf5vGKHfkREBIaGhjg6Ohb5GOnp00fgNwbaAx0BV+AGcEQIsfJJGvogGfhSebLttw0E/foVU5v/OyH9XnIG844F8F5bdybtvcqv/RpjaZIzMWpVYMJDQ784/hv2uR439B+06+ARUtMzGPh8DznLtQzRRx/+RXIWQVkNHCSna6fAh6+SJEG/V4dQe+gUvjx7B3h02AOMqmtD0u41bNu4Tuc8h/fsYumns4pcN+bAocMoVevqhD2AoUpF3ReHsXT5isd+T1FxCcQkJhW5LVLZUuTSCoqi+AEm5Iy/Pw50LMKwTEl65mRkZHDFz4fkqEgwMKCWVzNca9Z6rDvafq8OYRvwyYpFBETFs6hLfWZdTcOzlisWxvn/89MIUB4ou3B4zy58f1pISzsjlsyczrTPFhXajj7P9+bmrTD8j/xD7U7P522Pu3OLqD2/suKbL4rUdo1GgxAClUrF7TvhREbHMLT/C2i12nylIR5XWloa245uw8jAiP5d+le4ct1PW3H+rfUWQjQSQowVQqz7b9grilKy9V0lqRRcPH0Kn/XLqB13k862gk6WajJ8/mHXL8tISnzkKOSH6vfqEPrMXUanYeNYEGbI95t3MeDDxcy5GKdzp/xzQAL2fUbSd/BQ4N+wf7+RHc9VtaRl1DmWzJxepLvryePH0tA4naAjOat5xd25ReSutaz45osi1dZRq9X0fXUYDVp14OrVq4RHRBJ6NwKVSpVXLbQkhISGYFnfElFZEBMTU2LnlQpW5D78Qk+kKOeEEE805FL24Uul6drF82gvH6dh1fwPKLM1GvaGxNJ95P9KrBjZmZMn2Ll4BrMa27EiMBH7PiN5aWjOfdODYf+gw+HJ+Do1K9KdPsDXPyzn5O14zBLvFivs+w8ZToZtVTq/NZUtsybQp30LouIS+GbBpwAlFvpqtZo9x/dgrDKme/vupfpc4E5IMKaVKuHgVLnU2vC49DHTttBrluC5JOmpEkJw0+cIcffCOXLmHInJqTqvqwwNaeFoxuUzviV2zRZt2/HC+wt49cBtnbAH+PmLBUz0sM53zHNVLblz+hB37tzJ95pWq+XbhfNISPi3VNXk8WMZ3a3lY4V9t3HTURkZM2DOd2w+dJIMtyZ4tn0Oz3aduXr16mO+a11GRkb06dyHHh2K/xA4ISGBK+fPkZGRwfY9+/JKST8uU/NKGJvkX5axPCnJwJdPcaRn1u3bt4m+fJoW1tDW1pATp06SlpGps4+jtSXxIddK9Lot2rZj/SEfnbAHWLJ6I+9fSiZdrVvWYOnVeJ6fMIPq1XXLLmi1Wj6eMAbPwP0M69qWN1/swbqVK0hKSqJ71y5F/lbSf+iIvLDPDWCVkTGD5y/Hb9tGXL07MPy7Pxg25UNmzVvImxOnltoCKzY2Nng2bUZycjIBoeHExRc42rvIHCpXxso6/x/Z8kTe4UsSEBZ6Cy87M0yNVBipDGniaMHtyKh8+xnoYRHsgsLYpWpVZvy4Xif0l16Np+6QSfTq/5LOvrlh/zJhXI+MZ0xdKxZ4qFgz70OGtPXi6uVLRW5LUkoq1T2b57vbVhkZ41y3Ia5e3qiMTXhp7vf8feo8Rk268NY775XqqlqOjo5MGzOS6s/gYu9PW5ECX1EUA0VRCls88kQJtEeSSoVTZWfCkzPyfo9Oy8TSPP9MT43h01tM5MHQ//xSbKFh7xMaRXVrM/rWq4JTJRM2DPTGxQQWjnolL/Q1Gs0jH44e3PYXgTvWc/3YPp3th1d/g2ONOtRtkzMRTmVswksff8nlA9sx9+6eL/Tj4uJIT08HckbiHPE5otPVJJWOIgW+EEILTChkn0e+Lkllmbu7O9E21dl3M4IDQZFkWjni4qj7wDQyPhFDBxdO+51+yFlKXm7ot504O1/YA2z783fqxVzjdFhO2Pep++/Ye6dKJnzWpQEWZLFw1CtcvniBGWNG8MnQfgReK7hrysjIiCM7t+qE/uFV35CdlZVvhSlDI2NMLawxsbCicq9heaF/+/Zthk2aRotuL/Dr73+y79Q+RD3BXt+9JfjJSI+jOF06+xRFeU9RlOqKotjl/uitZZL0FCmKQqeXX8ehriddunShZaOGOq9nqbM5GBbPt1t+5ptd37D7wO6n1jZHJycat2xV4Gv9XhnMdft6XIhMwt0u/zcSW1MjVAYGzG9fk0UjB9BNHcrSVg78NG1skUJ/0ydvkxR4HgMDAwJPHcrbRwjBgZ8+x6NDd5zdG2BTtQbRqZlcuHCR/300lzYT5tB31lIW/bQG/4s3CfUNxcW2/NTvf1YVJ/BHAW+TUxr57P0fOYaygjmycxsJT/hwrKxyb+iJiVcHDgZHEhmfiBCCbI2GS7cj2Xwjmj+unabTgk50mtGJjWc3PrXQP/jneg6s/k6nqmYuAwMDPvt+BTbNOrLkVBABMcl5r6k1Wt7f58+kVrWwNzfGzEDg5WSBysCAhc1sCw39Y7u28+e3i9i76Tcs02M5uX4Z14/tRwjBvmULqdeuK9U9m6HVavH9aQHvDB3InG+X02r8LIxMTLFydKbP9IX8tvMQqgRz2rdon3f+zMxMOVu3FBSntELNAn5q6bNxUtmjzsxEk13yDy7LigZNm9Np5AQiXZtyONmIk5mWGDTtwp9XjvPcwucwtcwZttd2atunFvrOtepiWa3mQ2ehGhgYMH/ZKhy8O7Hg+E38o5Lywv7tljWpamnGpN2XmPOcB84WOe3PDf0f3h1NeAFDPCGn793NzQ0LCwvWfPslf69ZzqVNK1g/9XVERAjWlV3ywv694a/w9S8b8sI+V27oL/xxNX9t3Q5AVFQUA0aOoUvflzhw+EgJf1rSoxSntII5MBVwFUKMURTFHagnhNiht9ZJZU63lwp7dv/sU6lUeHm3BO+WALz4+ot0W9otL+xztZ3alh+m/kD9OvWpUaOG3trTuHW7QvfJDf2v583l28vnuXvIj2417KhqacabB4LoWqsaLpZmOsfEp6tRm1pibWOT73xbNqzjlwUfY1+7Piu3/IOFhQXu7u5s27CGA8dOMqB3D8ZMnU6qMGTe5HE0bFAfsx9/JjEiHIcatXXOFR1yA4eadTl84hQd27bmrWkfobZ1oc5z/VmwdjMAJiYm2NpY07B+/XxtkUpOcapl/k5ON85wIYSnoihmwCkhRJOSaoycaSuVRTv27GDTlU20fqe1zvYw3zCy9mWx+JPFZapyZHZ2NsHBwXw4diRGCL5Y/xc7//gVhwt7GFAzZz3e6NRMZgcJFq75I9+CL1s2rOPmui+Z1sqNb32DOWdUhVVbd6EoCqcP7iXhViANu7yAfWVnoqKi8v7YqdVqBrz+Bh6vTswL/SDfY9w8fQR3KxVzpr/L2A8+Ib2SAzWbtaZW83YIIdj7zWwUdSaW5makRd+ldQtvPp05o0Q/k6ysrBItCVHW6GOmbW0hxGJADSCESEeOvZcqgD49+zDQcyA+3/jkbXuSsBdCkJiYmLfAeUlTqVTUrVuXvw6d5KuNW7gdEUmnPi8R5dWDLSFJRQ57gIkta9FMfY9R/XsjhMB3/y7+WLeGK36nMTMz0/lmY2RkxJZ1q7n+27fEhAZx8/TRvLCfP/ODfGEPOQ/Le7wzGyM7Z25HRNFw2DscvRHOjNmfltjnodFoOH7wQImd71lWnMDPun9XLwAURakNZD76EEkqHx4M/Se9s99+YDtTFk1h7da1entwmZWVxcZt/7D/Wiix5k5cjMtE5erBrTrtmXmTAsN+5+Y/ufFA2OfKDf1BXdoRefE0i1o4sm39apKTk/mv3NC/8ecP+P2xAncrFcu+WISRkRGZqSmkxcfmhX0uRVFoP3QsWempONdpQK93ZnEyJLLEQt/Q0JAuvXqXyLly6euPtb4VJ/BnAbuB6oqi/AocAN4v7CBFUW4pinJZUZQL90ssS9IzKTf0laPKY4e9Vqtl+frlWHWwYt3mdQWGZknYdegodg2bU8PDE0sbW5xd3XBv1xUrj2Ys27SjwHV7LaysuZuUlu+PkBCCiOQMVHHhfOrthIO5CZ/WNeSDEYMeGvrbfl3DlpXfs+yLRRgaGmJtbc3Gn76HxEhObvxZZ391Rjp/L/mIvtMXAjl/AHq9Mwuf0JgSvdMvSRf9zpCSklLazSi2YlXLVBTFHmhNTleOjxCi0HqmiqLcAryLsq/sw5fKM61Wy/gPxlP5tcq4NHIhITyBS0susWLJCszMzAo/QRGp1WrW7zpEnRb5H/ZG3QmjgZXhQ9cK/mfbVvYuns5X3eqjKApCCGYevEZwUgYb+jfV+SMXk5bJrJsFdw09TFxcHC8OewN7z9a0fW006ox0/vxkAn2mzcu3YEtKfAy/vTeSS8cPYm5u/pAz/qs0+unPHjtMmP8FXnxrQqnW8tdXtcxOQFegMzkLmkuSVAS5Ye88xBmXRjkTkGyq2uD1vhdvTXsrrwxBScjIyMDQrOCANLeyJj4x6aHHPt+vPz3eX8SU/dcQQjD3SACH76XxUcd6+b7ROJibUIdkLvqdKfBcNwMD+HON7gqodnZ2/L1+NVHnj3N0xRfsWfAu1g6OXDuyR2e/lPgYtn02ha8+m1WksF+xdiUbj21kz5E9REdHF7p/SbF1rIx1ZZcSWxBG34rcSkVRfgDGAZeBK8BYRVG+L8KhAtirKMpZRVHGPF4zJenZ9tMvP2HUxogqnlV0ttu42FD7rdrMnD+zxK5VqVIlNKkFh3r8vXBcq1Yp8LVcz3XvgdJ+IB3WnsI3qxKDPl7CikRb/GN1yw+vCEjA7eUxtO/cJd85bgYG8MPUMWTvW8+qpV/qvGZnZ8fxXduY+kpPfl/2FYOea01yxG2OrsuJk9ywn//eJF58vvC+9/lffs3m04Fs33KAlWs3cCei4HkF+lDLoz5dBgx6ZgK/OMMy/QFPcf8ARVEMgMtCiIaFHOcihLirKIoTsA+YKIQ4+sDrY4AxAK6urs1DQ+WqiVL5o1arGTNtDHX+VweH2g5521PjUvGZ7cOKhSuwsrIqsesdPXWaGCMbHKv+W0EyIy2NqEs+DB3w4iOP3X3wMKqajchWZ2FoqEJlbEzspVP4bv6VEeaRNLSvxIqABOxffIMBQ4bnOz437Bc1tcHI0IC/gpNI8n6BUZOmAhBw9Sou1avrdAP99Ms6Tpzy4S7mRNy4UqywDzWtgmM9L3Z9PZuWA14H/6N8v2RhiYewRqMhOzsbExOTEj1vSShql05xAn8zMCV3aUNFUWoAC4UQrxWjUbOBFCHE5wW9LvvwpfLsv6Gvr7CHnAetx3x8CYqMw8jSBnVaKtaGWl7o2qnQwNq+Zz82jVrrdOFEXThF/x6dmTFmJJUibuA1dHyRwj5Xbuh7Nm/JlvnTicEEU3tnFi9fqfP8YsUva6hetSo9u3cr9D0+GPYHli+h1zufYGJuwd3rl1D77S7x0L9++RJB167wwqAhJXbOkqKPwD8CtAByl/xpAZwC0gCEEH0LOKYSYCCESL7/v/cBc4UQBc5Hl4EvlXe5oV9lcBVurrupl7B/kEajITk5GTMzM0xMTNBqtWRkZDyyXzw07DaH/IOp3SQnP8Ku+9PY2RrP+vXQaDRcuXSRxk0LXs30te4d+aWVDSYqw3yvTTkSjMbAmG/aVyU2PYsP9l/FoEYDvlj7O1t++5Who0ZjaJj/uIL8/MtaTsULXLxa6oR9rnsBl8k6s5vvlyx4ZrpbnoQ+Ar/To14XQuQriqEoSi1gy/1fVcAGIcS8h51DBr5UEajVauYunsuIwSNQp6XmdJ2ojLC2d6Cys7NeR3ukp6cTGX4Htzruj9zv+o2bXAgIAkXBw9WFJo08i3T+a1cus3rG2yxoaoehwb/fEDYHxfHH1Xts7NMg75tDTFom0/f7czNJzURvV3bEGfHO3EU0adWm0CGv4eHh/O+juUSnZ9Np5CRsnKvm2+fi3xsY1LgmA/o9ugurPCjxwC/CBU8JIdo8yTlk4EvlmVqtxv+cHzE3rqDKSMXRRMHe3ASVoQEajZaEjCwi07WoTcywqFYbr9btSnS45tPy39DfGpLA6gthbO3fSCfIs7Vapuy+zDjvmjR0suJKdArLg9N5ZeL73AgIwMrOjldGvPnQ64SHh/PWtI+Iy4KeEz7C3No277W7l/0wvuHDkrmzylTZC30pjcA/L4Ro+iTnkIEvlUdarZYzRw6SFuxPQzsznGwK78JJTEnjUlQS2so1aNuzT5HXpC0rckO/rZ2K8AZdCA0MYJjJXbycct57tlbL9H3+vNWsBvUd//08/KNTmHYshHHNa5CQJTDq8irBgQEMHfs2brXyF+fNDf3YTC29Jn6MubVthQt7KJ3APyeEKLhjr4hk4EvlTUxUFL47/8Lb1ggn66JNTnpQUlo6J+4m0bBrH1xr1S78gBIihCApKQkrK6vHDs1rVy5z5thhhv9vIhqNhvdHD2eEaQReTlYsOXGDNtXtaO9qr3PMsjMhOFuaMMAjZ67CD+duk5qRyR1jO6YsXY1brVpotVqdfvnw8HDGvPMuwsiEqu16Yx15vUKFPcjAl6RSd+dWCIF7N9OpVhUMDR//waEQgjOhEVg06UiDps1LsIUP53NgD8otf4RbQ1p37Vki53ww9A8GReETHs/3zzfG3jxnduyyMyFUtTKlbz3deQJrL4ZhqCj4ZlVi+OzP+Xbme1g7VaFj77706PNi3vDOhIQE1v32BxPGjq5QYQ/6m2n7yGuW4Lkk6ZkWER7OzX1b6FzH5YnCHnJqy7R0q0LGpeME3F+MXN9ybwSf5IZQo9HorNJlaGjI4p/XskHryrF0M1q7OjF6z3Vi07JIycrmxO1YnTV5c73mWY3tgREsaWrD4jcH0c4oicp3L3N86Sf0aVqP8PBwAGxsbJg4bozewj4hIYGoqCi9nPtpKc4onUpAuhBCqyhKXcAD2CWEUN9/3VMIceVJGiPv8KXyQK1Ws/+XH+hV26nEw+dw0F2avfImVtbWJXre/3rSLp0rfr5EnDuGqaFCmoUjXV8eojPkMisri6Xz5tCrlgPL1m5ggoc1n527R1UzFQs71MTg/jVzV+6a0LIWte0qseHybQJjU5j9XH2EECw4HsiB20msPXSaqlWrcvXKFep6eJT4SKe4uDjenPoBGhS+m/sRrq6uJXr+J6WPYZlnyamfYwv4kLOebZoQYuiTNPRBMvCl8uDw35tpZpCIlXnJj7BRZ2dzIDKLnkPfKLPdFqmpqZzduJyOtXP64WOTUgiyqU3LTp119hNCcOXsGYLP+bB9y2b6vTQQtbkV539fydymdmi0Qifs//QP52p0ErOeq69zjtzQf2P6LK5vWkm6oxuLVq4vsdDPDfvGoz7A0NgYv+Wf8e2cD8tU6Osj8M8JIZopijIRMBNCLC6JkTkPkoEvPetiY2II2r6WljVd9HaNoMhYNI06Ubdh0cbGP47ft/6OjZUNPbsUv/8+OjqayN2/4lktp3tGCMGRFGPcmjTH55oP1eyq6Sxo/iAhBBfO+LLps2nciY6lY1UrRnk6cycxnTe3n2PP6/krgAohePlPX9LUGja85E1MRjY/JtjmhX5kZCQqlQp7e/sCrvhoD4a9qWXOaCJ1Zka+0E9KSsLH148e3fLXFXoa9NGHryiK0gYYCuy8v6306oFKUhl0+cQRmlRz0us1ajnZEXrBt/AdH9O6P9ZxMOYgG89uZPjbw/n8hwIroTyUra0toZmGZKlzFrs/c+setTyb4BfoR+2utQlKCCrw2cDps+dZsWUX52/dZcDMxcxav42UJj3YGBDDrIAMTG3smXP4ms4xQgiWnLzJyMauWBmrMDRQcLc1Z5xNPNPfHMbNG4GMe/45BrVqyKThrxX7mcTr49/RCXsAIxNTvMfOZOz0T0hNTSUpKYmRk95j5UFfftnwW7HO/7QVJ/AnAzOALUII//uzaA/pp1mS9OzJzs5GxNzB2Ei/90GKomCTlUhCQkKJn3vdH+s4lnCMZiOb0WZKG5KrJHM64TSLv1tc5HOoVCqee20UJ9KMORSrxaFdb1xr1cajugcBBwOobFK5wO6oG3ej8GjTCXuPxhiaWVCzdh0mzZyD6vm3+HLjNr7dtItLaQZ5oZ8b9vUdLFh/6Q7LX2yClUnOfAV3W3P6GNxlfJ/OvOJWiX1DW5N6+SQ9vD1pX9uFgICAIr2XFo29iAq4mG97bEgAdaq7kJ2dzchJ79FwxHs0feUtDt2KLdOhX+xhmYqiVBJCpBa+Z/HJLh3pWXbn9m3Sjm6hrot+7/AB4pJSCHNuSJNWOZPbhRCEhQRz52YgNk6V8WjUuMh1aXLlhn3zUbpDP/d/tR/U0MKqBe9PKHSRu2KLj4/n7GV/rlwPwNKlFtlpSQzu0QkbG5t8+4bdusX4l3rT3ApUCjRxtmbpudt8170+9Rz+nedwKyGVcTsvMdyrGkMaVQdAKwSjt5/HAIhSQ6OuL2BjacG7ny565POQ2QuWEOVQB1fvnCVAIq5fRHP+AJ99NJ033plGwxHvUcnGLm//a7t+p7ObPSOHvFpCn1DhSrxLR1GUNoqiXAWu3f+98f0a+ZIkAXeDb1DFpviTqx6HrWUl4u/eBnKGP+79bS0ZPv/Qglhsg3zZvfI7khITi3y+lJQU1mxfky/sAbpO7krQ2SDuVr9brDv9orhw+QpbTpyHah7U7/wCyfExdPDyKDDsAVzd3Fj65w4s2vdl9+1EVtxM5peDviyNMCUiJQOAhIwsRv99USfsAQwUhZ/7NkUDVDczJPTQ37jf8mHhB+8ihOBOWBixsbH5rjl7xjScYm4S5ncsL+xnTpnAwCGv03D4uzphD1C/92C2nr7M2XPnSu6DKiHF6dL5GugJxAIIIS4CHfXRKEl6FqXGRGKph5E5BVEUBTJy1lS95HuaJiYZ1KviiLGRChc7G3rWcsB3z/Yin8/CwoIpw6dwaJFuL60Qgr/n/E2vab2o3bk2h08fLrGF17OzszkfdBv35q0wMTPD3MKSZl1743ftZoHXyM7OZu/v60g5sYPJnRpx4LuFfPK/N7l26ggLV2/k01uGRKRk8GNgMqYOzqg1BbfTxNCA2PRM5nVpwL7AOzQI9+P9saP4fPwwPh45iDGDB7J/9y6dY2bPmEbluCAMrhxl6aJ5WFrb8Pao4Vz5a0W+tkYHX6eyQRZNmzQpkc+pJBVrRogQ4vZ/NmlKsC2S9ExThLWK7LEAACAASURBVPbpXk+bc734sBtUttUdl68yNMQgKf/d6qO80OMFhjQbwt55e4F/w75xn8ZUaVCFwx8eZtWSVSU2HDQuLg4Tm5zFYDTZGqKio0hPz0BrbIZarc63/4ld22lVKRuv6pUxUqkwNTGmeU0XmhqlcenkUZas/YO5t01pPXYGW0+eY3u8ijUXwvKO1wrB2zsvohXwQft6uNqYU8euEmnpaSSfP8KSprYs8jQj9tIp1n34Nnv/+Ufn+rOmv8eX8+agKArm5uYMGPgyM0a9iu+KxXmhHx18nZTj21j2xaIyWZa5OC26rShKW0AoimKsKMp73O/ekSSp9AjFoMA7YmFQvD58gL69+zKy1UgOLTzE75N+x7OXZ17Yfz/ze5yd88+EfVxWVlZkpiSCgCvB/iSZJHMjMpCkuJh8xeKysrIgKgzrSvm/QdlbWZBx5yYmJib8v737Do+qSh84/j3JpPdGeiBEmvSEDtJBQBAERFQERBfL6rqKvWJZF2UFC/5QFEGxsC5IEZReBCIdQhIgISG9kEJIbzNzfn/MJCSkkEBCBjmf58kzM3fu3PvOZXjnzrnnnPf//ruOoXeOxdzcnJ93hVYm/arJ/snegXT3cuKLo3HYWZhzJPUSn43pioW5GQ5WFqycFIydueSH159i22+/EX/+PE/NmEZeXh5lZWXVmn369AqpTPqZsWdMOtlD4xL+48DfAV8gGehhfKwoCiA1Fk3W3NGg/ZkbegO16daLs6lZ1Z7LLSzGwvPaBgZNGDOBR+94lKfHPk3M/2KuO9nHxcUxdvpYjp88Xu3M3draGm87Cy4kJyCsBTZ2NhQXZWFrVlLjV8SlS5dwt6z7l4WLRlJQUFBtWUXS35RryfDvQrlQrKWvnzPdvZz4vyPncbG24FDKJT4Y2bladS4HKws+GNkZqdPy7atP8t6cabzqmceDQ3rx6ISRRJ6NrPbvXJH0dUe3mHSyhyacPK0pqF46ys3s5KE/8U+LwO0aZsVsLJ1Oz/5ia4ZMmAxgmH455hQ+NmZcLNWTb9+KofdMu+7RpklJSVhZWdGq1bX1PIqLi+P5xc8z7P1h7HhzB+lR6cy5bw5zZ84FDM1GR0+cZP3uHWity3HSaHjq/sdrVAErKCgg4uev6BdYewH2fefT6DPjyTrLN6akpJCXk8PLf3uIVuW5pGs1rB7XngX7zzE6yJM7WlcflPVrVBph6XlkFpeycFQXLM3NyCoq5bWdpyl08SU/Lw+9MOPLdb/j5OSEnZ3dNR2fptJkI22FEC8aR9V+BtRYWUr5jwYEY45hKoYUKeX4utZTCV+5mWVkZHBhy4909W+6Zo+6pGXnkNOuP7d3v3xhsLS0lMzMTBwdHZu1bGJDVST74QuGo7HUoNfr2fDGBhwc7Oim6cwbL7+DXq8nOTkZf39/cnNzsbOzq3Pu/20/fMMIT+sak9GVa7XsydYzanrNGrtX0ul0HDx4kLZt2/Le3x7ATOqx9mnD3bp47ggw9LapSPZZxaV8aEz2Fc5m5fHCtkh+nNKLvQnZvLcvGmtLS0ZOfYDXP/joOo7W9Wlowm/I139FO/31ZOJnjNtp+U+hojQTDw8PwrQaut6AfZ27VErv9h2qLbOyssLPz+8G7P3qrkz2AGZmZkx8dyIb39xImE04n3/zOaejT7PvxD66BHZh6p1TuXtCjdLYlXrdeTfb137HHf6u2NlYo9VquZiXx6HMEobcX3dlrKrMzc0ZONAwPcP8FT+j02rx9PLi7WefgsQILhQUk1lYhh7JjG7+1ZJ9ZmEpnx6K48cpvXCwsiD2YiGvD2rPyCAP5v76P94qL+ftRZ9ex1FrfldtbJJS/mq8/VZK+S2GGrW/VHlcLyGEH3AX8PX1BqsopkwIgUPr9uQVFjXrfrQ6HeXOrUy6/OGx8GO4dXOrTPYVzMzMCBoYhI2XPQdLDnLg9AHu/fRe/B7w480v32TghIFotdpat+nq7s4dMx5jT6EVi3cfYNHBA6zISiWzjTM7j+wiPz+/UTF6eHjg5e2NEIK3Fi9hn3tPlscWojEXlGHGJ4mC8Iw8ALKLynhrz1k+GHk7DlYWfHIwlo7u9ozv4IW1xpxlE3oQt3M9bz1XvcHj/PnzN/S6ztU0ZuBVLyFEOHAKiBBChAkhGlKN4WPgReDG9llTlBbQrf8gjqU1/ZQHVZ1KyaTzgCHNtn0pJSlJSUQcP0rkyeNcSE9v9Dam3j2VPtZ9OL6q+uCjyK2RZMZk0u+hfpzZc4YpH06hVVArggYEcff8u7ENsq2W9IuLi6sl8vyCfDKdShn4xkMMf/URRjw6iW6juuE9yJs1e9fUuHDbUEIIXv3wY347GsHZVt3o8+QbrNy8g1VlPpzKyKNMp6dUq8PS3IzPD5+no7s9d97mWfn6qkn/Xy/NA2DhW68ye3g/7mjvX+uArpbQmNkyTwF/l1LuMz4eBPyflLJbPa8ZD4yTUj4phBgKPH9lG74QYi4wFyAgICAkISHhmt6IopiK46H78UiNwN+t9tGi1yO3sJiTuDBk/KQm37aUkpMHQ8mKCsfXvBQPexuklKQXlHABG7y7BNO5Z0ij+uF//f3XHC47TMjMECK2RJBxLoMhjw/hm1nfMPGdibS6rfrF4ISjCRz84SBFsUVs/Wkrj7/6OGX6Mpa9tww3Nzf+u/W/BA4PrLUnTHlZOdkHsxk/rM7LhI2m0+l45bHZeKaEE5edD0gCnW0J9nZmWKBHtXVLtTpe2B5Jhpk9tw8ewZH1qwn2cuS5/rcxfeMpSjCndVA73li0hKB27ZssRmjaNvwK+RXJHkBKuV8IcbXfUAOBu4UQ4wBrwFEI8b2UckaV7SwDloHhom0j4lEUk9Sz/0C2fH+WVmXlWFk2XfFxvV7PgbQ8Rs2ecfWVr2HbO9eu5naRT8/W1b+oWhkHdZ0/d5g/UpMZfNfEBif9R2c8Ct/DL8/9wsWki8z67yyOrjxKaV4pDq1q9mZy9HZEr9Mz5LUh9J/Yn4d/eBgLGwsee/0x/vPif9A76uvs9mhhaUGOLqdGzdvrYW5uzr+/XMmubVvJ2bSOmDORXMhIp0ynR6uXjAoyfGFVJHvh6IZPm06VyX7+0I4IIRji40B7V3sszPP4+8RRzH1rAbK0hCkzH26SOBuqIb10KurUPgTYAj9h6K1zH5AjpXytQTuq4wy/KtVLR/mrKCoqYvcPXzOqtWuTzJ6p1+vZEZNGyOSZuHl4XP0FjbT/919pX5p+1ULrSdmXuNCqA70GD6t3vSvFxsZSUFTAvPfnMXn0ZGwtbfn0f58y85uZ2DgarkXkpOSw9cOtjHt9HN/N+Y6ZX8/E0dPQz6M4r5jdL+1m8pzJdO7TuXK78VHxtOnQpvJx9MFoJodMxtraulHxVdAbRy/X9oUhpSQuPo5zMVF8+s/HybiUxztDOzI80KMy2dt2CCFi+4Zqyf7jgzF0cneobALaGnOBhX/GMLZLW7zumsmDc5+8plirasoz/Cv7Gr1V5b46I1eUWtja2jL0gUfYvnoFgzztah0h2lAlZWXsic8mZNKDzZLsS0pK0KfE0iqo7u6kRSWl5BcV08rBjuhz4egGDm7UbJxBQUEAbF65uVpf+U/nGJJ+SV4JWxduZdL7k1h27zJmr5hdmewBbBxtGPbBMFb+YyXvdn0Xaxtrln+0nKSsJEK6hDDhwQnodDp0xTosLS2v4SjA/iP7ib0UCwL8bf0ZPqB6MRMhBP5+/vh4+9Bn/0mSEhJ44eHpLD4UR8c2/jz07sfk5uZxYNMaJrT3qjXZA9x5mycC+OzweYaJ7/gBmiTpN8RVE76UsnFf5XVvZw+wpym2pSg3Azs7O0bPfIzQrZtxTIynh3/t88DX51x6NvHmTgx+6DFsbW2bJc5Th0Lp5ln7mX1pWTn7z+zD2iYdZycdZ2MtKMj1IOL4Ubr37tvofVVN9rMfnA3AoumLKCkuYc6qOWyav4kA1wDykvKqJXyAgvQCrIU15hpzln+0HNuetkwYNoFjPx5j6btLiTwVia20xUN6MGbUmEbFlZGRQTLJdB5u+PUQHxlPQmICrQNaV1vPwsICCwsLrK2tcXFxYeuJs0SdPUt5cTFdehqK/2mXrOC5px5m4chOHE/L5YlegTX2N6SNO9+HJxMancg9DmtuWNJvVEOXEOIuIcSLQog3K/6aKzBF+SuwsLBgyPhJuA++m+1pRRxNSKe0rObEYFXpdHrCky6wLfES+i53MGrajGZL9gCFF1Jwtq99pOjeiN30C85gYLAlnYNsGNJbw4CQDEJ3NU2Rj9kPzib0l1A2f7OZVQ+tYmKnifz202/kb84n+Why5XqZ0ZnEfx3PVwu+4uMXPsa2hy3thxkufDq3cSY5PxnHQEd6P9+blz99mdVrGxffpdxL2HvYVz529HAkJy+nQa/t0LFjZbIHuHP8eF5bsoIXdpzhvs4+vLg9klLt5XkmS7U6XtoRyW2udszp2ZoHg5zY+9NysrKyatt8k2pw46IQ4gsMbfjDMPSpnwo0X501RfkL8Q9si39gWy5mZ3P40AHK07OgqABbocPC3AydXlKoA2ljj5m9E+2HT6arn//VN9wU6pjlMys3F3f3C9hd0d/fw8UCG00cZWVl19x8UpW9vT3t2rUjcl9k5bLF7yzm2TefJZlkrBytiP86ni8+/ILFXyzG/y5/2g1vB0BsaCxndp5BIhkwewDenbx5+LuHWTBrAQDTpzSsCIm/nz8Hdh3A3dsdIQQpJ1PoP6j/VV+Xn5fH0V1bkDodXQcNw8PT0Cx25/jxIFYw/4nZdHR3YPrao6yeYmhif2lHJK42lvTycWZcOy++jrrEnXOext3dvVHH7Vo0qlumlLJblVt7DAOwRjdVMOqirXIrkVJSXFyMVqvF3NwcGxubFpl4a9eaHxnmKmo0N52Oj8PV6wBe7tUvgOqlnq1ntPQatxyP67imoNfrycnJQavVYm9vX2M+Gikl8+bPI78wn6ULlqLRaDh28hgfrP6AYe8MI+FIApHbIiktKK1M9hVK8ktYOWslL816qcFJPycnh/0n9hu+PLoNuGoC1ul0bFm+hNGBbpibmbEjJo2BMx6v9j7Kyso4Fx1NxImjrP73azhbaXCzs2JogBvj2xuSvcu4WUx5aHbDD1wtmqNbZrHxtkgI4YOhEErNxilFURqkYl71lta6azDnT+wkyLP6BGIuDo5kXZJ4XZH3MvKKwOY27O3tuRalpaWEHgslpSAFKw8rzCzMKIstwyzfjO5tu9OxXUfAcHwWvb2o2mtDeoTwEi/xwZsf4DfKj5zkHNoPbl8t2QNYO1gz9aOpvPvYu/QL6UebNm2qPa/T6dh3YB9DBw+9/H5dXJgwfAKJ8XE4OVWvL1Cb3NxcfK0kFsYJ6jo6WZGemlKtj72lpSWdu3Shc5cudOrWgx0b1mJj50Do3k2kRV3CtQmSfWM0JuFvEkI4Ax8Cx4zL1HQJinKTa9u+A9v276CtlNXO8r1cXTl53JkObYqx0Bh+eUgkF4rByrHXNU3tUFhYyJpda2g9qDUdHTtWe05Kyemo06SGptboIVNVZdJf/QHdJ3Rn/9f7adWuFYF9Lp9/5mfms+mdTQztPZTWratfeNXpdDzx0hMUeRURdjaMZ+Y+U+35zau+YewDs2lj7FlUF3t7ey6U6pHG45aQX0pXj7pnFe3WvQfdjJPdnRo6guT4WMZNmVbvPppaY5p0bIAngDswdMfcByyVUpY0VTCqSUdRWkb8uWjS922uMf1wflER+8/sxN/3Eq7OkkNRRWjd72TitHmNbr+XUvLjbz/SdnhbLOoZkJYam4pviS8h3eqfueXYyWO8tfAtpt01jU9+/oRRL44isE8g+Zn5rH1xLcE+wSxZsKTal1hFsveb7YdnR09Orz9N24tteWbuM0gp2b5zO4MGDGrwL6/UpEQi/9iO0OtpEzKQ226/vWEHo4k12fTIVTb4M5APfG9cdD/gLKVssq8olfAVpeXEnj1N3B9bCPF2wuWKXjsRcYkcTM6k7/jpdA1uyBRaNcUnxHOi8AT+Ha5+MTpqRxQPjH6gwd1YN2/bzLx35zH82eGcWHei/mQ/yw/PTpf7xZ9ef5rA7ECSUpLYdXIXxbnFtPNpx+L3FnNb0G2Nf6MtoDkSfpiUsvvVll0PlfAVpWWVlpZy6lAouXFRmGtLAdBaWOPeritdevWuc676hli3Yx2+Q3wbdGE6KSqJYPvgGv3g61NUVMSLb72Ila0V/5n/nxpfFs+98RyOkx3x7lr9V4yUkhUzVoAGpiyYgsZKw4rZK0DCiJ4jWPj2QsrKyuoscpKRmUFSahLB3YKbrN5vYzVHwl8JfCGlPGh83BeYJaVsstECKuEryl/Xzzt/pu3Qtg1aNy8nD/ske/r07NNk+z9z9gzzPpnH+MXjMdcYRglLKVn36joupVxiygdTcPI2XKwtvFjIhjc3cCnlEpoiDa3btWb23bPx8fShV0j1vPr9b99jHWBNV6uudGjXocZ+b4SGJvyrftUKIcKNM2X2BUKFEPFCiDjgT2Dw9YeqKIpSnV6vx/wairDXp1PHTozrN47fXv0NnXEg1NaFW7mYeLFasgewc7Vj4jsTcfJxQmuvJTk/maV7lzLnrTnc1uc2MjIyLm/XvxNmaWYE+F1bDeEbqSG9dJpurlFFUW5Ztma2lJeV13vBtkJ2UjbdA5qstbhSj049sOtgx9pX1zL42cHknc6jIKOAvAt51RI+GM7yLW0sGfjwQOIOxTHp3UmUl5Tz83M/M2DCAEJ/DaVVq1a42LnQc0RPky5eXqEhFa8S6vu7EUEqinLz69ulL4mRiVddT0qJPkt/TYO6lq1aVm/lq749+2KZbcm4sePY+85eZj0xi5efeJm1z60l6WRS5XoZMRns/WIvHUd2JOVUCpPeNdQfsLC2YNqiafh092HAhAG8/9H7THxyIp2HdCYnp2FTMbSkBrfh3wiqDV9R/trWbV+HU7ATjs51l7eOORpDb8/eBLWpvx98BSklOTk55GRnk3khHVc3d2wdHPD09Kz1IrNer+dc7DnSs9NpF9AOHx8fEhMTuXPGnUxZNAVLW0v+WPYHI/4xgl/f/pVZy2fV2EZ5STnLH1pOfmY+vab1os/0Pqx8cCXz5szjVNQpFr658Iae8Tf5RdsbQSV8RTEtOp2ON1+eyeixD9Cr79A6e6o0lFarZf2O9VgEWuAT5FOtV0tJcQlxR+Po7tmdbp3qLKQHGHrknDp4gKL0JERxPi4aiaW2mNzsJNy92iLNLbhQoqfcwgbsnGjfawC+AQH19qJJTExkzP1jKNWXMuLZEZTklXDilxMMenQQPe7uUW3dbYu24dnOkwPfHGDksyNpP7g9h1cfJjM2kx539eDi2ot8+q9Pb1jSVwlfUZTrotPpeGXevcwe+SsLV9pTUGzJ08+vZPCwsde1XSklMedjOBl7khKzEqSQmOnM8LD2oF/3fvVOa3AxK4vju7dilZdBd08nHO0uD5CKPXeU1p55JGe1ok3bLlXeh56o9CyStRZ4dwmhS0jvehP/H/v+4Nu13xIeHY69tT2lDqV0m9itMulXJPs/v/uT3vf1JmRqCKc2neJi0kWGPjEUgJSTKZVJPyY2hg8//5DP/v1ZsxWeVwlfUZRrVjXZnzijRa+HGXfD2194MHzSt9ed9BtLSsnRfXsoPXeSfq1boaml+EphYQEZ6bH4+HXAyqr2ileJWTmcLrVkwISpONbxxZKXl8fWg1vJ1+VjYWbB9k3bORVxigFPDyDtbBrenbwJXRlK0MAgRj83ukayr5AalkrsV7EUWxcT8nQIkYsjue+u+0jNSOXxWY9f9zGpqsm6ZSqKcmu5MtlLCQ9NBCHgrccz2bV+Fn/s/v2GxVNcXMzv332FX9Y5BrX1rjXZA9jZ2RMY1L3OZA8Q4O7CCE8rjv9vOVHhYTWel1Ky4Y8N+A/2p9vobnQa2YkpT03h2yXfojmq4cS6E4QuD2Vyv8lE/h5JUlgSJzecpPf03jW2ZW5rTkxeDCP+PQK31m50fb4r85fOJ1wTzifLPrn2A3IdmjXhCyGshRCHhRBhQohIIcTbzbk/RVGuX3TUWSzK/yQyxpDsZ9x9+bmKpH/g98c4FLqr2WMpLCxk1w9fM9zLGm+Xyxd68wuLOBp5ljPnE2hsK4WFRsPQIB+Kju8h4lj1kh4ZGRnYBNhgrjGv3K7vbb5Ep0Xz6fufcuaPM6x8byVvvvImKxasYM3za+g/qz8b3thAYU5h5XYunLvAlve3MHP5TMwtDF9QLn4uTPtsGqdDTxNtF90iSb+5z/BLgeHG6Rd6AGOEEP2aeZ+KolyHTrd3ZuCYRewPc+JSLT0cpYSCYgts7eruadMUysrK2LN6JSP9nbGuMlFbfmER+w8coL1ZIbY5Kew9fKyerdStZ4AnZRF/ci4yonJZxcyXu7fsJnR3aI3X2NjY0KOHoS2/f9/+rFiwgl9e+IXCC4XseH4HhTmFSClZ/8J6xrw0pjLZV3DxdcG3qy9mTmacdz1/w5N+syZ8aVBgfGhh/DOdiwaKotRq3IT7uXPyUqKTnFjyw+Xlej28sbQt0+b8RNfuV20yvi4HftvIYC9brK4YqBUVn8hAf1ccbaxo7eaILLjU6LP8CsEBniSF7qCw0HB27unpSWFCIV4+Xvj4+QCQHp9OUKvau4j279ufswfOsvHzjfz4yY/8+daf7H5nNwueW0Dc13FkxmZWWz/s1zCkTtJlTBdun3Q7vx/+nezs7GuK/Vo0exu+EMJcCHESyAC2SykPXfH8XCHEUSHE0czMzNo3oijKDTduwv106/cix09b8e5Ss2rJvnsTznFTm7hz0bjnp+BgW7NXi52NDTlFpZWPSyXXNWnZwAA3DmxcW3l2P2HgBKwyrShKLeLMzjOUhheiz8sn80J6ra+3tLTEx8cHZ2dnvnr/K1659xVGDx/Nlx9+SezS2Mqkf3LjSXJTcxn8mGFGmoOfHOSpe5/Czc2t1u02hxvWS8dYPGUd8LSUMqK2dVQvHUUxLbt++xgH81OcDE9i845o3v73/5o92ev1erZ98zl3tnWvNZFLKdlz6CgU5lIqoWOnzrTx9a5lSw0Xk56FvutQ2ne53J1Tr9cTdigUs+ijBLo5EpaWQ+sRkwho27ABYWBolnrsxcfQBmo5t+ccM3+aibnGnIOfHGRKlymMv7NpZq5pjhKH10VKeUkIsQcYA9Sa8BVFMS2urbqTn5GKd+sAvl+z7prLGjbGudORdHI0r/OsXQjBsH69K8/Im0KQpxvbTx6slvDNzMzIiYlkeIChMPmgIBt2HzvYqIRvaWnJlx9+yc49OwkcE8jrr76Onbcd93a7t8mSfWM0a8IXQngA5cZkbwOMBD5ozn0qitJ0evQaRnFxPywtLTGvoztkU0sIO8wob5errteUc88LIXDT5pOdlYVbleLlWszQ6/WYmZlRWl5OWFQUdRdfrJ2lpSVjRxvGLfzr8X+RnJ7MiMEjmiz2xmjuNnxvYLdxeuUjGNrwNzXzPhVFaUI2NjY3LNkXFBTgWJLXIoVEuvp4EHnoQLVlPUaOZ0tsBn/GpbEzpYAxU2dc1z46tO/QYskemvkMX0p5CujZnPtQFOWvIyUhHn/HugdONSdLCw3aK3rMtPL2ZuzfnqG0tBQrK6sWq2jVVNRIW0VRTMaF+Fg8XZq3f399RHFhjS6eQgisra3rvIBcWlp6zd1Cb7QbdtFWURTlanSFuWhsLetd5/DZSKwsrOh+lQLjWp2O07HxZBm7ewcE+BPk51PvWbqDmY78/HwcHa/+pVNaWsr/tv8PnECfq2fayGlYW7fMr5OGUglfURSTIfS6ep/fHxHGH+e+orjEDL3+aXq2a1freqVl5ezYd4BgN2u6+dojpSQ2LY4dCUmMHNgXIQSJF9I4m3YIJ2t/+nYMAeBidha7fl6Fg4MjnQcNx8vXt85YjoQdwbe/Lw7ODhQXFhN6LJThAxt7SffGUk06iqKYrMLiEvIKi4DLyf6VJ7J559lMfjn6GSfOnav1dYdPRTDE1xFvZ0M3UiEEt7VypoOtntPnDYX6zqWfZeSAcvLLzwNwITuH4pQ4RnhaMtxDQ8Sm1eTl5dUZm7WlNWUlZQCUlZRhZWnVZO+7uaiEryiKyZBUb27ZHh3FprOR1ZK9EIZJ3K5M+gfPRDLtXy8QnZRMWX4u9tY1m4YCXB1JT00FoEebYHaFOuPjaOhXcj4pmW5eLmjMNQgh6OpuR3Lc+TpjDe4WTFlUGef2nKMgvIB+waY/TZhq0lEUxXRY2SKlrrKdfXyXLhQWl/Dk0pf5/iNDsq9QkfSnPb2EZyf9jR2nv+THj7N46YOP6O44iAUxxxgS2IlebXyx0FzuVmpmnM7LzcmJkT1GVS53cnQkJS6d1taGM/WMwhJcXQ3THhQVFbF211ocbRyZOGKiYTtmZkwYPqFZD0dTU2f4iqKYDFffAC7mFVQ+1pib42Rvx4Re4/nuF4ca6y/93pkBnfqz4/SXvPF0FhoNLHgxne9PbKBN8FE+OfEDf1/7A+Vaw7WBwtIyLGxrHy3cKTCAk2VWHDifxp5zKRT6dsLX3x8wjA/QOejIKsxqhnd946iKV4qimIzMzEzSf/+Rrv6eNZ5bvXsrxZZreXiqYc7mz1c5UZY3lHzdAd54OgshDFM3v/EJ9LwdDobBgucgNhH+84k/n95zP3sSsrlj0CDsbGr2ppFSsjsHBk2YghCiRgH0xKRE7O3scXV1bdR72r3tRzp1HUz48d8oL06h79CncHP3aNQ2rkZVvFIU5abj7u5Ouq72lubpw+7EumwK3/xsy2cr7QmwfxA3Bzu6dSyqM9mbm0P7QHj+mSQeWr2K4JCQask+v6i48n5cxkUCOvfA0tKyRrIHCPAPaHSyBzDXWGJmZkZ5cRxBfrlkZqQ0ehtNRZ3hK4piUg7tO66v2AAAE35JREFU2UmH/Hic7e1qff6X/TuxsbJmbO+BACzbvJZWAb/h6VHE5r1QUAQfvWRI9lVFx8GyVcH8528vAHAsOorPNn9OF7/e5BdrGThoPKPmPNXo0bTl5eWcDj9CTnYCnj4d6dCpO2ZmNc+l01KTyM5Ko3PX+ouoXwt1hq8oyk2pW98BhF2ouzvk5EEjKpM9wNy7ppCROI4Lmba0coP0LLhQS02Rk6dtud3f0G//WHQUG45/zuLXMtkZ/hsBQdtYuOLtykIoDVVQUMC2jQvwsl7PkO5nsSv/gd/XL6a8vLzGut4+/nTp1qdFp2dQCV9RFJNiY2ODVWBnMnJrqa9Yh4qkHxXjgptND+YtMCM14/LzP2+2pSBjAnPGTKpM9s/OyWT2K/DDQnhkKjxxXzb3TWyPXq9v8H6PHFjLyL6leHrYIoQgwNeegd0yOX54R2Pe8g2jumUqimJy+gwbyZaVXzDGQV9r80ht5t41hfSLI/BydebZLxfwz/fDWPQyhB67nOwj4s6z/tjnPPeIIdmveB9cnQ2vnzwKII37p/Rg9S9hlJaWcur4XvIvhpOdnYm5xhytmQ9jxj2Ek5OT4UXaZHIuFVNersXfzzCls7OTNYXR0cDYJj8u10ud4SuKYnLMzMzofddk9p1Pa9TrvIzZ+8FhYwkO6sw/33Mn98J45oyZBICdtS35BRqmz4Ov3r2c7CtMHgUhQeE8Nmciodvm077VbopyQtm3cymnjm+gtdse/tz2Gn/u+xUpJRnZRUSf3U9W2kGiYwwlEKWUSGGao27VRVtFUUxWXHQUaft+Y0DbxpcwvJhXgL2NNZYW1RsyYlPSeH3VewiLi3z7b6jaISfsLDy30IHXXniI4QM9+HXLKZJit/Pk9AJ+32/J8l8ccXPSMW3aRNLygjkS+gut3SLoE+yHs0cIXW73I+xMAU7+c2kT2B4pJVqtttZeP02poRdtVcJXFMWkxUVHEb9nE3e09ULTRIVY/gg/y6JfP8PW6nLSDzsLLyxy5m+PzuXesTbVkn2FzXsgJhF2H7HEx6OcfUclAb72jOhvQ0G5K16+PenR7xH69BtpWP+nVWTHRuLStTedu/bE19cXKysrIsL+xMnZA//W9c/42VAmUdNWCOEPfAd4AXpgmZTyk+bcp6Iofy2B7Tvg5ObOtl/X0MMBfFydrnlb5VotBxIycek7ho/GPcATj4zkoZdTeWGOjlc+ceGdBevxst7Inn1RxEVv4x8PVu+1c9dQ2LgLziWU8fwcKC6BCcMKWPxtAbkFmQzsDV4+Bzjr6sep+FPElkTh2dOGix45hMtwDhw4gKN0pINvO1zdr6/w+rVo1jN8IYQ34C2lPC6EcACOAZOklKdrW1+d4SuKUhcpJcf27yU36iSdXW3wcml44i8tK+dUahY51i70G3cPjk6XX3v40J+8/tL9/LjmKKeObmRYcAKJSZdYtORHFj6bhWWVOdikhNc/Ngzu2nsEPnoRLC1hRygsWgkXc6GwCPw6tOOttd+h0+vIuJCKn38bhHFiOG25lriwOPyEH3f0uaNJjo1JNukIITYAS6SU22t7XiV8RVGuRqvVEnn8KBfOhuFQXoS3nQXeLk5YWV5uJ9fr9WTnFZCaV0SWVqBp5U/XAUNwdXOrd9u7t37NsOBkAOITclj8+eWkLyW89jEEX5HsK+wIhUXfQm4+BAVAaoEXvcaOIe58Gs8umo9GU71BJS0uDadsJwb3HXzdx8TkEr4Qog3wB9BFSlnrqAqV8BVFaYzi4mLSkpNJiztHWX6u4RxaCDDX4ObXGu/Wgbi5uTV4sNOe7T8wqEsUGo2hA2NF0v/w2SzmL4GTZ8DDFZa8AY61zMH27lI4Eg65BWCpgSG9DW3+YVFQprdg4IwHmfTovXh4eCAQxByPYbDvYHx8fK7rOJhUwhdC2AN7gX9JKX+54rm5wFyAgICAkISEhGaPR1EUpTbpaalknPuIbp0uz8wZn5DDy++s5rZALzzsw9m6X+LsAN/8C6yr9L7csg/2HTP8EkhMg05tDctfehT+/i5MGAr/Xgb5hTDk4akMnDCZNu0CSduXxj0j77muuE0m4QshLIBNwFYp5aL61lVn+IqitLQt6//DqH55mJtXH6YkpeTDxasIPZxKubYUJ3vDwC1rq+rJPjsHWvuAxJDsX/sYZk2C22+D+GR4cwkUF0NSBoz/5zyszFx4bOLTDaqjWxeTSPjC8DvqW+CilPKfV1tfJXxFUVraxewsjuxdxMgBmhpJX6vTUlZWxoZtF3h/4Xe09jYk8xOnAQHODoYmnY5t4a2/V0/2FRJTYeE3hpanoxEwce4TuGS7Mv3pF6pdTG4MU5k8bSDwEDBcCHHS+DeumfepKIpyzVzd3OkzdB47DrlwPCKf8nJD8RS9XhITX8K+Ey5YOvTj4NZXGD1qBMvWOrHzENjaQng0XMqFM+dhyQ8wrG/1ZA8Q4ANzJoObM/TrDhuWLUVTlMW+NasaNY/PtVADrxRFUeqQmZHBmYi96MoLEWYWtG3fH/+AQA6HbqW95x5cnKxZ/mMYaYUlHDp1nqTwGHzc9SDBygq83eHFR6CN3+VtZuXAm5/Cgnmg1cKzCyAhFd6bOR+PoZPp0KVro+M0iSadxlIJX1GUm4FWq2X/7tXoy9JJz5K4O5/GIqQt55MziDyYSMrJc5TpbZGpx/DxgBcegUC/6sleSnh1MTw4AV5caMa3zy0kztyVkffPbnQ8JjHSVlEU5a9Io9EwdNQMwNA1dMv6RZzZGo9LBy/uf6Q1gjs4dDyT7ctzCT0Sw/TnYMmb8OHXsPy96sn++YWCb55ZQJCvD4kpddcBaJK4m3XriqIof3E2Njbcc/9rsH0dZn5lpGfEUFRcjLtLOc98OIu42FjOH45i5kt/YmMFK9fBiTPwt3sNyX7elGfoGGAoli5p3uIoKuEriqI0gaG9hrLxyEYC+g7gYnw4nQJLMROCoKA2OFhqaBscyPm4PI6HXeL0+YM8v1DH8D6jmdS3NwCFxSVYeVzfAKyrUQlfURSlCbi4uDCiywh2HtqJtb8VgjIkUFpagE6fi6e9hlJ3e267qz1DRvYkefspZva8o7Lr5/GUbHpMn9KsMaqEryiK0kT8fPyYYD2BNVv/S+jJM7TuZoudzSXsHPTk5ZYSm1CIXV4kWVGXuLvtSFoHBAEQmZKJQ5d+ODg4XGUP10clfEVRlCbk6urK3PufYNU3H3B4xTLcW5VjZq4j4kw5rSwKmDtZEOFkTk5MOlGpmSSWmeHXcyA9egQ3e2wq4SuKojSDovxEHhzjwqWLiTjYlBNgVUTndhbsCy8jLsUa/wAL4l18GT32ngZP7na9VE1bRVGU5lAWQ4e21nRpZ0W3Tk6ERZkRk6jnttZWoLHl3qldsbczu2HJHtQZvqIoSpOTUmJlqUVjrkFj5UFOQQHPPNqRvNwctFodwV29uJRXir2Dxw2NSyV8RVGUJiaEwMImkPzC0zjYOWJnZ5gJ09XZMDlafAacOW9J/1FXHRzbpFSTjqIoSjPwCxpDVLwNZWW6assv5Wq5mOeMg8dwrKys6nh181Bn+IqiKM1g4JBJbPk1ldyTWwn0zsXORsu5eC1HznozbMw8eoQ0TT3bxlAJX1EUpRloNBrumvQ0CfFjiT6zj4LUAtoE9eOZe3phZtYyjSsq4SuKojQTIQRtAtvRJrBdS4cCqDZ8RVGUW0azJnwhxDdCiAwhRERz7kdRFEW5uuY+w18JjGnmfSiKoigN0KwJX0r5B3CxOfehKIqiNIxqw1cURblFtHgvHSHEXGCu8WGBECKqytPuQNaNj+q63Iwxg4r7RroZY4abM+6bMWZofNytG7JSsxcxF0K0ATZJKbtcw2uPNqQwrym5GWMGFfeNdDPGDDdn3DdjzNB8casmHUVRlFtEc3fL/An4E+gghEgWQjzSnPtTFEVR6tasbfhSyvuvcxPLmiSQG+tmjBlU3DfSzRgz3Jxx34wxQzPF3ext+IqiKIppUG34iqIotwiTSfhCCGchxBohxFkhxBkhRH8hxHwhRIoQ4qTxb1xLx1mVEKJDldhOCiHyhBD/FEK4CiG2CyHOGW9dWjrWCvXEbNLHGkAI8awQIlIIESGE+EkIYS2ECBRCHDIe6/8KISxbOs4r1RH3SiFEXJXj3aOl46xKCPGMMd5IIcQ/jctM9nNdoY64Te6zXdu0M3UdX2HwqRAiRghxSghx7dXOpZQm8Qd8CzxqvG8JOAPzgedbOrYGxm8OpGPoD/sh8LJx+cvABy0dXwNiNuljDfgCcYCN8fHPwGzj7XTjsi+AJ1o61gbGvRKY2tLx1RFzFyACsMVwnW8H0M7UP9f1xG1yn21gMBAMRFRZVuvxBcYBvwMC6Accutb9msQZvhDCEcMBWA4gpSyTUl5q2agabQQQK6VMACZi+ALDeDupxaKqX9WYbwYawEYIocHwnzoNGA6sMT5vqsf6yrhTWzieq+kEHJRSFkkptcBe4B5M/3NdV9wmR9Y+7Uxdx3ci8J00OAg4CyG8r2W/JpHwgbZAJrBCCHFCCPG1EMLO+NxTxp8x35jiT8gqpgM/Ge97SinTAIy3rVosqvpVjRlM+FhLKVOA/wCJGBJ9LnAMuGT8zw2QjOGM2mTUFreUcpvx6X8Zj/diIcSNrXVXvwhgsBDCTQhhi+EM0x/T/1zXFTeY8Ge7irqOry+QVGW9a/6cm0rC12D4ebNUStkTKMTwk2YpEAT0wPCf5aMWi7Aexnbju4H/tXQsDVVLzCZ9rI3/SScCgYAPYAeMrWVVk+p2VlvcQogZwCtAR6A34Aq81GJBXkFKeQb4ANgObAHCAG29LzIB9cRt0p/tBhC1LLumz7mpJPxkIFlKecj4eA0QLKW8IKXUSSn1wFdAnxaLsH5jgeNSygvGxxcqfnIZbzNaLLK6VYv5JjjWI4E4KWWmlLIc+AUYgOHnbcV4Ej9Mr7mk1rillGnGn+ilwApM7HhLKZdLKYOllIMxND2c4yb4XNcW903w2a5Q1/FN5vIvFbiOz7lJJHwpZTqQJIToYFw0Ajh9RTvVPRh+spmi+6neNLIRmGW8PwvYcMMjurpqMd8ExzoR6CeEsBVCCIyfEWA3MNW4jike69riPlPlP7bA0FZrUsdbCNHKeBsATMbwWTH5z3Vtcd8En+0KdR3fjcBMY2+dfhiaBdOuaQ8tfbW6yhXqHsBR4BSwHnABVgHhxmUbAe+WjrOWuG2BbMCpyjI3YCeGs6KdgGtLx9mAmG+GY/02cBbDf9hVgBWG6z+HgRgMzVNWLR1nA+PeZTzeEcD3gH1Lx3lFzPswfKGGASOMy0z6c11P3Cb32cbwBZoGlGM4g3+kruOLoUnncyDW+D56Xet+1UhbRVGUW4RJNOkoiqIozU8lfEVRlFuESviKoii3CJXwFUVRbhEq4SuKotwiVMJXFEW5RaiEr/ylCSGGCiFyq0yN+2YLxHC3EOLlq6zzjhBi5I2KSbk1qX74yl+aEGIohqlxxzfzfjTy8iRuimKS1Bm+YrKEEOuFEMeMxSzmGpc9IoSIFkLsEUJ8JYRYYlzuIYRYK4Q4YvwbeA37sxNCbBZChBmLaNxnXB4vhHA33u8lhNhjvD9fCLFMCLEN+E4YCrF0rrK9PUKIECHEbCHEEiGEk3FbZsbnbYUQSUIIC2EoiDK1yv7eFkIcF0KECyE6VnmP243LvxRCJFTEpSgNoRK+YsrmSClDgF7AP4QQvsAbGIpAjMIw22SFT4DFUsrewBTg6yrP9Tcm8d+rJuRajAFSpZTdpZRdMMy4eDUhwEQp5QPAamAaVM5N5COlPFaxopQyF8OQ/yHGRROArdIwqdqVsqSUwRhmenzeuOwtYJdx+TogoAHxKUollfAVU/YPIUQYcBDDbIEPAXullBeNSbLqdNQjgSVCiJMY5ktxFEI4AMeB1lLK7sBnGOZpqks4MFII8YEQ4g5jgr6ajVLKYuP9n4F7jfenUft02f8F7jPen258XJtfjLfHgDbG+4MwfKkgpdwC5DQgPkWppBK+YpKMbe8jgf7GZH0CiKrnJWbGdXsY/3yllPlSyjwpZQGAlPI3wKKuZhApZTSGM/Zw4N9VLvBqufx/xfqKlxVWeX0KkC2E6IYhqa+uZTcbgbFCCFfjvnbV8X5Kjbc6DPUioPZ50RWlwVTCV0yVE5AjpSwytmH3wzDL5xAhhItxDvwpVdbfBjxV8UAYi4ILIbyMUxAjhOiD4TOfXdsOhRA+QJGU8nsMVaoqikXHY0jOXLHP2qwGXsQwE2n4lU8av3wOY2iC2iSl1F1le1Xt53KT0WgMM8oqSoOphK+Yqi2ARghxCngXQ7NOCvA+cAhDgerTGEodAvwD6GUsY3caeNy4fCoQYWwa+hRDwfO6uqZ1BQ4bm4VeA94zLn8b+EQIsQ/DGXd91mBoqvm5nnX+C8yg7uacurwNjBZCHMdQwCYNyG/kNpRbmOqWqdxUhBD2UsoC4xn+OuAbKeW6lo7rRhCGurc6KaVWCNEfQ0nQHi0dl3Lz0Fx9FUUxKfONA5SsMTTj1HcR9q8mAPjZ2K2zDPhbC8ej3GTUGb5yyxFCVFQWutIIKWWt7fuK8legEr6iKMotQl20VRRFuUWohK8oinKLUAlfURTlFqESvqIoyi1CJXxFUZRbxP8Dfrf7ZG76/mgAAAAASUVORK5CYII=\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "plotfit(surviving)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "region[Africa]     18.265792\n",
+       "region[America]    17.085884\n",
+       "region[Asia]       17.864741\n",
+       "region[Europe]     15.872183\n",
+       "age5_surviving     -0.141886\n",
+       "dtype: float64"
+      ]
+     },
+     "execution_count": 35,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "surviving.params"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "surviving_byregion = smf.ols(formula='babies_per_woman ~ -1 + region + age5_surviving:region', data=gdata).fit()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "plotfit(surviving_byregion)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "region[Africa]                    15.080914\n",
+       "region[America]                   27.506243\n",
+       "region[Asia]                      20.032483\n",
+       "region[Europe]                    19.884446\n",
+       "age5_surviving:region[Africa]     -0.104053\n",
+       "age5_surviving:region[America]    -0.251994\n",
+       "age5_surviving:region[Asia]       -0.165384\n",
+       "age5_surviving:region[Europe]     -0.183029\n",
+       "dtype: float64"
+      ]
+     },
+     "execution_count": 38,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "surviving_byregion.params"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "surviving_byregion_population = smf.ols(formula='babies_per_woman ~ -1 + region + age5_surviving:region + population', data=gdata).fit()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "plotfit(surviving_byregion_population)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.5"
+  },
+  "toc": {
+   "base_numbering": 1,
+   "nav_menu": {},
+   "number_sections": true,
+   "sideBar": true,
+   "skip_h1_title": false,
+   "title_cell": "Table of Contents",
+   "title_sidebar": "Contents",
+   "toc_cell": false,
+   "toc_position": {},
+   "toc_section_display": true,
+   "toc_window_display": false
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/grades.xls b/grades.xls
new file mode 100644
index 0000000..11f37f4
--- /dev/null
+++ b/grades.xls
@@ -0,0 +1,101 @@
+grade
+3.6486506831864647
+5.959914531099744
+7.387369907819315
+4.047514932455342
+2.8469122209808155
+4.908984524445626
+8.019990399866751
+4.357031328001026
+2.9726682668432396
+5.754509437093547
+4.079202365341606
+5.200295045685908
+4.48959612164084
+5.713149842536605
+6.832996121655891
+7.866566835452222
+3.2672802811163937
+5.939390128316047
+7.467589190193696
+7.395194804216371
+3.0362852116433254
+8.42543413299341
+8.419048725637117
+6.513623100686676
+7.578157607765048
+6.050065289181116
+4.4463766747108515
+3.161202472677994
+6.555170928903836
+6.229383468553857
+7.107329166304159
+3.097099702256456
+6.727782864693218
+5.663903752510569
+2.1303818687894944
+4.9287134060700915
+7.507273214424758
+8.263140484984751
+1.987371083115574
+1.9831673208244243
+5.043670069070349
+7.206693105434189
+3.707078449421833
+8.0400349968493
+3.7911280741042117
+3.525235343259275
+4.4238487528253865
+7.894119024634566
+2.2765778622910924
+5.844761486691925
+4.212468680586445
+5.877232087673094
+5.891793333622445
+8.467353114696675
+6.284652455835449
+7.233759629364596
+6.679370724852464
+3.7845739851876625
+3.5363056817185248
+5.066895635983498
+2.90273485956826
+8.091733918855121
+1.1608992634920643
+7.687033348360689
+7.7579933561774626
+7.99631534503564
+2.795255844568848
+4.2789211999355015
+6.658985688205322
+6.285302294615455
+3.3039162776414335
+4.081779561599752
+4.413451415074048
+7.993866951700736
+2.372759801454405
+4.204147254214313
+3.9216042106927835
+6.350133275480319
+5.085033543257526
+5.186679551245832
+4.640268984540133
+4.964791482645964
+3.620425764324112
+8.351605009967543
+6.053939279533999
+4.912927217276879
+8.522332488755932
+7.712100299357658
+2.313363021557444
+7.015815025743799
+8.400557507678222
+8.888041750327998
+6.299029420680743
+2.771281538512943
+6.797934569359432
+3.9406907006664618
+9.120704531417568
+7.842357435219203
+3.920675894041414
+5.485458607961167
diff --git a/london.png b/london.png
new file mode 100644
index 0000000000000000000000000000000000000000..2d0c01b27c100ab436bab0681eba0c58f4723d47
GIT binary patch
literal 59070
zcmV*2KzF~1P)<h;3K|Lk000e1NJLTq00IC200ICA0{{R3!=@z200090P)t-sFE1}K
zF)>C)MNCRZN=iyhN=QyjNls2qP)|)&RaIJ8RbN_FSXfwESy@_IT3lLKU0hmSU0q*Z
zTwY#YVOmmPTUKCPRbgCMVP0BdUs_^cTw`EeWno%oVqIusU2bPyaA{v*VPRroVq{}s
zXJuhzWMpP$WM*b&X=Y(;XJBb)W^HI=ZE0j|YG!U~WN2t;YHDh2YiMq6ZFFs8ac*gF
zZ*FpNZg+8Nd2wfWa%*sKaB^~TbaHTZbaHfbbb5AhdU$nwd31Ssczk+zeSLj?ettDP
zl4xzNEt}44x7UV$cY%F*<R2gJb904(eTRg8fPjF4f`W#GgN22JhK7cXiG_%Wh>DAi
zj*N+njEs(sj+&E-n3Rr?kdTv;l9iQ}nwF56mz0{Am7bcCoSK)In3$THnVOoKot&AT
zotmAUouZwVrJa+Yo|>ehpQ)vvucw^1vXY>nprWFprK6#wq@<>%rm3l^tE;Q7tf{W9
zt+TMJv$3tTvaP(csIs!MwzRUgwzjplxw^NryScTvxVXByxw^W#zr4A<y}gvm;lR7H
z!MwA;zPio8ug$}^$;7?U$Gg?bzS+#W?%1*N-o3!Uz{A49!^6YI#lytJ#Ky+P%E-mc
z$;8OW$j!{j%*@Qs&(Frn+SJa(($LS=(#+r0$Jx`#+0)A3+0W3>(ACt^)YR11*Vo_K
z(%ISB+S=OO+}z&Y-s9QL<=V{d-^=0K(c#_L@8Hbh;os)q+2`Wf<l^1y;L`2l)#~Kg
z>*n0<<k;`!+U@Ay^y9?#>Co}$-uLg_`S08L@7&<v;Ns%o<m2Mx<mBe%<mTq)=;!C`
z>Ei6^<ml+=>gww3>+9_7?C$RF?(g*S>f!V3<nZwC_3-KU^6dEW=KAyJ`}OPi^zZxj
z?fm!c@bK{S^6>KV^7r)c^z`)h_4W4l^!E1l`1SDl_VM}l^7{7h`uFns_w@Vt_51nv
z{P^+x`t<nt`1<<z`uh6(`uP3)`uzO-{{H>`{{H{}|1{BPNdN!<0b)x>ME=qM!czbM
zAOJ~3K~#9!yuH7R>P+-MzJHlj_<Zle`(0UWV`s7D#lqH3xV5IS30ATQf!IhuL0Pl=
zAd*5M7$${_g%Gf?5!AqU&P;wxl9^=Uy`RtUJonyp)g*Jyyw2<Vm@_ZtY&J8E?3m@o
zG6;e>{(FJWfq2{w?tCU3`yhC5UN-*u*z8WX_?}L?P4b&bzt{U*eWgcl0>4`0_wEY5
z^n@Qz_)8yOC-<TgY@fS-GoEq>ezfto`?mPX<V}Ws3T5D|D_rWuFnKSVc`-eLz}<Vd
z0_k7Sa#lFz_)W|I+X}GWGQz*&|6?IcCcR$&^ZP3|KKtbNC!P?Ku_;oJ9scDe^V<3r
zJog0A#2kX)zBV?e0`VILzA*mf+6f=}R8i+%_%Cx5plIP^we$9~@`2@n@~@iJZaF<!
z+ufG^>3B_U>9}1dLgg;~aD4a3TekQ^MT@5p0&dYljK}5{9G`ijWbWs9(Vg&BuVV2N
zwPY6mM*c!{2oxY|1B#b^fEE(c#{*%Q_*V+B-a3wh|2Ld1m747^!jEvD3RSf9qtPce
zz_{mxn44=M1UPuLre469@QnP;%zWWzDY8p&nR_T3{~3cLp#TfFXz^b?YtLKO++hWN
zz<K$J`!+U?^U?Wmd`-c6fPeDiJG!TgJ`rl~^Q&;IC<Gkw;}l)<RPg(>cC4{7-k*_2
z8hYoqVyi^&nLhQg^5Q2$qyW*4Sl(4E{KwfPOFy_uD!>dIMeCm^z}nH@-a7S$@6_Hq
z{yh<X76ge<CnX9%Y2eo981k%;g;E7e9sY9*h<tiZAnBQLk7K*|d#HH)o#fZEA~r$D
zMGAnI{-en1$D%w3^O@YZjECcYVgqca(ZLp=v8~tJ(H;3b3kX8nn7tAO`0Q^^REr81
zToFyQL+v47bgjh1vlGt@XE-c0BwM2O6?M&|vL{2N07l``56&s8?*^`<0_=yw;owOH
zz@VS#x$V?6=Lkz*eWQ$TFyepg3bwenDuaM4{))|x&~EYA716{ita>2h&!RCM83@pa
zg%E%*=U3FVw2E;R0K3umqNSfD{EOfqsQ?qK0G-iuHo!4dyu>%V9q@kp*s809dO0=!
z3QK>`6?_cX*`!|v0aL*C^}RS0VBAYQ!6*E%V)>Ln0MGj@{&q9-{donjkMc`D8aG~i
zhc^bp!C*XjLILdE?uhx`cI#|EbWHpFz*n2iMy+|e*Hs7RT>q_eKS>RD@4Hw5LK=Ab
z3mOR8aoar${UQb6K!CY6!>fS8CN>F#D+E(BCwiU&tP7WZz;)tactJ@BC>o=kKIGg-
zsSU6l%&bl|{phImW@7d4PF?letu4`j?m#HClhI$Hy!-#zPk@0&12+;hQ26^}QJg?Z
z_B<J7A;4rN%%Qi#2-oC%r&%BnRsl9n$<nv*U;J;8cLb3=<iwdv6=3VUbx;0#=X6r+
zz*ivr^*CW5aM~STS86)o^5{4JvjisHub-c+^n3kD!VSV`;I)JX-U>nmg-(LZ;LaF^
z0B1c;i60LF0UP4urr$0t`LqHQFa6trT7CRaLA+1e5nLXJI>%)wnihNK98cR;y?(@e
z&!`1PN9o>=j#F<rj;eediCus<{ua<cz)7dm{6QJ%<6klUVK35_LK^54t@2Z;*Zzb8
z00a!RwD`j%b0RluW@b`S@{9r$FMTG$e+~kV|26WC;A1$fmJZlr@~8QoX3Yn_XV+>?
z)i^rqjiWbewf7Hai)kSZm5OK}o~O-QeZ(k0FAV(|jDPq^GeRXa5LUS`FuScv$)pru
zj1^#*7XOSu0Njhi4ck{3FJ()g6|5VGR=T_+cs8VMz{Vj%RoZpz>H+T8wMTt`7k}5W
zqu(-^E1-e)G3eGh_Lr9n{o;|>07)9?7p?MJaV)uPa78)lV)^S#iYT5jpQ6!UDuC3|
z4@Z;|&JTG<(A^F7as^m#u*2tUyPc1duZ#m93%}I~?(MceP_&O$!+`{tjYkTuc{Fh2
zAidGBedo(dARrXBVX*#TUy246+K602;2$W!Y^DvdBar(Yi9E?JyUGf1J8jp3lraB$
zq#eQKbvP^_0b8=BcX(+ZkA~9j)Qq6sHX!M#y&X@QayqGvMrX?pwB>2w+C-?MbbLeC
zIvq2ifjuz<l+eIJ8&OtL@SFn7?4j-DUqwQv>~9s|N<*rg+c^ZHl`icF&K~2jm;`Jb
z?Zd(1R~s$;+U^8FyB%Qu)~q*An;Q22Yiq*&MS<4eT5dwosD?)qe??786d>gMMw$i^
z94e!MOw7OHFP~Nb<R2gTMS}uq->ZTG+)qg;BmZtp0&e{8*^B65Zk+GDx01QvY_?AO
z9XtH3cfG6lhHtd%b$m-lN3Y=*Yi%D>erz3t5IyKHvq`6Ok1z<_0>51!c?=7PZ9tv|
zmaJmC$VS+KEDba{v`3@>P#2Jw_5TG0xS}O{Tlse{@S6mwe`!ZB%_QfG@cRh*JN~9s
ztFO11@dp_7yN&U&X4rM@<Gpb_f?3$w#nT$oz<4g_uDeHPyV2gJLIIzJG_Y_L7c#x_
z{B5M0CT6F{-FC~MjgZb^S?3|(A1lCvR`an6z`38BkOZ6q$)b>DqC^YJMF>+(tObkp
z*7?8-f30G+kDYxoYHMd(Q~d$8`dP}y8>*U*r!5fbVj_8RzL!5<M%V_229~Yj!hm0y
z0b%aVIMI<@OQ--`2ta`}>Xs_NH6i@$-R9r!1;LsBMe>edq(plx{Jqvf?h^k4c}Mk4
z?c$}6*?v&7AJ>~2)LUAk)jFLDtbS&Ue&;6<?ceKKx6^#9)vTY4uwf)=f>0}N#kD*l
zKY;{bKvV()l2uIONEN`zsYZVAAi(`cB=C_g<SkYJL0#_*tb;%^awBAt3#4}&wf8R8
z1HIK~IrpYUlu>&NZtpFG#`VB{Z)jNdn*yt!nd8~-e5w(tHKoz)cE=yA4M-rMpQV9i
z&Rot<U`2Zn;Y04eOk=a%f)cDtq(9?Bfc19@Fu`Lq8ogv0d9e+Ex?YR_g;!ZeFl3So
z49pr?`(|A;8r`5%?{vDxV_Vx_Y^Bw~sEv`y*=}U>YvgW6o&5FS8pO3t6$SL7C!JKK
zfxARO@=@2NC{&nN0P<n109%Pr4hI6BQ-DzJBh$3)<G~MJa<^5e0D`(+7@kNoGQ&EA
zBmn6(y!sE9d$$z?Y8}%)b<kGabG@To+-}E&O2p+tR{GJs{>~+v=az-9GVW^IJ*xpB
z4V?6ug28Vo8n}*S%#)lbR49-#I-O*w90vlbDL^QAko)1l1b=f1P+|kb(FaR{k}RWL
zB|rl9s6MzkDgeLMXx4T&9WT|Ie%2c;?*ROOgq@_;KQp<i%DFY9DYZuP&1Q=Nh_ENU
zbiJq?4Rm6n$9cwV)zCVBkEwgZ5FnFB$wNRD1(;yL?+$*DA9)2Rb_6Y9G<fzXb_5sh
zA*nFD&gT2`1AF=PHgWfm_oiOz@0~^qkwM&q1H7-iTr7>kqu-p#GnH;j3%c#E@0747
zy?&-tOpXQ`v036gXQsH^oW=j(53B$((3yt-DFwjj=Us|&eZ>mEj|K};!bOhYo~bar
zfDIr&j%$!zy__2wvg%F1eGR$b6H*lebGj_67Rucsj|O&INNWb;hPz4$o3mAb#)ze3
z`aA_-GsbXtc_mHXoSY5FLqMSd%&~`kxD?d%!tjq9Bd-9nqS-A<35y)TCAuUlpVSjZ
z_vP2tKbW9h+I36-y9D=B9?2E_g(3*xO)G~6BDICQIwqQE^^>U!$qpJLmX7Iju5TuF
zA@uf27(Unl83h0cuvmh_SAd0u(D@RSjgz5&sDlq<Q>*~|Xs`h4d5$1kS)ObhJ&?%L
z8F`Hkvb45->2^jL*+<vHN-qcf$;i_{cdv|4yVkj%zV;tKs7L|iXkeiNL?4z-(@NR^
zfPg!TZW#qwmVrGT$1MqD9F6T!U;;`=029c|j+`SnPqq}D+1&D;VEc5Ay7fk_(KXL_
z>08t3H2a0~0vafu-aHLlBE4=R49(hm?X6e=BxzuQ0z{7|J!Eab2$Kt&QEn?t%vk$!
zun%al`o}>1(BsWSG73;B8k}_m=b=7cQC7nPAQIE5J845Cz+F!1;Cv%~MqbvWXmxRD
z;L<x^&YO;+v?rHau?>)<frV;#s}!V_wE+`54FRweCBPoT{V~G(BjX2L4+q;eO^yPT
z*Z^@#IO7N|A3?6BC>&?_j_K3_XKy*5PDKg;$tP<jH|xpZ&_K^s-)gP#!~gmD`0)xg
zpb`z_--;`Ym-5D3)&@`rAnv?{&Nm6sA9u!B1JQ4fvFlIe4zVEkCat;xh*QF8N07*0
zpep1$u*Bzy@c9~W$<aUw%gUpH+FKX4+8QlILI02j^6v)Xr4?#*q;0?suiK4%Jlsnq
zf5)aC<GnUEcHz$P`{8JBh~Os^8Wb7~)PXkQDL}CeScolL$`J$&6+IXEj%j}IG$mkY
z;98DYacCfB#^;?{ueAn0B?$0Ufd-09(IJrEFDqpOKwzfrmkOS`cA=@KZ@*kH!CHob
zC*P$FR1iJ=sk#Dyb0$!4))BM{R{?y7i~`J98Yo@;n5Thr?=X0;H8i}|zIh~Y)lWhK
zpE5MCxb%8ii3XP1faTtmSoJUrYU<(5kIMnM7Gr;5(T~XA?E2s-z|$#V#u1z!3gc8B
zED;$Eh-qMzT6Yc&boF{0Wa^{*PVv<z^pB9Gfl^iX*Fd^Tc1CP~V69j#x|ADxYU;te
zgGGP4cxcZm6o!w~qE8L30u(!f;*@ac2+qT}Ux8sG^~Ev@5YoVkrO$a9xW_i&a<l7o
zJ?r>m=}$~HB`BhSRW@9>yb>Pa*q=_v%u93d>PtnRHuYBm_UyL+%fps_Fd9un*Dh6n
zN-1IN2wF+p&ntN5hpY{_1k!~D$>2c1{-CuEt?pP^rYT>vM}*lx&Y^*oHrvdi2!`xf
zU>gv#rv-?<)U8jM`pY>D_A`q21HqzC4Xy%|M1wD)#l7@WH(A7kz?qbhKZ&YH7Mn36
zPXiaI(M3%oXbw^dfVei0Z6d<bz^bAThbQ)xIO9lcz!K8drFhSH^>=LM_nEaA;r*yo
z^mLRe06!(1m+hQQ_MOpkSu8lf$Wq~xaeJorF;4@r0+{H1?AJdmHY4;M6$Y_3fNF*H
zl<Gy76T>8DpzHNk9>oRehh9A<Sf0zFnOZU4a|T}ls-}c3#3cK|xZkZ11c@Cfm;Q{X
zTZOe0j!Di2EKsY1-VCRCv{KC?;@UvQ2CRC~6L^)c91Tg+CB^cnsfWUe`{{nz*`}Em
zF~$2TVo$~k_hVI3!fd|hn)D3<kT046JV9Qm@X7ZF!US}|$kD(#+P^6Z!1_AXFet7K
zq&DC`GWz7Eo>IMN6q~NeNRH*DO#S^}n|OKKyI5vb@t!mI3Q%GLl9Vu$=g$<E7C8$r
zAgfp|{qSo4f(9<oezZRWweP1qLCX0}bK3ha9uxweQ@v;aepuXK0G7Q|3iv)_>hV;a
z_huyJ1DHfA`l@)(880L5%f$*nqrpq2YcQuvY=N@?ql6<c<Dbz$*LA^q9rr6X82s6%
z7&q;$Vg>l_5zTx`_2AiDY@aa#J`l<%5FmaT!#^bfe3;oo&b0$fkl^=nL!bb~HUNZo
zh~bN$@1Y<sysl~7q#dQFY%#Ak5a0O)c7Kn4Xihj0_7ob)ekTy{*@t&mRlRVR(-I*Q
z?LAGYDT9k=!C20gdzp|<pi{5@2$4JwS=p;kAf7WmK95Ve@iO4PT&Ms`l-%%H+#p(5
zIzqR_9i^97wd7hfRh-(u*&g9_snu$A^M?_3kF*i~j~xjOl=ncEWS0}%udBS@?oQ1P
zG({$SALZ&{!9#0c2<4^RdW!d2^yB>TFZP6mgQoyyX5(V=8*H@q2Zr($YN7z-qwj`x
z8glnoF}W5FPEvS@)b=B&cim3&C((dafA#%ecJv7ZRHA{d+1`8DmA_)SzXgHX44|XM
zbz{q$`r8G$DYMCs=bZnBo5XT3iJV{ZNSQ0Z2w$I0Q_UmYQgGyheDw7jX$6=ap4kF1
z>gGj+l<p;{J<zve{rp!rD$~HZbsp5h_GR^MEeN_z-*Fn9<57^tIi+&-*E8C)SW5D>
zqWJycZ`_kvTEZ`b@~(Yg1EzD<+XEX=p6wDig5kH?@=x(pNQPqr+|e7h0kz=p^)@O|
zfd4Acz$kXxX_NM4!MNen^kchmbgr=HB{z})K9A)|@cU{}CZPnV0%#HnfR}#EUmk}&
zHUw80P%b_o#Hp~XZ^6l{{Fr$g;OcdRZZ+f5Res78K#B&Y!#K@xw|Q{3+lG2nK7ui{
zu<bT8!rz5n{Yk*`<oNxiQnHaNfz9nkvfVF6-c+V5aF%WopT4-5F88qlcrq)4=Lja>
zjTJzu6pl#F815=RX5I$uQGJAL4A1S+rAz_7i)kPx^=H<X_m9V8ZM>-u{OhKUb)jpJ
zJ?@bL5L2&{e*i7SvNxG|5AhzvF6Y|OI+>@38BRY@fDOkFOr-BJ-kxWD61v>O3Lx$o
z$&QR8nC6yv4LGuQJa>kAWg5r}2Wv{J4m%N%TM7Xp8n_@lj}^UbPDT^+2oeX{-)?rB
zO0DT*F92JGtCKFv1H^}APwUp6jpsc6syT#dBrWY;j#~Z=AxmQd{AaxM@!J1feSd%V
z0Rp6~5bFqLsU>Woli3zahc_Hb!$mxJRRN<;7i(UpsSL^#AWZ{dk<K#Nx`RVPv!+dp
zuhe?C)u?rXR=aC-F#fk2n}IU0LsL(AUV`|ePRQ?{3g!J(l$y#SEO>eG2TRTyHoFrW
z;D<O#|MQ!UPk?}nj0#4MV6God*qYLjR)D23+*ByF59c`V2S8oO)o9gfBd<&WLK=u1
zo7Cg&n4+xvVYe~KPFofW+V!qxz;3sPe;n5~+jU!Mj$`~p5oAaFzN`I3DDSx_waGg8
z4((;~g5i*T58RXG9e0KvQNB5m{^~m!pa4j!>=7Kntn`^vy-xC}_Tz9^nfCBvK`v73
zO2=tUzRTqQ-)C<^*0*zDR{hl`qTlQexoG~IN|<0{qmQ>cgLVEM=h%LYV!Y>vDrHCH
zp5WP)nM5<+lPWBDc?mSu5|6s;!_gqkN$=1&27tf!$x1)80pgyK>^Nli%5R)gye1$h
zEB(N(KHOENJ=}ew3aJnGJ_|J9d$sz6Zo-`X)Q1!lFkb!XSR)-y93vC!zwXQtjpvYx
z%w(#6S9p@#pzet&NY=1|7w)a3JyBnRk9cC|`}L5Hv9ZOt&y_yd03ZPm84TK|>gw!c
z%qXwN4LR>j`hn*=OarSzCdUTAMqz~S{oMcL*?kZ^JTx|UKQfzc0_xRks<zo^IdwTW
zyW?gois$@((gIMKGQG<9?<n0@Pum{91cpHb343^<FZE!k?;O~y6_dW)Ab!AECPOn1
zqFx$oJM!>UFQB3FkA1**)|G!d85|pc_8PJP0@&;?S@IxwP<Qkrv*#vYH{0z_*<T%Y
zYh449_hD>AEbloR5XqI<gwEK2f(4%&HaTtLCD`bPu$;>$tA7uLIxOkS4^RMCiichZ
z)nwX{-;Qy2=W7)=V4`tP8!8!j8?b;~$Z#6lq4&uwc{o*&S@KwbMG1T2)eo?6jbnDz
zUk^5R`v#F~2fMjUfdWjb*nqGkIT0^&IDrW}(5r}^EJ&*6o0s7Dk&qQM(bQ3n^yLPa
zfO#Mjo&_~YPI85+f#fz%RosA?iWT6assfAzm_Y(5Ju*I5UmgSY5y9Vx6kt0}ayJ>R
zAY1Ozct61&pd*6%-=mqtNF+PU#!;T`O1p8QyLVoK`ykX^k1Tz@+2@b|nS8#L5a_sI
zD837)k{dAl7!K{KG*Gz600Jz_W%twLwQGh1pU3jR)Nje(#~>&A4FH0wg4{FJdS-CH
zi{xBp1Bw^*^M?~e2hI9$;KWN1s8N7lPWllED5?3&GzLkWc=icy@+@#R+YRl?(Lnwp
zv)oHsfK>EphmT|GIV^88{umU6@<xH~i?qDN29&kOlH9?b9ief9!v>-AIaYv=<2jUm
zUq<>72`H-hTc9L$_&BGNKCxC;a|32G?{umh{mR;aOb8!hc@q-L<B7h&)ZY)=^;o>$
zin)Q~aJYWP29%rhXAUQb4jB)Rm_HE(81JrF{L|j2obaPa07Qd%!MO#KKL{>(hG&<Q
zq9hN7e{WY1<}*pqWRY=1PhxpTUd;~V>IJ6$df0@bmny}b=y2kXjCx{;bLOZ>m_gOU
z2{sY-M<3e|1vvTGC&Ii>UjCE>a8kl^wi_5U1_6I`=B3zT@^E<SE9Ll}NrK`<mdW14
zqCaqXo=?2`v5`0Rlq6J5-3;KU%rZY9T<)g4^uzUAg$Axe@v{fbo&wq|`m@67k4b=+
zN$4}X0^xMgnDS-YhsC=r4;52dm6M>0JwjgE)(b^X&U+;akn`#TA7~z4^swZsMsK>q
zq52_$dUA*=Bk*d+D9ayCK!!seGkw0Y9lQ_(Tvb$nZzu|2Q^HHu=pUGBF?gzlAY@ee
z%oF(}=scaci&C~+(PL9@gr+|CJM0vWKS(^sc(MRr9S?_2P5}tPhj8!{=Vm9P8V$4|
zES>v`7w{&6uPXQ-+kns}vn@a$=gf{Z1Ay(pm$Owhrzw>LO_$#Lhlu8JY&|yhy1>-m
z4>mFNVLS)x&F0C-?Zg<`tO6wL&SVa_cxpH$hZAH5ujjh+qGJ|#|LIj!fK`|hKBO2Q
z%5yY=_LqP=HH*rS9uy`Z7Ac;0EfPKU>c`mBe{f9w{b(E6`2A$}eExm38|snr<kq|B
zxLdjLmuFOwuK)!2I0jV}Ac_Vj)9vlWvP6Ok(nnQVFRIZ@BYqUkvmGA8Cl#3=V~(l6
zLOej@yLJIE-UULHixRN%42QcBSN!7RZY4+AA%_wJNT9wA`jP>Fctj~-!uSqu@j~7U
zVuqKh_5Pe1%{1bN6o0eJ`}JVzPlPt*A;EXnI+*&2(6NI`>?PWpsCp@$X<!8qx%I!t
z)#Q~PWrrL}d;=%|X1|qLV3ZQR9m@9y%;p03&8xiUi>=X2BR=JMT#BEV`h1M{3TeCY
zcn+~X2mP&$s_#<7Ho!1NwjK^S`imhr<j_9(C&w;V4V$`wyK!|E7^Q^e9P=B$dZ_xT
zH<Shv#6L!Yrv5qC*wgMwTvJbehsnR}E=&BZy3#_G5P+6rjED^oh~O`60QZclB$Ih9
zJj|TD@8xblKJfAs3E0b0qjSK0*{Zzh4;JE;BECJ;Z6`AJS;WsbN=!4r57J8G1CxJK
zj@&Q2K&uT9axEDMNEPDf*ajR$3Lrf4TyEsgF-;PEWC%H8^uCv1aEEkIWd#5dAeR!J
z!NTQ|J?YQWcUz3LKWqk_cDpmMv#Gm#woxMcJFpYX){D_mwxJ`Ye{IFMk;5#?Fd%2`
zM^~(8B0>D64am^IIML@gKEZ)I-wwp@+r0$iT`=$i*)&j^1jugjwgdqjX*U34e&lZY
z$MuKW>2y1T;ZV=Y*x-BhVX#NdgzqP#K<)uB{d;?J>~ZJ4-YR7Qc?H0FwiA(n@!#11
zmIg*e9&xZ2LWNh(309GffcL%NkAolhU6ln&rG(=lc$-Xd`O=N@3)Hh8bh}U-qHl)7
zsPvZRZb+lVoapKAL@ZBoo29$2*BZ5Yv)fSgavGSOZyn#+RfzN*&G?%U)4)jWZ_E*k
zu=yhACvH>kdpVx80N<fkl?6u8U^ydx<xevzW|5fZQ_yEUdj|{N22MA0;(*SW8_?O%
zRvKDC5O*O50ejR{M_5@pZ#vp9s@nj3m5E4#gYI7`KzK&gHpD_dP5S`pvqbPtu|NFj
z#lR#0`+?V|NPs9MoEryz$dBs=SQg}PF5#}roM(T(vZkKL@@OYLl@R>$8<T;6Ih;L+
z9__{v{w~#+oC5d-HbDP78$iye3bXw8Q`X|IuXzaYQwhNrEf{a1EU@<!36R<)OeD<>
z;l}x-g#~8^oG)ypPLjM!;W}-cHQ=&5OnM=iJCJXiB?$qP2DJTPt+l(ASpe7oUu*;Z
zDjb|-ux`BLb$Owp)Dg@t>V2bQD^NKj%ufjmr;h{mSm+ShyX0Hv#9{ngQ0FA9$b@YN
zwy6z97!ah2EyHn;>*~8e+qZYMU9Z(!YIPPc!M7+>0Ig&E#fXYLPJ(mQuO-Kszl?XM
z0r-KHS>U()E@3=wiJriTW}>4`u(7A*dFj<nx@mk6<j;PBvH*<tc-4=3y<SlvHdnHN
z1Q9jOjq_ep8ePLbAF`)gahly_XPIOZg^9nvNC~c;nD1ni>UW4MWyhJn=$Hif*bn@v
z%mU?i31f!~+yFSyjC-z?Pfjr*$64T+K4j!eD|B{Q(T6=0Nh}WoKGZaQu2wzbb5+UQ
zq7n$8A)U2j7>)<AZ!ax>Zm-Ln4ZvbJ2qEC<l;D~Mb8eY$*45t~ZS<Q0OFmSTQGn3^
zlK|`o-YT;|LIN&j;e2vBiFpmKJjvhVs!ZEC98!`m*mrXbJv*}K@%Q(s@aeAp$p+@S
zf&$D1WhS(4DJfyy?T&|YpeY@e1d3YSW~bRKv;oi2z)<}6UD}hxi(e&|3b{o|#_(k_
z@V7c}g~|!RC?zb4rBTrfYVV>_Z2W6K_p7)<C!e-U7X7Ff4ya{jcJ-6FuAl&U2oTic
z@0?Df>l=-P1BiPaXTN|LCb128CMCF|;s@rJun4^PBkYgT48<A4^~-3y^#@Q5S2-a_
zA_0&R&I0bFNc5!Haemu%Gz>n=gM^*|xjR_&qfqQCEbeTFH*5p&+beZ=&q9DGYU`+q
z_TCMQH(K{n-0M8601&efLckN@U>fwhhr~ZjD2$@TAL@w$C&T~%AOJ~3K~xn5h5{P6
zIo)6EwH^$%A5WBp5gS0Jn`vH5jwlywu7S70Z}}P9u?A3o%$WLnNCLF+ST`flCriGU
z+vD4VfQ?<Ld<#;H^Wv@4L;*T2$E!OkQGl|O4${19vn{j%l~aN?b(~_qk7&>UFa8wB
zgr-GE1Ib30mjEJxI`#uAmxU2WaB`;89g5!G6`yXDU-Sg#4Nlq)TLSVcEP2>ppDg=y
zFRxr{pV7Vw2>_w5)8~B)6~It*)Tt}uGvb_fQ(yxiN(T!?M8@sY^;V^<BRoBfiRS3P
zM}yy;oPtqc;M2fO7(60d!!|lJx2UWDKmy=6OJ9uWMT2H+KQ_5v#M?4<4g`RsW#9WR
zKUTf(+$&W`Kqy+N;!4}m>TgQh39c3@KkOv>6v@zFnspLX@P>jom0mvnz$q(!P=McE
z4!(p@W)2OEvVqqfYz^C;2G|dLf(7>blMzg}Tti$2)&&{cB#UpXZ8Ng=y%6zxD~<-_
zUi_{^0_Z}Ogn+G6@1UEn)!S%UssQ0P15+omVh@#1Mgn`15D<#rXTv_2`E|KQM5hsk
z91V=Kfi|fL+!(<C8Wm5gvcRv;etF+}j_5gI+~i;cXKRP&TheXn*tL(~p4ZbOZvzMk
zkSjHeaas-nHb>`zI!e9uHsKfn&Ub^fqMaBVGQNp=X81QL1%w+VpGc*6N8R75F32f{
z>@r0IBZ3{?7;Ft21mgj|KdS-@3|p=Dq(vWZw9FEGpA_ujRj*+?5*}$wWKX0I2p=u-
z72gKrdpo&uWgd)~mV|))Syk$TAn3Nr6<|h8H4~q|rftAFT01wa`$sN3<OgBMH`btI
z;!l_#Kb9~`Xkhq?o!uS?HGu<vqZ-gNql)Y)<N7HVJ-H&!w>xg(#x?^;*p3`$LXS2L
zyOUt4gVBdhKJg-#vjMA~<XIG{l~oP_Yjd_hs){_2!PzQf0q&KV<?s@Tkhc-^pGdNn
zw(BV!Hd(mL3rWORP+CSk!D#<Lv^O}F4Gf?x{HS6-@LsL}U#Xe??Dq>TK-dqPg9c#`
zR}0TF#`A^16Q9y<Eh~!m-@O$fdEb$Y<!r!rFK$y#n<dF8Kq&;!-HebG_O5ofYa**i
z0p{qIOV1=WU=uaVy6z&S^JQq@8h`A@sHv6&eK6tUrj){0$u`o+;-s^Npa9!(phAnY
zLKes_{QthO@Oz)%!gflcl1y5l9fk7PDtv_c)Z{bJ4zdLZ==UqxfIj3XuL;0Qm;ed^
zVjdPL(R{H)`$nzVtc{S1T!98Gyay*WAKHL*#K2MsoUp8;cpOtWfyJM)`}}YsrGezo
z+;H_}>O(*Q?t|b1{6NeCSEaK5Z?)=UL4EPlc?`in<y1l=lGoCbj}*Y_rCofy?7#8y
zrx5ThwgKO{7eD*UfF)c~Heh`huR#_=T=e$7#U||?S!xyq=sTb-&YhQ<2OD6gp+6Zi
zB;?Mph(SjDqHtpPYPeE4YDu<-YbQg+3StqTs{r)r!e1eNa6jH?nI`y2(vC0saAFS`
zk3L%d5bKM2`f+VQuHoN`*nng@g*G4y0en|1{c(3x2NqzwV{gFP=OJK!$*{C!Bms|`
zle>}(4NRU&=R|#UZdN(0Idv#|<ftW40DOJ*2*GO7AZ{fDeZ24mtWRh9VaIrXg#Gr1
zC|_F~ojsqXX+cKI|C9V*$p-X@4XCI9FufcI$bJ~koIqEnU2BX`J{sWOGA?>*B+YsF
z+EEq?U}z*y*n9}+lq3X*0vxqKC6%k>DKH3dK%ZyvDXwpWY$%8pX<*6gqjJ$x+`OKy
z83^bTQUL#BTv`>`fNU_ZpRoa^g!ri$&WK>0|0Fg6ol&dSG%nsg>k2{#(o=yHVHx_O
z+<aN(j*;>ec*5pq6d+TmtG`VV!q5&O>Rp4?I+~I+UY{Y>e9#vq>zPtbD*JNL(=oq4
zf)v2RsqUXW`v2-XqWbx;56C;C72o}S+6Hi0Kz=H+5Wqb(dV$betqGm9k(*M0IXNe=
za1q-CYz3pNatB7@D{zI)FE0E&==@fpDv@6oLKR@VGoawg9GOsjd!wS@Qhib9tmsVZ
z@mR+?<W)ZA%Y$rGVsA*#B0~RHJwgXpVjGasitiNw#w=w6xDb#}{Ou%Q1GcEB<IA?K
zC~b@J0;~(|2wyC~pupQNtK5n1FjSJ?oX8(H7!>)6CjkUd1=#32jgjUB`{FsOFKVZ8
z+J;AB7<w4PeP-J)l;(v?nOyoCWKGZ=t3tx`ifsUq{^trif)X|$KNk!Hh;s>Z*Si=>
zdu+6ljKKa1r|Iz3iXDCt)tA}ppZE$~w?C&9WA%4ukkp0n6pSi>Ke(%`P%o<t>Yp@i
ztY>y#Jp2v(yd4|%#x_&dzWTOb*nRueBhn9#@B~?tKwyvY1Pg3HBz>YnPuYMN0*X^f
z7OHo#hWoY94TPZ2*%ILjJDj4nUNSWBm?#O424=JZio?c&(l9fsSfC03b)orPv{=O0
zGz>^JZtAyy_qws(Vg>O1gR?Ow6DxJ<opiBq`Xi|$JU{#Yg;4;;6Xe<eY$+J&6D7*n
z0Nw>TvZ4@BmPxcw4Y}7)0p{K#cpOqqvBaa01jw{}Vw8l-`I&eysSG9m3i*Pa7@#%N
zcREynkKK5eHuYO)YYex$xIX*OuRjUD$1dOL@w#!$(ZqH2Awq}kCRHsTR6pnsKYuEy
zLl%7u0a4;VpZ*1!n3jI8H=Ql-Mp-N<KYuU<<r|$a0+{IFH=93ui!eX7ps*MMib#M|
z=g(^~4UDxyV~WEDVT{lZ@yAR({|mL}_}3AqgU-k5VC?9xudly`kwzH5cE|1bL#Mp|
zdUUq-uc0+rAmbN)+n>wu)pOyH<R$)NZdp)fx5R%-?WU&#a(F3^4unsc06;(}`HT%9
zeBr-d;s{U<(4Wnmp^=IOnK@F=UxeiyFP2EHcUnr*e?V;BE&tYJ6q0~#AVmZ31vGGk
zP5wAl8497G4pj>R0n99ztOD%lu8WPXVc(9J_TUw-`0cMF9D%eu9sj&K$18sC<90$j
z8y#GPehuB(9{u`*(D2v!j4mE*?t(uK2+ZQ;0RKkPM;k$H=8E+M3EYF+LkP&(0OBfs
zr?rBZ3OMjf9}Y8CGOGY4cYY<13(g*Ej{{$8-}1graao~|1cY0=%V;3uEAVLGprdtv
z|4vngVhRv}g`ZJxssNz_KfutQYLvMBg-!kG_0RE_eti8i{PpYgaeBpnqQkG(U-}0B
z3lzXLej(RIf42JT<qv)h{`hm&e_aCO^<v=n59Rx65l@hX04n?p1jIIgF8)v}zKN3j
zN8e9QgohTb!}RoIFUXl-DF~SD54XVYDs_$17q1WkL?nPXRwpMYPYRz3X&|6NX0s{i
z3AF*Hn^A9*DgZspa-eVh{{Q~Z|NPJY_DQ^IH+;oJ@A&6W@aJ{-`ndmj^-r&_X#4u-
zf+dXq$Jh@FFnmSU0<V0c02^!xw&?Yb{_6}1@cIX11Cnk8$9RGX4g8KF0ROa#S9`qp
zBjE3U;*XM7=_jE@YZe32E0tgSF9QJ(@HMdbv9j#*Z!Us>HJ9nzQQ?q8QkZEEo2P*!
z@SompJ_g~#I|2W090+(B3_g4k3JO5{F#b2d%zvl966*ISxW4`x<2C*oobhr-!`I8N
z;Tf-cY64OU@amnh%+Y46|2lvIVBTmTc?F0(!88q|T7cyW!J&{9ton(wK;KE;*kd4J
z*3|}jW;SJ{R0;tk)gJ^(=M2Z5@fyYy$?uvY0R;QQ7Opa9KqS6GuD8hGH%L3p4TujI
z9Z;5q0ALd@dPwqoy8M3=4WK3<xM6{M?(44&0tL8XiBknQ42c4aLldwMO~9+?fdXJ{
z_=T_nTs`9t1`T-yAf6yASTN`j1bo6a6cQNfrxt&r1bt?c2(|(H;qaP{twtoEXpNRY
zz#P#oMK{Gn80DG`UUSrfuRmtiIK}=L_iyD8!1xNOIzZy~slU}hN-fk5dG6?dvRmdX
zUnAxKCx0Ib9)O?^Z5UqvY+e1=<~)4;^NP+`0RoUNn1JB{{W8$@*LXj*&?_Z@p#tEy
zqCdmUFLWEeUSBa{R4@VL{#Go@CyWnk0hs$fBwKr*xy8>Plm<F!QcV<~>>!3)LD!o_
z*cAD&N1YZLHEZqNnG^CZ`1Wne)q@QKsrKCxbs<c9SY}`Oh{k-3k@}nEhNIs)dFbeH
z8aJ~Gjw-;;_)s@@EccN9{V&!8XW~*f@Z$U$gVaF*w%Fr)b+7_>SmgMZSOMnL4IEMh
zK;HJ1yahh`diw+Kuc81sPY_l=$qR(V7J|jkfddQy>!Fdg0TL%`feiS!yrdf+9^L|y
zg739j8?Q#Y8U!#TfE4IulY<g<A*Tc-q9ULH<MyQtLv$obWCJ+6;9lS!Fb@5H|L6bw
zf6>7I45mwjj4?t#8*Iim#$^LR3~y+lgE!vpEwmXUW4oWi+s0!E1i@R7g+DX|=Wn?2
zw-0ZN-|trFtO)m)Dht5O?i0c~P-S&n00KyfpVB~UIIPl3I~?YXAI7$5UL*|rERfbg
zmq2SOdrrHEg0GKA04dPR=Z+<ULE8)sOhSHiBtMvHC%U7^2A~`Syo^TV!TwKr1k>r<
z+VA(v<$iDB|K0r_xQgpqbNuRj3cuTvggE@XUoKo2``KcT|61Umuupf}V-Im(skd$_
zCrG(IEPm?@w}@4jd)#M%4LDZsrA?SfZdHe;Ox<F2-XAXKL0#!!7Emb`KuN&X7j$%y
z>HnRiIq+(aus<20VK7a+?&EZPca$tKH+82k<ZQzrhX5c~BHX0f1-~m>10^hqCkKaD
z>#Ir@7V8Ou<%chJX<7;pVA_*a0HA?J&IU*f6MENWAi$*=@hdxZXpO~>;kap5VgWz`
zc-S9}Q+a6^TNuQK{GtKz0b==?GpXW(inC3zKmiW1<&QbQ!`pAi$RdBlDeuSY_AIRc
zvmhA$soq%`JV8POSK;E1X}3d^sV6}IV;is>4$Dhzb0Z4@bL1E#Lz;#K7pZ#$$mDS%
zU1A7WQ_d}P_9S))L}!LV#Fw8CpzcnWJ(4N{gKSeQ^MxFS01J=t0(#zbKgRqW|3M=B
z7BL9tUq%3-{we%nEv#tJm_Pn`32mRqE3>(E4KOLJtN?I`NN@EWE&h;qky>W*RPr|9
z8{2^G^@;No(h#sfyYX;%3=UbV0B6uH0a3mABHuYs{PnP3q)03M@{^zl4W!u5s|6qZ
zHd2e8YD0tu83+IcFr$V4KmUt;Z20RjjTPW>ApLQni5vF)f(z`7fEd4bhF8w;=MQ-c
z3H+nOh5WU5(Q^twJVBDqo5hAVS}*WY1sl-s=TEPf8ZiV+w1sD5@sAx(^dLa0;K{S<
zA%*~_1mh)6f`X87xFv|66xP80rw=EO)ggQ8$_q4biZy^n0uL6W0Dr)v+no&v{u=@0
z1h69*W&>Vz9slzJFB%sT0)Rj<WCIS67<fhj;ILt0QNoBDQ({kkFK+`d4cwQz)tTAf
z?bZndsDsTAi+@)@W#9@%>s`-jfbbHfbsr_cpfGC`nu+mmb&x9%A9S!^nB5>B>%%!s
zabDnbQ<@OG_ee0X_W-k>D8R1`js9Sd-#FqQ{=8x#|IlmzR)Fz&_sc-TUx@<X*Du3Y
zCwNK$LQgdcxv<AvRkQ&>10NO6)Y)t{TW1Sp5F})}wD8(jhq_b5WcN@vrM$NlJ^L;(
z1eBHk?us-dF2{?uF+tbt-@iM95n~ImUzim?HW-ltSm~k%Pykv9aQryIKdv4rc4ZI%
z<hmiTU*pfOKY#F&|26)h*#N8n5G2I^d^I8kfbiet^^f<Q2>?&<M%}*L?mGB&1sm{L
z#Rk|89;f45XX}J}nrz4>Ifb>Y7E%X+Q9C2GArAq&GFM-`S3KU@dr#Mej5HOrfPevn
z1v;5isVCTABtNA&E|`F@*`P{_0ydLrqyT$2RscOw01)!{kSM?bzhjSH^^5`_tN@26
z6krkMqjSv<pR@r|^4~f}tMP95s!|U(@SH&YYH_C#*Q|}MM(u%6O`Zj;gM9zy)Zp$^
z9*^~1(h!*0#?*~ifIb=k82nZz8U8m>S@9DGoq;P*fbfwAJJ`tUgbILujUfdTBRd5D
zb^Dk9KsHtYk7fgi0vNxx81;|v#@9#z@DH~?ujlFtV1?Mv+s0JY2K0#yD4gtYY#dGL
ze6*Bpy-up5ZxDL8EXt0Ebw>^4`L*C|<`qB;0jCmJ;ueUjP~Tw0;iH5ousgya_(SfP
zVE|bCYU(N6v>WgO%1RaBV>h@%!ylpmOB(KvxgGgQ$BY2-1E3r91%eFZ#j{Oo!-xW$
z9g+>WR8)XPNc?hJSQ!YYU;{7&l-hu;1IZZMscVjN#OU08BNg7+#Hm05^g2S<nsIw;
zd%4OdAq13WeDc8{+krEvhkiUSyCAnoh%I>=L?M9D?~M58*u<u?U7!FV3p9)mC<z*c
zaUUAw_ed^a^FxFGKi8viI{b{cE`D*m{k3t%$a3MI$VJ=XW@BH5TdW-30S$Nl_Et#&
z_UE`9Ngy=xHhCNH-6Ln*7ccz}9j__dQM3~YIQoiySkCjc6Z|_y4Ha!_ez11V`Pw&9
ze9OCN*%pvZ+DNQ-jsfByvL}CD<8T3ifK0*TgiyXwH|GpkWQDP41qu*`g0?y-TQ#W-
zm@Y}QKg<Oz!{9#{RRqC*^g0|v{ug4!Bxx{Rl5_xaUC0a2Y(Rx`K^I=M_;-$Qg;ccx
zm<E>EfQ{2>VBWuR+Da3TwsUL0BS>ILLBJg8N<(R5+-P?+KI6^dfLU$>QpbXCjyqWW
znB1ib+?XP7wUaMoSJeqrhGs0-p2XE|DOCjpn7Iyh1Gaj?0tEwHWJm#_4F>sb(kh4Z
z><{VvVe=^D1O0M}x^=*trELI&6Tt?Yi{{!fY8V2rb2aXE$NKx*Wm9W+K$emP!e(c1
z4g5~6E>M6B1Yl87DqpAoiFEA~aYpRpR?h_e{n$>-ay~y8{@+;wyYMiO93gU<dYLG|
z;eI%nhr4>z5*8>JBuYj&0y#iSDE%1;I!YZVw2aQ4j+!Qj_sWy^OW6RrU4TYv#9p;+
zJI7WlJcsUfMrQ4B(B4NNOF0&>MCS|YV)Rf&<<BgZnMru7Pyxc?KoaxOhx(3}I<Vus
zp*iTJt~kMlzxzAo2@dA&2}0VKMrQkB69qspOS^#X4+~jf0R$ZAcG!8L`03o2&R{en
zY|{kcPF7hP@J%a*R}fJy=)ktYuK)46t`YpZYFMGWbrhGf-=y?+k2*@z2%M29=8>Eg
zZpNy9^GgywgyYee&(U%C_VC1o03!WS!~!Du54OM}#sEIqS_h&4u&f<3Fisl70tExa
z%Iu5A4=9|Rpzy43GJRpP=bjGvoP-Gx_)v)rp!<VYbdL~i1T2!jUa!5`L9-iRPu^7C
zJB_-I7Ex-)4P=f&aQC$lBrLDOCyiA%vU8U$UcMy>pLj>MFJv&VOsHzlVh9*@en(lK
z__YNxAf!1o9JH|VutpRB4si4#C7^E^7AP3E2m+}13-;2HlV!#4h@HM`*5?-|M94Q4
z*nsbFb18I|#eZW6SY-06gi5b%Ja${f4m$N<tT+y_<{dS4I`~ayhwC0;r9nmJf=)p6
zuuxED0LB+Vz*=|+RA!mbfRRZdfRO%V-BVb=S_cV@;g)8t^UUTYdREfTn79GOERcbK
zh~NlU2OKI#AkfUeDOwNtfS*y25Gk|)-^teE6)hdbZUAI<nD5#-&W>QebG(h4f#0p^
z*ShK~W`xwF4#Ku%AYg&^$Sr1!*c-G$q`Q)eA`?_x><3Vmc)Z`7;zZUaCd=5}&q#kp
z@_)p>`eP=fnXL+q6aa)_9>5VOWq||&Jp5PU;H(8tJ|{ECiY^*UFXDZCTQ824z^A!3
zfRX-xw3vKFivnEsyRh5Wb+(S)sMWfGQEw~l_0b>H`62&{3<NBp>aCD5&clMDq^5wV
zIDc`+r+?bxvaP~N%osz!?|jg5un*Z4g1!6Uz2saossJGiJj$@ZDbb>oe=9Nq<UE<&
zd**J`B-IfioY)iO+W_cgk}ep9=0c>!AaO^XaPiw~N3A<2r>+II()DYtt>d&Er)BJT
zw=V?&blij|Pc1@SzcDOv4JyuqfT)+_-LbLzS9Xp_+}e&a|MRH7!#Vu~UiO?sssMY+
z0#!IgxQqo(r;n_3L=Zs2&XKA_vl?}kKNVR)p(n_(0Z={GOLvL_G+5CF1N4~<2>PnJ
zvvanJdNpeJ`eWtVelwiz+wtT$8?FvZK|r*ExF=8TBjT4@b|xPJq85^*UJwj-*<n&~
zPAGTTaFQRnN|tOrNT>h{$^r)`a@J@G3!K8!rU6<oE%3EVmMJ8>ugty)Jwf;y#s-ku
z!PPh0S%B;igr*T>A5lyLG3Tpwu<7r<1)u=8gEBs~Yqj^SLwF(Y{-q&+MA&l>5V^RI
zTvimMomoV26Yr4tLGou%cAngg2LbUUKX`$-Og%`b0N}A<7WhH82bZuw0s(G%Sw_)-
zOi<t&`2pljQLw+5+|nWR1X&vpN}oo3Qy~D-P@?zA(m-tfmA5xNaB4=N3_KUrKTbdf
zLsk3>2nY*TGZ3)!!q&W;iV_p>o6Y&|{H#Ny4hO?h77*ox7zmEY^}|~(cumu@p5ROT
zq?iQ~C!m}K!lB`}v{0r*1E$kVSjbIi;3ndIzEq8l&=ZVp03&_M`e6GoK!4myB(eb^
z4RqEuy<6+}?e<MobcD&k4!prs#TjR|${--BTTVlOdoqT0-ULU(0Q`<1V8dzRZD_mk
z&?&8FyQRB+#N?XpSUdA>KI5^33g8hIxS=~m%UIwP=sgPoGv*Mb^yI*9k{Qz>S<L%5
zkH+_u;CrWG|3H@Yk%p3=No#Rp1F)7%XS6bGb9%H}f!(O9HT%+0Y7ISoFV8{1B3%8*
ziy>eHrNktG^AHx35(uD+C@S;GdVTBdP%m98pkt>sot1=KM|{)b#WFLV;7hVp9TR(j
z<Z$^i1;{{vITIeCX9esy$rNXVL+A-o2ne?dGj8Dbf2$Q^3$P9Nj&>E|+r7dx+coEQ
zz_M?jNg?wxuUQo#U=eN?#3&CA7Fk)Nu5FXB`>7}uW`LDDZj5;G=PB`VI4rMcBUOA@
zk<FM~9~h2z<v6DqPw<6`&LS)j+J*xSFv}Exc=+j=<14@{$?=!PH8Ml!3C1gx9}h}e
zi}%Coaz+iCEi8Al@s41(!+a+AVp#}a#6P31^kOzQF?S=C<i(v)Od7~3!o`g-+?1Xo
z0q4U9_oE*!{%e|WxV(0aX;1Ja6dPrMs#Gj+O0&Z0iQ_|nx%Q=bUv>eAJi+L@r#<dY
zQKA>|){+@hW#)ORvZq@d7LgQqUn~Uyqb~6DEz=|nvPTC}N?2S<Oa};WOWb~8xZfF;
z(?DaLH1K;Ia!U8$IHze(Fj9akVSyjV?O28d(yVZL<!}_Bd^2{z5PE{qN}cj^0vP)l
z>Bl}1P&CZ^J7_V7#UD$7^TnwlfPlq;^dMrpM1dK-lhUnmne=B-nt1CU#VZ372^q@d
zL<+!BR8;B-Mhb8yEO5L%X)-L3fq=vV$!fq~iQf==f{~nheVzh9pW#UQan$KS?cM^J
z>D}DVLcrqSi~#`BDL_y)|7d?`GN%^G%+3~@5{b9jur=wz&0fzlaliPHVyuW101+05
z4FG8wTdn}aolG}WPZ<G;Rt%-jCGrHr>+$4Ie8YH2UZXJFJhXdD*G;1&Pq8xNk`12D
z79N!8=tDIVeg_DU-w-V^1J3SV+B!12?R~&aM;v$=`77fIzAysyC%dsE3#3`$Oetcb
z0A}?~xtt;L1jF3oG<RIoC$soN{|wt`n3h}wG`9|gNo|-J7Dq$zpAMrmeT7?;-}CnF
zvcS?yhr|NX2uMi764Kq>rKB`cOG$T!bbh3yn*~Kc>FyTk?tJ;a*Y*1g=9+n)Gv}VU
zXYM0$RpqL@?V3&!=iZEvccvriKG{&r1)?a&5?wM7ywbmseUqO(t00d|Df$!%dcZm*
zol#BRFA)IP-`FZW@%gO}@&8REin>F|(}(C$R!cts@eKd|9w?-Ji{cPsyOW%%4dwCw
zWFoZDYaj5(Jt~rTO+qi9BB6K8vK1%8m6zi!;8_}o`JYt1U;)uZ|J>-oZWFkUg*fn|
zqUfgw_vKIZiw8eWYiJSk@<O}*0sbnkZV54h-4L(QcKVbZ=Sl!+F9=<X1-ny$87Wrt
z2?O}RgsJA9M9^v!|Kpx}&Xn<0z0yOym7@R7HKCT^Lw69uj%gRH;(T*w1A_(5QeUT?
zgq({?@D~A6P%Y44gCGnWi0j%jCg`W21S3;Q@RP_DPu)7BLmxwI<}PL*jZnaIJPctV
zVHbNH)^FPj3T@7O#i6PYK1cTp(=0J8{-05@Rgk7SZqCTQIQhoj*ce)+-b#PplikqY
zW|ouE{WOB-gJ*Iulx^-F?KH58jAS6B3MKvD5KY)ivao7Rw_3LpKM855V6hG2Wn=%`
z6o>*uJ>*`an@qW&Kj=RHBMgSH@Dx)0ahUsO3P*(2NK-^zh)3S&b0Ty@=pziMy|2lA
zgTI5I{7A|`FpZ@=iNKqTi9q`2LQit(UrJMNe?1u&Q&X}iTvw|GavMD|W6+K~VSwc(
zkjurgM6hN+-DdA}*ZTsd3}!$r+&3SU21SrWZe1t;==n9SS&DD)>ABIQJRdbUhrx^W
zw2vldeQPHW3piQV-yg67tTe-8hSxOUYUcZg<(d@&)CgQC%Y$T8@K`kw{zMl4#1Bnr
zky$JP94ky@QFJ{|g}d{*b))2`A-V-K+B5YxiV%c8doJS{lmz3?MG%Mp%WOMOocv*7
zN>Y_e9nf;V55LrI6E0SJAaToG>Yf4cG*%cKV8|HCr8xiJEC6>L=5RGjpahrbisnXl
z&kSBwwfo*PHfTqLWE^>NOX5PwQV=wUru11f3dK9gTZm)r@B5d?`|-T~Af^`2ih)Y}
z9Vz&gWVBFT`e}0m-CG7@$C5#u)I0d(m$$unQ@$i3A)d8U(Xt;e<T>ADKgkpD3<hmf
z@J9cmtvqS3VS=Ohc8-od*@}Pk9l13L`bK{RzWzu0IfFpjWle)7q-qZ@N*{*0^e5`U
z1?SzB&P9%Dl=x*&p?`2%ewG3NI4#oi^VsX{4cl^>r;NdW<Wu!f<Pbw(R4*mgTSrpT
z|4x+igI1xK!E~}h;9Qt2Q&=vnYnpVi>6AzR=vIapnV*dk%I>22Gca0sz{Kl^xffCu
zp%VgNtQ+oNy#Q|tNd**SK3uqj_uV`mnS3~|QF+|@pzt5*m?ktKS4GqN-xzBwQA$Yt
z`wuW^(336E**3MK(J<l95K1x$YfK6*vY2VJ4&pj^wBO!oUxzydE;^M2TF37Ve$>28
z-{4Q=owfOr0iOjnx?gXEGXlPnoCVu-R=I1~nu!8|^BBX*_+Qa17Isu5T~pr_1euyX
zSAG6gJ{IfS!q*+}eg^~1_CJ8F)i{pRe^&))#R3`qpnoaOJ|E=9!ljf?S|*?gJ|tJV
zBC0O0(#I78t$9TWa?K1Lcr@gTi~eLUOmlaxf0G2*s%UBw1;cjf6Qp@YL(!_c3PqjY
zLt%2CBSj>fuUvaVe#yc}>|)SpdOjd+gCY<|qax>ZqFSBZnuuP)N7vl^rS07^(H^yj
z1Dk5pi4>KhIARV>4_yq<4Wma|yJf_OV$b9R4kq<Ix9R&BJpg}nUw6|Sp<h9>46B_y
zJJeNTjDw>eblrbC2I0^-!cW^9BN_fr8gBPBFs@;xSX81NaZ?g*_F4LO7D?cO#zErM
z%8EI6+bCrSGagV<<!hH|UHU~*q+ZhF+#vaG7<5hN0&Hsb%CY9T)!_28>1z`2*R})J
z`uQFc1#`F2*N_nx=B#NA$Qni6MH!hY*NTWgYgKx{Z^EtUJUis=g!Z2DdsU`PYg#i_
zYDTwi=;Yb~BdynRbo|d~Ib=*aG~+zEK~nVu_0N+qd->h#?@0REBVH`6GU|rRTKs2x
zE-Y^X5V+zdW&w`n55KoMZ!n5&HTxWzYc^MS)4Lg&Hmh#1jI6db2#$im#kqO7-%!3K
z(%4{X+b_QZI>5_8r7$wBK0-h9Yc2GrD<NbrQ%Mg77G*^-c)>7|dR-m@)v<U@Q|INK
z^J{ahCH6}7_u(5Ne{lx_f{4JfeY#UAQ#<R1ntR|RVVaUS9AN7x`bElE<pCcIo%DqM
z&l4&MKu!TEMG&SnkWMw>Wu@bD^QLURL^3qhI*4R`-=*Payc#}8sgA8MAIhYI_*(xs
z7SGgJy^BY_p^FPt3}UiNT=tud9#DLtD+^Sb4X=AGYx9rzQgHgqVRnDG<s(hYF~(O0
zPqZjkU|v+?$YbYx;G-V8;DSaEp%s4qbqF#18DjZBi`C#%tlKl&U`GT8%#QO7gHD++
zYuy&cA}4pJvaGIAYC_z#A#24-jrhdf{v_xa>{EM%orQD!cpYwTRQ}>LpzVCX@{kS&
zEjVFQs`-82hhjlfNt8_~ZPpZ2h)7Qg$j=gWu6#X>uNS17z6KecVA-WA!}CIYWo~Vj
zcb*tK>9Z)b*fi<b_&U<`^GPYw=or&pLd3HP5mRo_qv7J@BYYpmmYTT9WHwbGG}Ne0
zJhZ}R!DqkzchI>1eeE2?ECi?K&)$vF4n`eg{&OTTQoWfL9Ag)iv3ctTL*k=%lLfsH
z0_uog{p08dULS>@GYL>u(rq<MeeL>!bj2M2EG|%z0Ui$0DwA*7yOlh7p5NNnUGhk}
z<$%@l#hQLTE&DBaxHdt>&#6c>2uPiOBs!WGJ;T`}2B3xy4*k<$H`C8bEbf&K*U72d
zFr|9|WG5@3-Cx&M9E2BtFDl-8qp+oAvVUCXy208p;?}hlV5!^p+E+TGz3a`{R!V%!
zJF!7(ha~3w>gpF7ec_9bg^<ZeLDh=zJQ3|70-43X=0Y<=F$+w<@yS?B54|Z{G6s>O
zCKx^PSbZExb3bx%3izh;jsGK+sivLfb07fd_JyIn83_cy4*BpH<}Hd@zrHac%t}6(
zCx!#k?w3ZLsJ7UU#0yR&IzB(W9KS<PI$1*jBgsQF@ehV?bbw;_Ld;0BSDrCTsCciL
zo-80Qa~hwA5n^#=Tx<I@;vYwLl|Kli3c@3q$gYl~4Fra1`k-rcm7(6|4U0;ksHIOf
zUAuMYkO2i+en&UD=L#?w(0tt2lP~5NBJ={SVGHZ0CRW5|)31U+aBXHmu>rA^SAjl|
z1Z}{qz59hs)w*Ug-hOXWlbEA;(<lrvM;K#p&qdXt_7<GczHD=tLlH~w#^eKufYZQW
z{OjbWG`&sj^@aB(C@qf-vx-)Y7T1!08^Z{%*Wblj5U*u3Bg5ky0lQ@SGaM=upqYsa
zXY<w->--M;fTC!h=W)B8xYHF^81+TWLzrMs$BiNkVRyPP-_=+U(hLQWWyjN+X@Y@J
zudYKDqm1|0iv7f|u1xBv2!4lzQoza)+k7uZ0N;pp0RG@hK&|M{#0s4BAiypV$CppE
zytyELbNp?SO1qAxkjf>BS<wrsJ>SS9mH-e#2f7=1+8pWSRZC&8_qW?+bP&L)=~Zi|
zdtWZ>CNPnyC3twOkpKL;*MJhEglMh387u#YXc3SUTu}^AC0?$x{H{m$sI0!=;yU@L
zrF$y0n5Ysk`p5L;CQ@=vm$m{yB4(I86;oa`1T@^4{DFmnt;vLA+ZRwc0KdD>uP_HK
ziBQjiVlHI6#e&{U-Zz*9^`^$w9Ca?^Wlp+3Xo}-B@MW4e6t}t%bu;UD_E+3wmGInh
zuu6ccc_4miub7+@6S~u?SE(G;A1YybkNZ6bP0}@c++*!Fooe#aQ5ynYsKO5m)f2*c
z<S~c@Ns87_sKkb}6@S@yD57Tssu9BK<!|!ffE@9-1_`sNQ?Cw>M^7wG@xGhvR8uf8
z*l&=1_wpCvOXie$-59sL$;X>HBneQ>6MzB?Sx0n8IDgZcNr+0=$ol0FZA4~yS&{yK
z1OItF37|28SFA_k2BZ*H&VQE<>9&j;gm_Q=bI?6j0je(hT6S!DI3V0Y;bBSmyUY*5
zAFCD}SsRC0nw0G2aF!To5f^ddLxSjsDN+EkE3uNG2Kwp@)Y8vzF8X7PQsT95&Hb2b
zNckjTSA>=|B*CF(WN2W;!`S&GPW)R8iZ$Ycnd4fsyKTE~?{Ru4KoO!-E3}!KJZinD
z(z&t|bBGl0^rEK&IJ*_Y5I4E;W+TG36+|GpuXmJou+l((W~>O$U%%5)w?unlKo|E=
z6iSK1Jgt8>-Cq!>l6MeP+?=H;M-#0+>93!Eh(Bgea~f$#c7evoXSPlh$Oi;9%Vf=X
z#j!)Gv{Hfq32P|p9vh!Hjj@5|jZysj>wV%Ls%0PQ-Wq7ZMjY|e^$S0s*6N6A;PX=d
zp`uA9CsxseSw_x2b&cCGdyegijMxl!nKjoG%*HJSHnvZ_)TyBGV+x^&V1=~UL(2Hg
z(urlkU8FP%7^#9{us?`3ID$zF6LSX#{`jw3BuAxR%SpHEg5e*A4blHjp+_jon!IZ|
zm++RV9)QXtv9(LGR9D+is>cLrxbMfMTs)l@c^8HLZvnN$+&n@~%f~{P2B%~n{o0bE
zNCAeB_U~o;9IO}(GsABd3gcbIh#w;NU{vi#E#cHx<thR^U!oUFK(<hLGk?%Ofk0y>
zx@{7Kh;8N0DdF<_85#7d$!dGm_x@o;8;k{Z-36o5l8Zk30=lw?d*p1|U|=mG*`g@S
zEVZ)r`c>Y$W~LK&ajNA5Yb6QfIkP%dmNsG<^3Fnlq6ugfD91;^j0N0^sIE8A49Tw$
z!!;@M8BaAp2|?I;wmnBYkxIgQ7-_Nl%unAsTi&6$AvD`(c9=gJDEC1D?ME8Q_APya
zMz3n+XoNP-q&gnjpk6#nCs|=-IBGh;E?+kd?7|h4I{6C|WndJo*@rh$x5w>Nq9<<;
z@w5ag>z9SR2c+!;(Wh^k_g51*a4bvU{M2V$X7$2Nt0%F-QS9I?ixJ=PxV@oA8Dmwa
z@hnn(j;GzP{p+<$ghSpymnBw_J2VG?175iu3MQ=?P1Eidsb*oS_gD*aPkAc_rKK@Y
z#!&OtzvBCxnh@Ya9r^aem3A%XyeH9*p6*IZdL#)80K8T51BYPc2AdZZ=w{N-CZW!=
ziq>-H@@EmZ*YC$hj`j<bY0w1E0VV{E3O_Xvfz1Msxj!Zp`HbIoMt8<!)&Ce-bzJ@I
zOH&eO@^p;}I|0`R%bV&oaFVkjX9UqUg*<h{=Nh0Jtm2%M5egs7+!u^W7iqcL8LmTe
zNdJwv80}yLn`UVuSYA{R_^{E@lV9r0qb^^WsHg^&Yl)22%}%!up23Q)MsA)IU;@8F
zJid4aTY84ur(eOi+ONu%d%d0Ku0Iu(zQ?S6XM6r9#4_IpS_|bG+Zk+Hn%p)sdjH7L
z8aw_=O6B;=0O4!duYZY=dx<lrxN`sk+-f<L_t3SY)SePe-B-(>34I@XfF2a-cnom2
zA?yh@X^TglY2XM>2|Yu{)r>F@3~v-Ft&yq!LTt|VD?@tH73#9~!%EK`iZ4E5Q1&*!
zffGnpY3av~^NjzsU_@Ph1LF(o+vX0C-xaLbcea6x(kKxv3T76#!^;KkxD7I$<?RzM
z(z$;)@d55@TvS(sUX~Xmyxf4`1h>@Mo5c*!ob|>(DFj1tP`2GUTUK-yl9J2f$QUY4
zed_K)^GU${%=UNiOZ~d~;?!EZ>?_%C0c8L4sTIn#T2x=Old#*rYS7*I%D`~`$7yL!
zDs22mXC0=C7!4CR)U+WQ_n&q6q2?)@$8;(Fe%(hVYVgucYs3y9Bbi~(0(;$xkbdk|
zS|-N)VJ7j5(7|?=mzgS8MT8t1U_5A4EK&gHow+~@9nO{nK>A_7%!$x9;1{ZXqhh|t
zl&HbV&2}(mcSqC#CoO^zjCm0;Sv*oIOmvxMKDD6m_#=_ob5jD)EaUr*>8JSa=cN12
zunx1ON<JaySvF}fA$`yEC)Wo%T;LU6DU7k~MLS5^peT;(DcQwEn<4{_^aFnEYB+J^
z-wQ$3kW0K02HC_Og!FlF%Kgsdo+xvEcm+X(!cX}H$RUuvW2sDyZ&ctWPa}mTMs!e1
zyGP{1d^OX&zRP%*q3%NVeq&cxE_d0gOQ{2B@$;lEHTJJIC%8h^(~vp<8;F4Z-+y8W
zLFA9P;<i57k2!5{e&px$teUQ9PL!3#d-{@+{~UyNqB0i%F&z6u3nS>p$wjD#m>l8h
zmL4zV)c*_hO2gvn&>UATQm?|bXf+XDcC*=aNguMx!9aU6AeLcCkh#Hv^oplMlsNYO
z&qp!|z=Wai?0Xjtdhf^P5dBxC2C*YM`@RYtF8ejaYr7oMTlGw*KHzn;wq&l2vg&-4
z`YjHUXl^Q4MF%_hWW-fs2uN$R<eCT?|FRa~e@x<NZYE}qojG>AB%Gv)Lq7LnF3^8M
zkiri@V^m;vP6^IeQNA4cns&@gAzJ@^x~*kq_WD1529uUccZ_jDiiF1;dEa=Ve^i@C
zuV3jrto`SoVW)C-4{&?WZx@!iREgvO))30EUS;rv7Mqg)gycI(e*C;0lqb->Bd5}+
zInQ5Aw6-5D08%3-k!GOnNoF_0!#vUHmKf_V=jZ%9+&g3X-t^n(^tElC!<g%H5J=7*
z{*ha%dzADYeLNa!<QTu=S;%&-9{<CFY>_pI9emDxJ1ZQZlGv510dV>{YO?z|Xt}yV
zj(b0=Sk!pujAyCsLo=)ju>Pz@g{|d9$O7-H1GrB<EV^!c7<jyK;X0ipdYm|bMMu%Z
zQ&WojNu*|9pM7ySgvi=T7v%DS1q4q=^CPJ0v)SG`Qk~dF_XX;0Q3i$eW9)6}$Hzqy
z3Xm!uC{KTEoVkN7p7AcwTTu1fIdj>{`=T15>RqmVL2>m{gD;@UeWgiYMi^)w)RWpN
zS5b>hd4*Dtfq22f3p+d45`80m*{82%wIOD!frRhqZD9yBo2L2WPwMtm?u)ilPW089
zqfI#q$MTHB`DeAjUILCMIh2Iz``SkNs{@oeSu2S<5r+;D<8@|0#tyl>w50!9oF{fg
zlQQ;n!4Ml)Ru^|mNAvjBq5t{$C3)oYD-H?e&HA#I+9CpQ@pK<cQBc8Qci)O6-K*l6
zVf$uc?;<o+U|PXVda--_e6k4XyO6?vOQh&&BuBTE?>;)yzfdyOyhEOGB7DQF$i3tS
zY@>vDN{O3dX}KAQ8ERwcWGjEUJ!aFRa*byH%(HSPOy|K2<<6H|JoQ_IU=avxwQ4XH
zlk;$wf-lZSIkgLOUc%-ujst~Om5xrD%ndWt^(o%Gm*6S)%~TD#a`xyWn`O|4Rro~&
zl}iI7F77AGL8+3+CJ=ZiQLvX4kyljxp|Pj@3p+M&d*FA(^Zk7?TF!GMXh0Ic8O!V>
zlN%wfecdBh7)_P^3Fr4b9=Ql^Utng^d91huiro>$Ub~YV^JX0*@kO2UeJP3AVRBZs
z&s76k0cZ@RMW$%ZIT8k6l$SzMdh9V$dQ;e8W-%L2=<lC28dP=Fhm65jj#8O^nG!*X
zC>7tkiXH5YW+6HYEqM@wXMYpw2Gomg{l%9CW#64p?vT%<(=9p*N$e(~0Yqqq^BIUC
z5VrulQ(sf~*&HL`?zj5L(p3~20GJXz2@3FSXKEDM!lVAz7R3i(128^yjvhbU93;E_
zehPbd-ix3+{jMb@`%npDPyCPfBMP&<LrfBRZhvIcjf>&L5Q+|e8J3*^@Fpzm11b{f
zR?h#bIusO2Jo4W3_6);UY4_Bga9SkcLN(zFBEE_U+yZ%A%Bo_lFqc{u^1NTPySyDF
z6c0i~``te!osvS4!#81&1j0Ze?s{1p*>12*(M%N1nF!xMb+6F~R3k+i6j;8VJQw;7
ztm<$wz~g<06Qj2grutu0#oU9pnK6t_6x+|a!2r@9f&P>?Q31J|dF=1|zCE{dLdCs<
zReuI;gRU+_z%L<WFnL(79lParnpqfDC&F~4*%h><g-;c6mjGOZ`+O@&?P^SF?b=yc
zrw}K4oV-k_#nGKGvs;2E(I9TURLl+`Fnd+W-^Rre_-Tj=N~`YyuG#kNaZOiuA0~qJ
z>t>U<5ywASmp9er)ndO1L7>x7Ip+KsR}d3B(yNHq*QoQ=JFntLKMw1<us;G4^VIvO
zZF5w7V-$xVRW4kKVdi_dU9sCB6Eo6}#!2+$wE6Tf^#w^nGAtF3mxC#CF-qJ#?dh@Z
zgJ)*{lY3Z0quknrE0!mAjBhHm_+7myfvG|uf5qKoqvS2lVHj)%t~}cr6E5Q7g8xbm
z1X%v-`|C(zq!sAvjLu}uS$I`>^WD2Avu1Xs_3o?=PU_kCj|c%rI7QH!b-{HMKg<Vh
zdr?sJi8iOUg<-hV$UR5{Ig(_3l9uuDoaIw9O-b%ap=!BMSO{B`C`oT{gu}>)kC6)*
zpL;&kg>A<B4qLc~kXv`!e!!lhXECA%kVyDZ{gl38pH;y&-Xj$S$Vslxgz3U7`$>Q+
z6mg+5E_eYoG~2$O+z~hwLJK?~wS?S^Gn(cxY%mq%hbxhpsWi#-#l0ib=lJAp0(=Rs
zBt$PM*ru+IGv>yYcC*MF@sp7KgA|ELxqJL2^|Y*<b3=-#YGL$`ud(+na?aBfjmQvb
zI@#}am~aOF{)s##MjJFxMlV2(J(QhP|5&*F%V1HV$qFxT#q68oeP3<X0K|(bwUTY$
zD5j9N`CuFa7SR5K+W#W_f~|W*R^{3_iR}$beLt&H==nJr8xfkwkdVp++ILScjP(8S
zU!)YYM6rO5V^!<>(uf)?5N9qGYwG~D1mc0kc-@p#gb>)<)0QxiclUd~_U<>k9nDll
zrF^flyn<#{2(^?R32^5^3PV05g4o}Fhd9l1eaq(-Ljl@rQWNF8#?U1O^~#qfWPd&+
zxX^V-;UmV|j{TX)vTXLD;JPhpa6ddNGe>YCHvGriS6B5=lmBds;%M_r2AN+d;3<4n
znYUoF&zK;i{i<=tSurO^)b7fT*jmX9(nhSersStmURWJzHJSxz?D<w1x)hv+8VA8;
zgIf9!W_bvaB!H?}gztOsv@PopHEPIBbav-#ZH}Y}$$$%oY@><&cl?2#P$It=uMcmJ
zjj<+?ZT^CkQ1k!|%=~#mzSK9=g81MiO(>V_+`QC^5Ufgc<ZD|bW7I8S*}dW~%#cu2
z@(?W9r@3ls4)g(;oZEUAwh)AX(aVVFdko+Q$iT|v;esVG><ZkP>&zNwo+dM}6di=q
zZqqRJvvRWfTJJ%`1c2Qq+!FSBY}L;$c@TDKhz}l8FWUTCAVX)@oEW~)_@$6`O~iFW
zcAf7$*yxKeU6CdsYW?uNaTiM?JDBJ-cnh{hu%*6;Bc}Nd;T`OYal;*Bt(L@On(v8q
zcaxKptTfolA(bs`kEK+SgS%>9jOikNIP>M{)ZB*1>|I?e6hWLHtsAIYu^N*VYa|C!
z2o{%luA#w_X_E<#V@@#8V|l%|lVw^`2X#q32fv3RM;%r>0;oX>>(NGK7cqurYd6ZC
z?xBeuL7JUk9<)#xf%F~H`>YF`XR&k=cjjH^n?D9vkq++hFthVSIP&bjF4UeDd)5%e
z`a}Jh00yat!L#QWTv*1x14hxzi#^(F^(~IbjtajIFIX*t5X24T>i#4LTe8VQyZT`^
zRs`tkRnH<ZY0*RZHC)R()&^#pxD4p^=kcVF>(F>Ra_fD9HF-zLh7|CH9K8O5sOA1i
ztt<m^=src7&VDeG`5Ml5c+JqadR-V|i;<_Aw|p9b;$IE{{l07Ck<tKK5rX_6uvpo1
zC|980r5mr>4#qYtU*OF_FK%KS$|qTZ>sA`CZM)ZM2!C6=@4Ww91NhziL79I(T5i%e
zC&o0y&_m&DQb&Z6*dZ!Z^wHCH&)%fWehE^~Pr3~cKO!wBEZv*WQZ1$)bclHWlH)xk
zgdvKIBoV$EMY8N9{a)uzr*BmwnRYP7L~-CRfYocf9W$+8IqdPqQXc0^4PU2I9C`<r
zH8%>?KKyEum*OWJK;HbLOa0h=@68s+b~@m)IPG~air{qeLa%aLF}Ubds{OqW-PKrp
z5^V(_2?K}=PI#a(smc-kj+MwXaPGuyYo7|nF>hvY#ar(=R$2;ww&~DOR+?-0^EXEm
zz%4uXsh6J%Ks6w0K>{+%%;JdvH!ft{1&Po|2!hNmo?D0XZzrE-*To}ET`aMu8ks3{
z6q3N_tkg*uLF{0?*_$pws7s5L13=_fpEb?+<F?r<153rH+BY1F`4K}pRf4z=xZL&R
z1<X{~JS9obbu>0GL}}RZHpB=Rff|@7Sy*wYz4v^1ZyLYEVi3NQ&p{!tO8my~{WM{8
zATDt6C4Ek1PTfKF56k}zW31}MFx^mnJ)tH2^R6}a&!i>B7vpc!dqS*i^sgG-VRH(`
z_^e2F4TK1ok`4l4laf(~lc~JXGsi*X$VQ%;F5~K-YQ9<<rXw33S}BqH`AiM!4Mlt)
z2@DMb?A4ply?qG<DUl@d+SYZe-iSSWvPFc4M6Um=+)KS#y-D6IzT@0yQ9Gsi5!lLd
zsYrz6{gr`E(FcX=A%kQ>J~zxbqXz!qA!!W|=V#*#?2QO!@Oa|TXD}h6+SD~Mrq9q_
zf2qodB-z6NHzB3Z&N_R!+(PYTxv+*SmE4Zk3B<-_m7mRQ3Yur=%XcBum)rtIpM4#`
zyxl%x2b22dIzVq`bWE<uA3^Jg-w6T#O%b{qS)p>>p+_(U>=79cuIM{SwS(xHS5tHd
zKr=Bnn5(i~<Ha&;FG*jo&Hs|;rB91qM~2gqN~F~D>DRw}8}IVBFI+I{=fGLoRtv8b
z9oCQ(X2j0cf06S0p_v-^8stfgPkH_l7=VCVk|gmv|BBYRaMJ;vsPjTQwXo6#?u~x?
zJV$b^8=W!G9wyDib-y{|QPu46-?$|FxtgJ{r6gG}>Pc|hC!M|$i5L*}2<e>m!dL<T
zm|>-0@bu|FW>lcR4zQN|B$%b2G!(h|!#XVx4LvPBxP_CIJD7AgxYrc|!y8JduTvdU
zshiDl7l59e1h{@PmNw@}=d0;swxwksinaiM?J1~)d&fE47rwI}=BH|9`O*8*BL}j>
zP=Mbbq-e~V3xMk>58d*v*J)VjNe!buLdrxiOAO{%f{Dlfd4lrsbunHDtu4XEzf?xo
z*MBbmy+_?3x6}-Fb>r0#I#z)0T#=_HA?j7=!aYSpNM1Z~hoF|wnxzcn-2u!$Wr!*O
z#jae+Oiq&LfoJpgUCSBC;kK2mNJ8o92s*=Kk}AM0&wrRCyoNiYp}T!~5m`6Ot?KI{
zU>B)wI?U`=2lDZG`l{17(&CwNFSU6K#0qxpO4i3xL+>-y7ik<AB31kgU?6*9qxQw2
zN3opXc8f-f>H7|};3C`I$H}qh_Z`F*rVStkeOGP;(m)-ZQniQEE|zdFS`~uu{aTY^
z5s67w46lRnbyp7|g{pc^ZNNhQ^07sYge0&xGgB|-#;dC)u3Ft-j=UsY_zS}NL@owU
z>~Cg&p;ZjzjR^j_6IMQy+);#FOb<sihThm#aQPS9sMgwRL4ffZHjrT<6{EkyOFNa7
z+&?dWja4@+zW+P?dmEDZri5G1%l`jn0nDv_I}o5|U@Q4UO|v?Bs{;w2^YMntxxwd1
z6N;lUO^0LpD!@hj0F5p%V@!NwUofEG!-v@gb@?ndg(qLZ?I?JAAf9E8AUcotba4q4
zii})yRb^hp{#r=LTI9Qw0!MtCT}Y_De4SK;HC5fYFBq%9g7ikJ;9Wk4jBP1HfMis3
z5P_J9_O5dL+6a8uPGBwx_D`X}rD6Ms&@ZH@)%jXF-oTMy7Wyahef<o&Q(^Z+Av(xF
zvKU9|WcY1SpScyMFY6b8ZXo@aN0>Plsht&FM8~0K>@Wc;S*#5W4aQw)Bdp+oiLg!$
z$FWxuo`!BgkMNg}y9cx1{yAo7EtPymMsjm3ZxDR>5{-%So7-mG%kcK^P$18ye(`FT
zV98G!66i@+a8asAcxuDRmS4^+vJgJ_7Dt*S2|HTqj=HeAS<AA%0Th$Tz<s89#uV>K
zla2cYK^TixvMlxy%<*V){OU!?|Ms}PATVXPXw56MV7;&xvBB+Yb7zf@m~Tra2}~gA
zCId0o59Z<}*?wc40fgvwNgQ*a0#Oyjyb^_L63DaP06}eIbL?$J(m=Fi{T<XK39Mkk
z+wkdQ^cXC2gE<u`02rk-9cgU*wuy8wFZ5}&qD;X{J)7n=7K#YQGSeg{7Erz<QlB{h
z6DZp<tCcN>-QVm-5dK3)yAtRX#FU{RTg8y_0HY!?Eqr{#mEze>eT<LKf*64!2VavA
z$^;1ihdn40f`lLo+35l&E8c$<4=_l0a#0NXf`y4v>`qf^N&-q!NIoIVej#a`+bfxX
z`<5XrjD&i9$@lPjKX7{TW9HDWA7AzAGdr+Z1Ep_k1-OancbY_}_GF+h&4{SyXwFI=
z@K_EPY41Q_EDW}f8H|s_Yga<`=l)T2!1;>$I>{DJjEQ1Z*ZbNe!3!K_O2)yM(Dky2
zzwYo#U&<c;K;NTKi`^ZSelX}^MQnw2CVVrP3#}78uF*`nqImr^97Py(yfc1iqBb!X
zqm789$QJto5R%V?A+E`4Y1wfN4R_Z#$%3R@%!;~pCB8l3GrjS~vX`>B;<v13%>n5{
zPONBQ@(_m{`#Lo5X^Yx2_gQrc-UdvY{koWLdVkF&Z4t`cpBg+^5efkVzkZUu_8oIX
zGbu~eL<|C+u%z&@fft$F<ER*rP17%_w7Tc}JoeyPPBJkElc&)4OYAG2T+tLkp^x8n
zi6>#?=dwAd`Xq2d(D_coueCjR8GNOy;81jI&m)!KBiGaSmF*w=9oiz)6dV5vZTkmU
z;qzVRFTxy-Tjr>GY+w4-5s4%wSqz8@Zu9(o8cQA}Z1Ul>>}n9g3{VOr(M7S_d1jx(
zc}XbE)?gc)+?_<LA(|5cm0|use+l=&*tV_ZfdZE$f2mjf<ov|evI`Arn>6v(F#7mG
z7jNPs-JUnDUmP-dw*f+*oh`?WacRLnF%g|eeEg<C2E?EdHF~n83oocl+n#Mf_ZI{(
z9Bpwga%CIo88SlS;1J=n95SI>kYJ4|1r1z8e}1>Y)ZHh{=pFl$5=Fdgk}{uR{zpzV
zHgnY;lch*QANW@#UEnVF2ds+5=e)*mw(7aJclU!De_s{X$=jOWCeS$wbt9`|m1~pU
zL+fI}I%?IIZBEh}%%P#*PkLXfzGD2TAls3lEl2L;pZ9@yqmO~r%a_*N|Avk`@`@zz
zbbmDZ0KN|aINA?Qxlt210jK0}<jnXTwWl%=1jl<V7ibx8S}N}L$T@wvhM%?-Cb2Q?
zU$1T(UZKI>x0zV}iQD!h@tgnXWU1OKE2`I$&L=)SLDV$PgGxicO~g3QIiOs+q`>={
zv2I0l?tp=TJp508DYA$$uwS~L=eyjlFDA*#cB!i^ml16)4nqODlW;f$K{sGxZ1ntb
zrrX_kzX9A&oB@_?gtmB$Aym)m@Yb~z-T#!U?rL<Xfq>HB(0lNrlu}&bj32rWVU01H
zFmJ&u+m@}AjIe%i_9P!Ad7C9n9UQ}hrpAnzM^7+4{*fyt0{3A)5<c}c#(NzFD{CCO
ztnrH}8~7#7VD*9jr<~eyDhI{Me<)z-%(YQPrYu^s_QlV%Dg*DyX0VRZ(g(MeRAO*<
zrp>J<{|XxfS39*xNB%jJbVVZ@fBs_tk|Tn54G4;Qf*+|ZzeWJw%mrc$1|fm1bj)s#
zY`R*gk=7O24+bn+>glr1AqYO2DT71V2?!8MgL&=mNJhi({l=R=vw3xZV`sX_)wiUc
z!H$0IGK*ZGP{)h`{J@v)56TF3VQ`R|ZJ?D#72lK0uY}Z9K63!H@j>b(Ot2*1P#^oI
z83#z~n^9UbkKz38&oo$lrwE$(EL!N1BXe8lS1bM7*}>NjPKN)1Pe<7Dxcm&fn!!{J
z9Pca7WD<vP)YJk0G~R>1n*f8}b*TlGLy5N}^VPr%)q&Hj7(pchN*j#$Ab9I!-JhZ|
zSHs-IAS#Pa8u>wAck!W**hB$WHt|+d{KgpQ4#D#FbzMRd9gDv?#J_T^@-ad@{{Bgt
z*RufBg4i(gjkM8NeW;HX)3H<tjKTq|;BvZ_fwQhQF>4O+hJm75Bowaneusc~r5uJ(
zaYpJn*`&Z=8A^=3+1KlWr`VQTS4NRgfnmn*<C-)_kCH4a>vZw#|Cwo7a!9kTKaHh1
zpDM{kM1jh=(f}<TaMhE6v4#MR5WpUODRs}#<?36HV_`y&nuq!(xjMvw`&cpkC)CvB
zVfP=E{6Z41SMs18Z%vmlWK=ZUWpydxV$CQld2r5geugb^>GyA~nTdm-qqjZBb@MmB
z^l6p=riCD8p0uutBiDI!@5)^s2g3w1wP}=0D9k<5`S6#ihdM31JgM5s)KJpk%hSPX
zRREW1^}z8BgV3AFnJ8nj7QQSD8kdZH+l;fq!K~WPn}b{R!n7uOY;gwje{I=l!j`Ow
zeFmM4blNA6PaC#@OA3$UCv}blA6Eu`M#>PP1WaEdQU5S^cH8WXY0$O~ypX3C?9<i_
zH$7)09omq&?-MIb$mYG1sBMhU2TN6>@J?L9KK6aG+1xXGIX#=J<vNq{PeZEZ0k`ve
zxv%ey6*NC@K9dFd$G@hA-->A1(H{GV`t7&ps@$Vtyq7p`-G9FLFAXcctoByjQ<-0T
z)z?x>;N{UCU{6?b;Jlyr{GzxhXtz*Y5K`4sW}lI+H52{l#+}*h8aOM*VS4+wTLFF4
z(*=H>TE^1(iHCwLpNv@38&HyKXh%(Y5J9rG+oou0GK<1r>G}ElPD_!)^s>a?Nl;z-
zcpgnO0qA#>$X^4MR_PXL1uu;!;9|eh6sUs1j_e0G9!Gz1#f95B^*5&$KjM|@Mpb!^
zkyjX<<t;yS((X?5E|=tQHv?XN3c?iKj%`N|NIlYm^d^-A1+v^$(9QX%I$#{-pBaee
zePg{lF9}AtQo!G0JRk>6#ojQ0iH_6Z$amPBgFkpYEMK#XL{W!ddG1ghULP-+s9%oy
zm3-*+3L<r$QYKaD?(#&>M0cTOfayiwpO5vZj!xWDX9OQxGn|lyJ!gCdn{ET-m0*UD
zs6hsb;5t<MOuY`mxgdUzZv+RXlE@>!d7KM#*R-r)Dw_>>e5O<4Qt6*nSIoN9c@^hM
zNzTmQQpl-P!$5xC_;#NyddlHkoJ*)uj}hL3_w%sP^AP>q4AiKtG5bzcqe`;mS2VQt
z&w#0Lxgiq-y3>t!9cKe~3bibp79xpqHzY*4F$>4lBz(tRoth)*74{+(y5fDo#6pn&
zn|3WM7$x6rYCT5wE{0jN35yD4<=gCY1_N;UNthO@IMywYrvn+tJ9+K%K^S~+;z#EV
z>Q!BKr{qGtpTRGXbH{kcgoX^wB(mXcnr#gcuX5a)i^fFN%|Q|hR4HL#d;`HpfKYDl
zIBI|XQ^>U;^@@Mb!Q0P|^*`g;@zySAFn|@l%!aHl-L%6u|4#p?d|Yg>2c|2=0z1@q
z$nO>Hb|s=HjW3=gmp9eB%vmRb2#c-|fZ^n0z)^O32gj5fk-F{)Z_d}ZG-MfaJDeea
zGtWb_R_{RaeHplNPkem*HQx3er*$ym<-=<}1Tjbga^6)e{P*#&H;4Gz2uYISFG&iK
z3oYliLWOQzHv~X1f}NBJwJz@r(lFZ$Qm-$o_)>BM=dsdYwSRCl(QfWsIk{MaSpg;K
z<-4k#5_f)1L%+}(!Jhz*mSO>V<EjkAP@<md?2T`XV4dc7+fGNl>{?zOU|<+EEftq1
z<X^og?p<5Rp4(E|gpBw%&Gn%C`GnXNcrTlA2aA5*<q;JAo=*y~2ocvSJgzPUFasXg
zevX*!f6Q|00bb~bZhxA(%xer8st<Y!qhp2uDQfMnGT#j+mXltWi%EPQkHU(#j%2uZ
zBUs4#BuJ-k0XG($H~Qw(;Zd|@VnXaT5!zS%e2J=<5H^vC>+-Z^j2tm00yK5GSbWH$
z5;Kz8CnOS3CDoq^eDmtT`h6`OSg*&}P+I?m8h;1sD8?&?<@co|jFL%nsH5@?yGIa^
zMN>Q~uPrfGDZ6&@yZ484S8$Ycvv1yo2}$IF6N8Cse+c6};r$MX(q&&DgPA34CNcFx
zDMJf={L)iVgX!iz=$5##B4aEJeWmr+G5)5d383m+ejP3i#Rfe%XQZuB3=Vl#Gto@9
zg{8^&5<TCIXwQ=Hsj3W!(;nBaOp~XCN#r^6qFZ(SsP~^n8AAj393jNA_GypmN8U2|
zNX&Jsf!%1~%?lD3Nit!?Te@&~JIg2FbNG$mm_I7_>%0$blOG@FCPn5EEKdaIGJi4k
zX8sfxb6S3Vr#o-kC<Tyuenpn<JXP#9O12<&(1r!5>$3a7Rk<FrjMt!s`|MC<stay~
zn&Hi|6l<wsN0Qwp`%^WQK=aQSiMRo3oaOcSXM71gMZm1tx{$gq3AWxrRUfACZ$_VA
zQ0%8q<2l(m*TQgsR3K8TZkK-#Otx;tt_#Q-K&y1?B3rSv-O&nLDp!z{!1vR}c^NtP
zOxi65Pt(FiasqN4I>Erc#orzliw`_w11fnu7U(9bmz~r>Z@)!#*KV~2l_$%L_Ooxb
zOdR3a?5G|S3D)tq{35j&8QsE!6HX&vr5xC_`BD$N*!c?FXt)CCqRg1MNel<h8ibjM
zv<WIVdjGLmBc7>1zp1uWf@WvKrCZa7Y{0)d&WA+%l3G9!>x&GDO(rhm8f<+OOSZVv
z^rccoS8hrduQEYnO1vj%hoia5E@tKXJP$W_I<Cme_wQYRmXLDQ)^kIJv-srawu+?V
zz;M8rd-B4fZW+8jB4BNgUfu#A7j8%&HBA^|rCpcQ_lsSNtmL~<61i5GOs56*nvXQr
z91AKU%SAd+$woCp*|CME7if-xzSO21#o<|-$d~ABl=-l^HHvx^hz2y=<`ti6VUld;
zy;SNH&rr+(R!t)8s}Yt=H>QeM9277_!E@t<Hq&oF-oJjiDgf^qU<fY@y`W-o%VG#S
z#-9%b`o7l9lZ=qUy)#K&hSqHGO-@qRB@G<F2ku4x&O~s68gXp=Yjzp_ig642IuhvU
znD<^6K<kjMB(!~Bu?)5D!KZQ7m>-PdM(%v_%-*S~+<9+`_mCm}WiXR0ksc?*zG4GV
zIPGz%$yxWY@L#lGG62YT7WhmGJy9maK&B7)0XOn=2gq+=2YmYbS2GmbQEUjkOR7C)
z@5aupu(N@th$lZF3KR?Z>YE5a!`Q5I-eCsO0923ibYJ>CKMrGbi6y2yQJxeON_-ps
zJZ!&S#s1OcIQ!q@F%+P0mHy@$Rivr$TC%5)I6RHketBi)yzu}N7P@C~HMSG+5T;S%
zZ6p=ggaG357?G3eGG<Ltnz;>>=RdZ6Z~7GH^x4~H^b52}iwp4Gt9^@&-CJp0L0i_E
z-h5Z#`_#hOvn~WMDY!0J0sxvHcK*SU98V|@)_tvhZRi%_stfNQqdBavIU|_r+}Ll3
zdvfShr#cb&ZycfSsD7uLNJlCAYpj_1iasOwX9QOa{<@s%Wcbv0#Tw#o)v{vafDp#G
ziRGVvY=3cw0-1$VpK(CQnJ(g^P&G{8s@;FrB87y?43uL+n7nRQMNTH1Gj%n)HGehD
zx<I#R2%s3A=6Cy&gQtLcLPMvGO^?cXN;O!XU7GjcA>~5WwC!po0q8JlE%-Wd$O7|}
zO%h>SsQ5$|4){Qrdw0QU2Ovt%h`54Oy5VKTO`=opi7FPNZ?{T((@NW~Gf>wBgg&)p
zh?X-P8BVio?zw#11EG<rE*sz^hdwz79COQzi!{DjW;}a&uEu#Rmn*<x{}F(9%dfjK
ztkAa;-oO%!wW3fwz%1X66~w2SeTWH+qQ(Xp^?Pw>J#d59jFlnM%s389dCN+=Nlm|(
zQd~&)uSD@H)OIqR+QOa?*;$vNu4XYs-BC3Vl-EU^%_|u2UjP@hw{?6~fykh@5m2ii
zA^baT@yeDlivLVIt~VcbBT=%5B|y(p*M`5DcR9d2jdH~Ay#6_T@4cu|HZXIgCM*;M
z?bFl>8iY(yoA)OgsYGa13Z!X~v_9I2NtYd&aC(o~(kGFaoMJzw&c<=Uxt^#Mf9o+^
zFtI_tnh*s^T}<rHH!LoZ0)LXvbcm|HQR4qIvA8N8;Qig~8{GiD=??FrI;6IIT;1C3
z-gxlYIIawFqzf;b<CgYY#nh+gt*?EXbdb*1^B+sOR-Q^(mgQ!gGLc@C#A2}=E^tV5
ziAdw~k4WK1iovJXMbBP-Gx@vT0%salcyj{^u4XIN0*c%a0d+4s&&TMfPj?a@-@EiI
zLZV|!g)x9}l&eHN*09OUhZmu?-GCBtB1#wZaF^j%p{1Pzhnpv?zLKx&duIlkm4z>`
zsWj@_m4C|ItSmT&NdVfPhC{+usZBR)IDN?LQ-FSNBuQoW?XNC>vTY1B8|TX*Y(ihB
zy*pXIp1<Twjh;}|U<vL>o~oa*?TUs*M3*P_ZgWV$?NMaVfCL>Q;uflwk{kDQ(0Go&
zx@3oJ?2#^XYc-2bqn@_x-|H0Tc=n13CCp;_A`LVC4l`kMePw+zC=&OP34Zu2-l4)r
zR26l1;FIRzoLOI>VrlVrKFOLE5M{R9oZ*pV!13{$HiV05Hu2d#wG8d=mh*8pD%7P-
zkrES?lp%p!!wW*c8r}&bt7Jz*wb~7W7{msr9qpz2mRaS-QC|`>^>-@&*CC<5rZ+z*
zSuDOjKk!}DPd4BK_UYM3X(TF7jK^6Xj#OpTJ|_gI2JRcRmaEC)8GAtvBYL>*nAwZR
z3Qx|toW2JAjsG3z06`y=A~FU}(Oj-~aKAK4sCcY5NMr?C>9hIo&r!TJlU;rzOy{Wn
zRCkFsY%a6cJzKqpdF3N(XO<4idz(!^(VW*JOJ-(MNZk6A`l*+J7B2N8darrQU)uVc
zKIEsx$ej8J=V7lnJ(h>`*NDW;XkMZ-sgho>)16U0y69W}e2$!VVAb$AjHh~d{UPqv
zNL6+L(xID!qp$gR_riYZN$9TPlQetaSfE2cue#uHyfWcrFi+DLHCA_{j%Nr;i5qQg
ze!)67y4CF#*7Qdx2>Xd`g{N=rFmCG~&w9aaqWR3;Cs#BxT=NfvZ}2t?-dD>xW~??Y
zMca}0?N6UtTvK@+eXO72GhQ;7_t@j*@ED}8Fs3|qUOm#P0BOxqd|b7Q<sN^I++oE!
z!%=1(`*CO~*I>5X?!5B+p!pZ@ayCH{Ivv^JPh*muDUxssLWv|q`ReyeR=iB{Pa8;q
zuDkve*xL81-5{{2$Qz^-dg|x1f7x$NPgxnm2V*WSB8Jw9zn`iOXWKVE?@-Sfxh++^
ztZpG{J{a<_>HX0T#s0=$W<#y7t}UT-YMD0o<2;B9fJ@-F;P*i90w4vsk5l%rFUhTU
zfBK!G0g*mSS<mWSPJMVduyD^JFJ=06G0-XD?w)h<op;%FXQ_5kb-eZ$fL%1<DSGbN
z^LVg3W)37hSE=LZkFv>u22j0?Sx_7iKyf#e?h)<1nTLj;H4k}QKG?rqK`%JcyNieb
z1l#Xy%5EX93DEN^^@_Le{og~R`EED^OhL!hTcZ=!7!x=R=8Fl}YN3GKDDJxP;mH$u
zFV)0aK8~D-*a*MLe1BGrMOgSYxBlePF}u_0^LUu+;_)0yW+59&Wde_q?N3mSIdc#j
zb8_bz_-z4lPne8i&~W{OdI%yf2|7U3<GNGxNj?lwXHmN~8ZM){ocmTaoq@lOKae#G
zJxxePi>j9$|IqW|a;IhTWKyx_%wn9l7<cK;KdS{XHb!pa@i*2VrF|^WSmD-aljBxv
znH>2Q%{;h2D`ZKz^)9&^!F3J1>w^c_<uNy0A74{|Q>Fo>5DtMa%@d}KV7P}GbK84H
z`F~ye>Te0fWJJ?{|0_BOJIjDhw&z9IU8#)jUINkgKf;KjOPTA2XmR=QlxDS!C^l!c
zW`Y)WM@0gCCREFGema|)E^8royc<6Myt~Byk?<Daa{Mpoq3l&C-T>A(dI%sDnjZyo
zWN`n;)U5=mJjTh?6nWV5rK)*mee;z{U?<}X<35Vf6vlW4ln=Fa7vAagmLhWoHDw^k
zPNw=p-nOQ*0FR@{!Ss(`dtE_go_Dg66RJyntq<>>D7?mj7%0WIbbzDTflKv1<9<_k
z#w$OGtl{=pv2;q%lR5-g2#G4_)(wSU4AG5h1P2Qoig<=BD!0Cqa5@Ei&0V(>AQsH0
z)D}_;ug$~2qjsa+n_%f|{k-~JnvLN0ozE6|Q26&IsV|!K+^PO3s#QT7+HVdP&Ep34
z?%v%|_<QNG@lpi;m=H6GmwOR1AlQq?yFlTjV6a*C{R&ioCMe_Y$OTG3tdd(uqGGhA
zPg`F-W?pbK=fNb+(&9Ya>|*|t{_hHd{<z&ylu<-Mwp(z-ckD%`LIFUu>zS7UG4DR6
zn#?pArBN!uv4kKSem&=UjILHx-DCR@N+6oPH01zG+ft#xvE<i}r?YCPKb1QwH-{8L
z5%Jf*7Xw`W#OOyt2UKF{EwnMUnNe96u(oRM2z2bS1NKnRnG7=JEYt+ou9^}Y+iB5w
z$mk@Uu0MKQC=b(5n9|TBZW`~0g`TM}NzZ>McrN|b`x}p~69aO!-P9KJE}K|_&mB+M
zExRz0eLuN7f$|n;%kvlBqzlXc{Kx_pIXxyNL&Px{+c0UUh<<a<T6ard`0o{|-n1#<
z2gf+NA3qjEy0w!!>MC13r-_#HdlLSGTHp1Om%5P-y)GjyXkE{<kk8kd*hYvry5;86
zZML^!(9V*rmO8Qma2yI)<j4$Z%F0@Dj?_h;Q~E-8lmzv%uT4=O1E+UXxz=tUc9jBW
zd@pXkeha+BvHJ7xW@*o0b?f}y$4H@poWct8>}xi3*TJ>7E8YqRLQT@@p-9=mgMq(a
z*d+t|574FM&s>&fhlegmbvuWFxA`{KVgWNg2~}wINoA3os|MNt-ox99GQ#Dfpdpcc
z<KF-_62jlKFyoHr!Rl_nv)`i=1OSQVVz&@8c~MRGR4eRW&5FrOd~Qpc(vm7cmu$*3
z3uoPr8ge~`6>VZ}M06;wB`w3w^waofP!2L~(niW4gXg?}ZPwsyJ;m4yU0Xl?6wI14
z{?103;E3t}0!zWqUb0i?SpQlMZd7?0wcv0u^*veF$KAW=XHPousx$-ka&qNe*8cpQ
zC)lH5(y8DrZM-pwL|o#0HlYbt!M~8GhgcglvxAQ~5<ulwUo}Kuvrciv;{1^;`&=ye
zyz<`;?85nX*xFU}9z)bjVtE8{cjJG6wQmz&5-#_#hqxCN;__;1_)#EhA+kpu{>2Y>
zlc}B>C=lB6`i!(Eky+L^q18F8_I?6vc+MWb2cO>@?#SgXV%4yC9taD0<0vXq3O&H;
zA{gFIZ|j{qSbmAy_2Uxbqn)hkAeDSBot1eb7&x&b$)J8xHH}p(-8IjDH~2V72@(Ci
zA07_@L+Q<qtV>~V#M#}CJD&|tzO|ImV$}+0LPxRE^MS?@BVpgqLDt*zO2_q{n)6-v
z>h=|O?CbEyeJG$m@DM*1&)D&mA=EerSEWDsGcMzcmRKl!iMj8rCI0g?y`+)lP{94n
z9_k#-Ei}0cx7u;My6O}1?Ee9)Kvcg@XUiuU1Uv}@{A!{<T<Uup{ND?2!BQ1C;v1;=
zewOozcT|(V>@<-L9@-GK%`}XDzwchcc^JG50f4|ya`{g;Y&&?TjZoAZp*0b}jphl;
zC3oCNUDP4xujX1rg2wpPnhdf*8WHOcTN@t5;FiP;i`i`X90E=s@9!=2J+`O;QN>w|
zRH37c{^bi9PbQbz`S4WvYQm?i#S|EBs0SMD<1*LO44{SpxXkIGkCUOE+>WlU=~ScK
zwD@N-`=K%XQ*HIpw1d)T)HTMp7B|px6&;NsIK@Sun1Tat_%JR(0A4m;e-7(SxgZ-M
zQ;dp81qX<cpJgza9fb!%&pP?P<q)u3ho44B*nd0-Lp1|5KmhRCMRyGAa$FNhFz3xg
zZ_SxM8)oh{x&MW@k9w6OLQG?<zUi%52PB%%@#$&9D;f=Cc8iF>bn{>Yco_tAG4tqD
z0oA(Ws<RmCVr3utElc`}=aXH9Z58B~Lx8^vZRc`6^!3^0qSOJJAb^&GjI`MmtfzI9
z>HcwxWe?QdoEo}Bh;bkFD)|+p8sl4|4!9&b?7)KvpsCMg8Kxoxe}miuKL9lcnK!7N
z0a$*Jd>w1v;#ejGzQ5&3f9J_0EDW72<|h-IH3$H8BHRa;A^5;A`*8a@2XJZAv&74D
zZ-#&+3r(w}`>Mh8uYFXe1}Zeh=6rw+vMfh;p6P7lOS&IPeKEwQo_Wk8MAd_PtpETZ
z07*naRM)Ko1Ry0)tR*TUs8;oOlrPQE-2|oaeeB*~wFjmQ0hHd`Gf{utJDwSK*kB7P
zN=<lK?s2Y71)ghz02)|R@kq&v@38nhL6yeX$N)qD7#IgeAEl?bh5lu45NH4e1at}a
zrmCpWO@biQz81e)mG(tUK|a2ZRS&8&%uzYqoOynNa2O_`r8_+*d{GGGWw{$<+oJu{
z3;~RD<N;uL+(*6WNIb4FO5W7S0CCjo0p1RDUuum?=?_;4i~w(jGgGj`y30jHEVcP)
zZiq;K`6ICLeZcp;p{BZvS}B{n<oG*W5?41voEUECy}$t+{i!n;3WbEL7dIFJd1AUm
z2NbOMF6+)CmU4};i2;`AIMRlgnEyl6#sKACBLV^75Y7yNCLKRpKUfkLif#%Of;JK^
ze{+K#Hl0l7M}Ga`3ZzXCK<{PM?;C#VL$CyFr-=bX{$uQxZeY$Cga&HRtL~b|3Z3GU
zj02D|?xS8Y#tj-{0|OAYy#fBq>fCA^P+^>Vp#f0VlUi-Us)vQ(VN-<)Q3!!H`jZ17
zScHm(nhlK<StwTU`|m@K*nk&D-<`d#98hHEAQiW*Rjo4eLMK!UQm$W6{z~L%e3P01
zBIFMGBYf%WbLFTqDgA-x3JrjAY!@L=4GRI(J&#Lr*QLq<wUo2(^_%lPmUkBN&m^E4
z0^qLfYLwj*`hOZ`fbUIuV2KBpWi2gL`Erp|2$Tz*;wlHotoTl=adefE0anO0+>v3P
zQ^!%ys*}<m@GaK>=<1aARSFAj=u`#z&%0U(aHjU#@_raSj@ggR5FnW`e%RZZbI0y*
z)W`wZheQ=EZKXW?n<R#}t`s^^IdZCg>?=LfGE(A()EFfLY!I}(N_vCq38_^MIsM^`
z!6BT_qU;p(&$C0|QPa$JSSut*p0?jces-tI5U7Lz|Db>X+e<vdu!t?Fb_a4>kel1Z
zks+13N9Ukcmssbz&N-k%+(*5d`cz68fG907I_d#=pRb{K)1Y(68Gw8x#Dwz9kS^XJ
zt_HAqS|!Mc<?O@VrLFXrbV*P^0LXqR1Z=}|;^_{#4o0gGkeJ)I)?wIuN$OlFBBaYs
zaUb<+>K`rh1VRpjf4bQgl!0r_1MB4U2eWg0C}oDU1^n3hi_^c<Q74E7sTo1trET<Q
z%D<=q$!-Kw{iF~;7~njxz!K<>FNdAlBbZI%sOs)Yb&n6jt`J)^@MzuaO=-o8525&d
z!${G$uNnue(cI9q5l+nhJhH4h15|{rg#G|mPkQ|e2xzbUVzkEhdVYu^RB&$}l2;w3
zk+1rV@H48)ARq{>&~(G_G1L0VB@A~e2Dr$zv~EJ6*5-h70MA<NqWq~{l4`%=8}`L;
z5Q_8>@-NT^K+~*9)+eRJ0X6zVu>H1KKI!$(A)u2t2(m*Yv{qyc02v#@s)g+@E)fEX
zOU-IML<Z19x3~99eT=QG<*EDuJC%*zK?q3TKU=4caUZ{Gi&U0!EUFJ};sg#rLkq<K
zI`i}-^8hq_4|9OgSR0~=VVChM-XIzllH>;+<vAcn+&Fi+K1`$dQw0JlhX1`Z6DA{U
zXbnSG(*{JZwKY@80NaNmJl`$^*6P;JtaVna^v@nbE(TN(;Cav~G^}y}B6c5GPFu}8
zZR!dj|DODNE95UaYc20ICX{D};4a=ERhsZkE<$b%CnL_%5f47UdxGC5kU&7_>1I!N
zFUi5ujZd{Du-z#xMw1YL9X3oxgTZmn_W9DKr%=sAMAA3C(bjI277=J<0K?pmmV?ya
zlygJr`(Q3sE-_;Kc$70k+ByK_LO_xqw0u5gu7tH(2(Y%XO0_wMfO@)bB7=baaJawF
zz;G}>H<*H|+z_P@i1DpyG8zny+kCgSN%LFxAjx-OZ+fG{;~!;JFh)Hyfh2ruh}2)@
z=Rf4{6B?^A?WKT#E~embP#+~}!jar1j8rEhnWa-*3<6}?-ZBV)A<^fvt-FBKNmE!*
zp@pf1z!jgKO8Czv2i=-`!wPnZ3<B!;F8tZwzNb*;{_qP9SfPt)cvo5?UHhQ&*Hpd_
zL{)W81DoEE<WAuZ-k>YtcX^udN$yX+NqYxz&AF*R2894Q4J8mj86zY@;Bv70{m&+M
zkU|I?m1E@DR#);jaiXo7MyGUZgDeyY<!^$~v9z4GqzWFPw!LTS(|QibR`JBNr?U7E
zC;T{+GDBJu12#{5`%&cw-J}SzmWB7J@%L<j%~Vci1q4tO7>$y#ZhNjiZ;A^l=zLd{
z=-iZ=>Z&w3D8@=lUV>sW7^?Q3DCh{Dz%Tz%QU$-@a@_rq8`YBlefjgQQ^`bJ_)drk
z6>*^!Z_qI_6{Pt=3YTzQJTmPsT?zxp#kG->xd8(9;U&~Z<d3eUb_FOoU?VLCVD*kt
z(ngiZL07D-5a<X)rSi9ejJpeU1%G`Nsv!OMGl~(C<p9ax1`PjH%H9a?KFbi$WC|{C
zMWZljeo!n|15!aeuCpt(Y=TX41(H`GfMCF9FWld;+dnrkzzafvsw!7m^H=Z-lo^|P
z1Qq<;jS2IyL?s%A56of#UsM&mfhst?HQt;W2W(I3e$<2p<8uiD8oWVS?H60p5a3nH
zKmwf+8#e;~jIgr*zTZG*1_5{3?+=6l!gFZ2k0w2^vk+ja3L+b=F=~Bs&|1~BN{Y)e
zCcH9fS(<_hmQofB%2YuZ|A76bRN=~<xZsB@$2wavjR^q^u%%24C~CjxlI8~~T*74`
zP&KGZA!FGiG(&(a>a!1f&Znc>1l7XVZ9!28tXX$lx=}$1AZ%Q-3gI~wF+IQ27O37^
zMt@3@JQ_Hqq1#<pcMK^xU`szDY>LO+uzO&k;U;fTx%P`KsXs`OJzfa=O?A{XBv(r=
zO`h*bAz-@?>j~c%IRtFOy=9u8kFc+wo78|#LVyi8VGRVTLI5TQNeUP4YPELTX$xsN
z&Jl9|Oc4&A`q?#Ys~4_(#JRBz*M`P}_BjMdO+h5-6eBGgS7eW8LI8;d)kY=+ibDbj
z2*U8Q9^>69AYe-*K$47f%kFtibprCkC<}pXzzJIwA+VNC4r1+eyQ=|`7ez&=Gq`6I
zDdht&Rj@KdynzD_tTWQyYi`7p(s)n-0TK{Th1xF`W0sbUr&5<Nqcbz8s`NhA!+rwN
zU*@JZs^4Y>1Q023-u89E&m;4H5(3456Shi107*3$PJfkJ+r<~)=b=uH{vrbqRq!S_
z1(h5SP`&OEHa#v~D;g6jAfTqn6GNzat>Ik@MPP9GlxCN~Z9=(3EgzdG1S)4lt^tg?
z8yVdpzzf3OU?1M`Ol$NAD}?}~GYkEeu6Zs5!1pUrsVV(WYPGfl5BhnwLx%n}23Q`?
zEec>pRmMS=3<R5IupFr~I1dYp-k_ss9I|(*B)%dt{N&+=dM|{^kyY*qf%BcMX|pgi
zN1e3*2n&E)c&0n|CU>Ap2v9mNPs#Z#82?-dz;%!~1sVO-YOQP!Ridy*C->o8pnr`4
zPSEM`CTFqoZdiU&Qo_v!A+UTxJgCSFsZf<SeyP!)a)4CgAElN=gjN2uvJj|J`LMUN
zzSkdz;b>5o0ZIti9l~%w(8tg!Tz&sl96;#&HJ*@l5Vbri1d#k8GWx63+IAG;j~-%i
zJxdG_XNp>L?3uOI6ZpU3^+<q#(uI$oLX5C@7yR^B<`23_Jj%S|q?G^iBNN5sVXu!a
zI4};OZAw&nr53OYUEPGc^Z+c783Xj&6nEl^uO2W!J@e;@qnmtiTuy(6XtnsKf(;7@
zDEeEA^gk^N27uV=jT%x-v+G%BrH9D<O?u!RJV7N0$W6g3ZxbtR_Xj`UC5qtsDY}H2
zex!>0W<sC_^1INnh%oONhCY{Q^lT!C>|Ddo5dnb*Fo-kU*ExVwMZTRSe#|G6u|(01
zuzVPNnf?sX1RbFPh^plGc1e}|kiL>L0PVuK=H4llYlrt%Id`)=^Ctsm@GK7ta}0+$
zsmns?TZqYp3q>12(Ire3s)l@NdStS=Z@Aazm&6F>fwcCYO$3oFa`6vaK+{k+Eki6D
z&ksVX7_Dy!x&Gs!>~B|jZbOCsEHYft5<K-1=r0HWmSy->`e4RdM~oHW310D%?37<7
zUnvZj&&Nu#GLiL>8~+)xWrO78{-A2H&=sq0PPS`6YuT15mg{{2X9t;0&nAM%7UTtk
zB{1xr!=Ydf78gM#1km#^naoyGX<L@nQ<gIz(4Tdk=|+FpOv&+k6Vd;>%mBwiiHbxU
zg)dgKtWtg(AYe_+z{2*pMUVqQjsJq!lJ_kX{-9E%V53f^s2tf%c9-|zr$gA%H7u!X
zKU6^gWuDLN)9u~EP}?6Ar%*2#zCMWjpDURaN$#CUf9CEgG)1p*`Ng<n;ri#vi<|-C
zvU0&P6vY{blz|@V!U*=z(lY&1$rHrZ{kV}``WgdB{Xy&8l%QzU)<@kB@gup&w!FV2
ziE9{+F*=9!HgMaATGJ0gV{{3%@ZxD@8Bl$8;UqTCgoytpgXvy#^sQ?2XPH*n>%5Lj
zu>DFo=8OS^P!sc0mhTnss)?H0q%el7KiTS8c!KC!E!xTdt@a0T197cR`z<Z9qr+tO
zkjHmj0}Q&^;Bt|)feRI~gED{?hIecD{2U~gTn`jEuR?5cb9cN|g=$4&w5KQytDI);
z5bQ{P|5&|#Wjl{Dz_ONeRxM4=dg`v5zeaiu*vEzLzFaYU`07G`3IS4o5G@vBd4DbC
zGIUeh$z&%(^KIxldwBLFoa=Q4fGP1e6$A9#@I36}=Vv(L2|^O*Yw=H-_y3r;JaAgo
z@TK$zK1m*^JN<p$8K=Ymr4OSFaH=c*rPAcAr*7bP`$7o>EPXHoOBKUihLlvVdvy_`
zIW1{2%9T-lGP%fv09f)w+xPkdsYM^EOhI5B!wUx%#zRB@3>AD|aKK6?RqJbA$=i!n
zX>Hf@Bv^N(zt7;jSb{eZ7y!xmY{R)PZ>ijo`tqZg;?EuHBFk0K)`(L<Y?(iZC7iaM
zXu+}b$y}b~Ls($m*N6M_UIzBy@|G*T`*5V``VJ?i#+nDoWxHQG%r;#G)~Q5rp*=up
zEzi*RrW+~Z>h-^^g|etOt|ixR62+fuM*gn1U%>&>b5e;3wT2uNT7R~v*Sf`JS(z9=
zn*>rc4?Pp69No{-;2!9Kce&oP5BHy8vem7S){HB3JN9eT1*{lp3sW#|uy1^DCX6~z
zVwF~}Kd@J|Eb5Kg$<l$8>r8Wek^G)S2z>dpb!6cXZVozEsa?wtf}JJvON;og?1<>!
z$$l<jfKO|8Pe%O#Q37{Cjn*_`EPuw}aK4OTyd?O=)J&L_{dH{Yk(+|j7D4$M69j0A
zMrKd<sF0sGt*Ai28;vk2I_KRO`M+PKzYGEr<`8~#fdKKo=l-A=q1BRUf0!IW6N-p?
zp2MY)U1Zt?Z0Kmv38?N60->eK|2xdJ5!LOQqM?3A@t-Yj3O3XKdo&qOE)6CbU4rK~
zxBbcxuzZ8lJSx5hIN<&|`8_!VKx$y&5Pm2jpsw;|{-6jA5js*-JH~{dBXy_i`ljU!
z;O)*^4V;vYvv&p(OW>xq1>?CE#SzAh6P-GXf4-<GNENq+egM9^+f8Q8O{;3xzt}?o
z0q6<Eq3YymRd!_Sl0X3U1{I}(IFR4pg><F(_wV1)DK_ju$S)Mc)Ml!U*ETdCs`Ms^
z36V{?rf!Tcb)6rALekt(AKGX|v0R1DS9kGWP$#0G(ZE%-iS2x{Yf4QPuYbj>!yy0y
zyKkzw?Cgs!N+qae)jsQMdfSc5MFMgNkkcRhLC5J7r4ALkRQnrEMw5&BfW$Qeu_?3Z
z!jVZ#L6?v}NrH2o-4(VVuy{m^=TB-0|C0FUi<pAXcKQ?HG?_G%CxlhyUkH{^2w-vj
zx2D-@4MEYiB|w1djGXbr1yeB3N0THUFI4O2Z(#I#`rLAigdga5?oH;>vsK8f-E1Q1
z0OcLRo-;BG7bk(G$-05URZ_%!8I^BXafr*;#6MrGRfPKQ{PA|dWTMbd#p_?I+W-h)
zv7ysj1AkIJYlw(6E`hBH06QKCfTBnMPX!^cP_N$`-F+f(B$@Ux>soc1O!h1Jwxy?n
z4>HHzHVk#$Nnogh`6+7x1-9T#5%Z;M^^_}YYj%^n_&m!CHG@XZ-b4r}dQ}M5Uy>@p
zt;5sm`z>w$CV2W5WkbHoXS9q#1sm?DDX8=YHPC;7M&_N?d*ZF`@~I2o%aEX;@_cHi
zLbVUci3On>Cg-8vhtWW?cY^I&IRjC{*+?OqI&x^nllq8dzg*or+<#a^2*^V7yQ=Lk
zE0RZrTKJ|GHT>LU0QedQ#L%&OGWnd|s<}ZGQ*hC^kgIR-%<fy;bfjBZ=Sox;0?PPp
z28xnr36s##O%FdVid_Fo)fTLitrAS-i-~`>eZ>hY{0GZtlUi1Krtl_#w7B*9v)(ye
z_gA-y<)24q@ctVH$c*FlVK$j~m(3_M1wVHZ2xzANB05@{W;o-4j;<poZ(Ma1gh2E4
zf587rgupJejPVTz!;xYt1Vn`%s-SO9?FuV$@t^HqMN7E@5h)>{`hbTzr1{sj>(Bd*
zWA0{FGJs$HmVXZcOL9vmvkRlxG!aa}3<A`IkJgLDCR!8B3Pb2yu1(90t5#JZprSvk
zVIy$4mkWV#e@?=_*6;WBiX5P-Ehr(|4Ojg3O#GJ;o>d1d=K$3-0r3GZB5k79>mTuc
z<JnYA6$6yM>aHxJY+2tB&?58?G9LtifD3ex&2?1f5LRFO82M-wBR-$~h@fjp#XXL^
zptyOeeeBuwm!247ki+@h8|VQZ+KQ4t!4|BOZCOzSnfNa!uc{7M?nG1!6sebHS7R0J
z*S{DxlQoP`F+lnJu(FQ2dHK*d;^tinBV;Nh22pQNqwZ&H5VBo*o+EoY(nmtqk~H^Y
zG++PQE<Z6@Q0VY!?8kjPGgUR8f<v%=VC9^e-1=8@Km#wqy5mmG87lhew*C5}QsYeC
zFhaoq6;YTd^CFt*U!QIBH5C}(F>Mt6G3pJ_9lBPhYcw~F!CdTGvdVhIsI<R*Rryy4
zfy1X6p8G>%tSb53RXIm;ar5$RCjRL@7YYt2lTv#Ak)#q_%HikycD7%Cmep6ZF{i8`
zXMpN={VRvCFKurQMd-9GS+>tZ69+8UM_->|ErDponvUSEJr=W?J6(Ue<U-)EhsHme
zP4(R%kZ{3)+_b_LlpWd;)2Pb2-1AS)0F~X!A)r27RQ`ydpMntZTd#j@(jXfnAZGyK
zTa;BYYVz{|ZMAsz^Z`2Hq3jJ(Yk&xyo+Evx&4~1mSF6otEiqbYj~K-^g1YT57XpwS
zXomm~yPY&DNUiRD&_pxpU5UB)&weN40O5nBpS2MoK*i!TU`^A0yu$q_@jmiNgQWvx
z^OB_uAb#1a4&g1YAdpC*uYiUFio}3W2>~&3O)J2bt{b}LMk?nRJcnFK-JZqk4@)it
z_ThdWf|>X@@2#FJJ7jwx7ROdi|8<;O;3e7#LV)~Fjgp-pKpm2Whde&<OxJane}BD9
zLON-XHjk7sK>f=uFFAz$>dcJl%Dh1(Q&3L-HL}f_W#Wr&p}8~gmEKXLU{96`UH^+*
z2<#4rJ!Ouq(UT8~4!p_yqNYDFSn_FKCAn8&0P;Uw+PQ4vcokLB1Dg(?O7?`<Ff)w?
z+a*;}T=^6Df;NwoFo3M_+@m`LDAAuS?hPs$h@K=6u#BPzU5V@uv{5?K<{<r5(QzN3
zuO6~z*I$+muCfF?>MtB?_FmEZA)HNi2RZ#$Fk;!V04kqCce3h}$&A&SXPNL4LMge(
z*<YHD8!kYCy*>{6W+1)(>zm>}!qt&5fb`kBdV_p5`twyw45&iDatW6oP1kp9VYg@L
z;ng0XXr=l*k7?+l5MbB;A+=u>mH?FleSP*+Hh+N#tc(v=gkC4YsC|IhwGhlHQ-2{p
z-*Wo+X0t&@edy3c9e>+Gf1gruW?)Yr8)KXV^(@kcG1CA6bq0`rQAdaHwh{f=A`q~5
z%ZUNE>34DS5kz{>m(hn2Ei*GY_N*(48m@oFo>fhcUjKWrmuEA`g@6}?pL#EBuz7d8
z$>dNk>|CM9F$bP)YcuK!5E8H3l)$o439N*!=}@z%Mz^k(_tlS^`5Y20z=jb*3(KSE
zLSzI{j2nn0450YBP7YzeHZe)IrXlEnrNjXL>pNHbM}r|cB6Ea8ee~?l@S$h=r&tvm
z$*7xDbrg2}L1P2urJgpS5CTD{TTmu|&r(AWIBh<fjB1%oDC!NS12@60zCFhAaw)X*
z6U{(%L!TvzY)$LUdqnqvMedxhroT@+%CMo9L;)BR7!YR^GlJZewbS=H1E{{O-68CE
z9BuS96<UWqI0PW%8m6P$fA1PjY{N|*eF(wd=Ic+dCN2XMzy2Pzk}nU5f*=<HyYSQ4
zQx3RD4METUf~cm*04wAS$hCzpb@a$bvDn6;(GSEpGP|zGw4!Ku!HMDA)8;$pgJa}|
z6Vrh4?oi{Z8Lr?bYb8irV*sVPDVwEICBJlHl59-_njAXLhRT6M81Nt2#uS(UW8E^G
z%_c}kLk~x)?U#=cga8lN?rz!j2P2s<ZFsxvcKb@I2L&JLe7HdvK5=51vdj?wdkUF_
zdtpN>WDW`az0v5LTDk#amXD$u(00o>1jKU#d>?Qm+B9quyFLgW7FZwaPGS)C?@Ab=
zLjNuVxeE-?kO7=DLBKW}Y}YCOjd_EL#DK??asZlYKKkq0aFd80JhHBTfqxaz^y&s~
znGgue%K!EOzdSrLJmtSl@Leth4q<P2xdetWaOxaDi8Px`0wGYdLU!+SWaxdvyq=~$
z1+10^|8)-F3^3KBG;xQ+%Z;GlPzeD(`&x44sikWfedit#^|34}mz@X_y|rwtSd9*0
z|D~zMS(!+l7!Xn+ut5X!KGyr1dm=)0WcY}d0IX#kAoEpSvg==D%!l|4zq?<crwiwR
z-5n=exe(Zf+fhOjPc26b3-K>T!A>Zn0Kwh2Tzv91qOPzO+q8nW;V=~5pcwUxzGm2c
zJ-pcFTmb=F_TrSNNd{wqnPG_2in<b{$^c%|O4JTvrghyqr#~`pP{|bJ5D;jF72>%T
zAj`DKU81w$ZW0ElODZY^*!3?Z?`$uZ3ulOcQ=D^x!X0!;`Z|m~uf+v(atnisqIkWg
z;pP+awIWs><KS{^IDr}md@so-t<uYE7UI*{_`E<jI_Vy{xFG6(&&ANN3haQO>NsR^
zpAH16I)a)@K$H&Q-K9JFvjq?^t9pZoZb)R-(15VNHoa2U50RZvcM*#mAl+xy0i{|n
zL#{t#2#O5{Z+E^i98*{V`}1%go}YnUMSzl}UhUBmq38tM|L}<|;FMxjCvP%WH-nHE
z0x^ot)b_g{p?lF`x7$jm82ULM;!&Ucr|bQ>kdVZae%cALsagSTB|r*?Fw3@lZKnP7
z^r$qF$Nto(7OmkB;jeFqEyWv1!4OJ;0p$B+^5h|;b%s0^0QWwiNnx2)s0s{2ENG-T
zm6I1cJ>;hyQJs~r(pWcjr#xhN35k$nMe$nw3AQ0}dK9%iH}rbEX^qtQrd-JUzgp-R
zLE;Rev^)@o#U$D%4T8(|RAzt{`cssxWe9Wh587t<R@c`TH3N%|0SW72laBSTf$@b_
zx#a}X^rVcXirY&B2HkU(JyZRqnnR~>2W_Db<Y&d^5uUB+(Xv4<BrD)!jONpbCo5+>
zE;AXGk8s#qJ<zgl$C0k-xeBU)fHe<0S-P1}?H>$J&V6fH+()v&Lzr&LIzS8gS!i9T
zlw`l8=~gc>0C<C{jpQlQu8AQ`E)rUoEN4{pt2MyXt%gv$2PHA6fjh<{B|~QWklHo7
zaA@w&kJ4v}yq#%ys|`BYS^`H;1b7@*&wM(Xi~|J<i<c-2iSE&(>`A*%<|c?70%Dd_
zK{OTe?eP+ZJD##^6zce`#eM3Fz{Inf64oLBvQop!5wl-j8iJ&%m3f2Qg8VmsO7y_5
z4Y^1a#|fl7EV^v6>JFkOOMeFV=evHCQD2f&OMeaBLP~Yv_06-U&ESZ+W3#W2e$yfJ
zB~e_&$`|fKZ|LGgA5r<W3xc4axeNjbjfXZnGu`E1&ddFzSvZmfN+M&DoB>)CK+18q
zL*<BB=efLZ+-n>F4&hxnG2l!sfpzuzXU~QfotU(SP<L{F!ko<8Th)|J<dwhF5uC>t
zWSgfWoY1_dSxI7ANa6Y>YQRik3s%$nUEMMIcqZ#uT897%x}L@$z!_v2(sXQF+U)qv
z7Wiy36(MJU){~_`9~LKALVr(nRT>t70Ok$KO+k>C(iF;5W_WpRt0n{v_>$yA-hm?c
zC~?5<(cs)-X`u3~T{^uZ(!J0&E*_CtiX-35C!S)mY0hZ0<y?S6eR#8b691zZh~F}6
zr#GUfKc8m|kac=)^~AIJzBw|zl{TbWOwVIgNO^WFM}LK_)L~5nY6cdj;CcEj?->fg
zm2}aiPeEM>+zZ9<K#!8E1qEX(XMuyAsCpzorFkDGrhQ61BT_}b;>qN!R0BZT(~+b%
z4F{&Zzl6rHz8RriC3vyGS3-@CQ&b9+uyUWY)e}z#ycR!l252~3e$)5Gu_QJ0=j$Z~
zpbp`rG+C6Di7X^J^q>bu9q2C+0!2OOg+D`B4rwIn_74<&k17U8Ap#Q^BQ%|*>S*;h
zu>}+PAAJvo(1rWq_=ycmcf+}zY(t52vH}4Fz(T|8Ys18t!RA(lw1-1#iNk&~8=-;`
zZ*BBHl=Qs(($vtOtrzt`mL6D23}6f(c`2B=-5QnD8mMkSwg3Pi07*naRC?Umh2JJw
za^R&bQyYZ<Jf#%em#YXFUZU$`gzVudR^PhSd@@(`-yr6u;p}^T-Nvp)NbgwZa4&PS
zlpuic<jjGgWv0=$u2ltd`8*%mTtDC;5-@@>fbu+<@>jX(*@eAGZqAEB-~mYirNjW`
z{=xf(I&na)p~r##Nd5nusullVlMtZovt<37V}x#QpJ-yvbf`y7r@l;P7u93!!cT1g
zi4X4G)@@5wmR5oQu$fJk_~#m$m?eqMlNJmH;V*JDWq_ATs&@|=`t$V?0}u!RZ%~mK
z@KowAVBM}EGq<TLij<-u$OHmo+=F$gmin{ckz5GWJ9G23K{na45!|K&ZQ!E@soOB>
zYZ;+SG6ZVQ^dOlzs>0L)0zeiMYtghQ{Kf-Y_~zwa?Ruo!zRSGBZw>Tkg1%OQzQ^h~
z^@|X2!*FBsprBIZGCj~Is2R3$Kt-%?&(8;bT=FK@0{vOpki3^Ty)qJ5TF2-((EFil
zolZ^3s^8RMcUs9Oei9U!Iw3Y~oSX;d<w9o=$QOqIQ2z;9kpFB}C}oIMGSCQZsOr77
zl8yJ~450Ylvs}<OX9m2)0ACyKT*^5>>A|2up>W@GTa%N^Vts$PT%b|<eJ7<qwQdtE
zZGpkQHm%*?HS$l`>l4#m_t9pvX)wCtCvcB^)K`ow)7HX(Xn*9XJ{zBkLI49^S95Wo
zk8aTlO*N4LJ_!OSx)F1~uVlTc0APQwDu1Qblo{|E1bp*GHH9-+`AQ(g(Nqaa;k=j-
z2=155fs&mih!8|8(|?;V`6je~s62*vf0r9{>h(ix>?2#VQKQEVargWYi!Fp!2wfqP
zm*B@pr@r4tT%#Ge51c^Y#MO!FthwO|4Td5ExR9=-VnvmK@FoWU7U8|WI9&O44j>Tl
zc(DK2QpPZ#meD5k-v_M~DohA~{>u3`ggZ{n*^-4o%f^5+g!T{Bhk*NAWB?J$9q-9d
zACE1B3MY(oowA&u+NiG;irgE`_eplizzh#TW4i4&U|O=P!OgSv-OVNX0;Eq1-}to(
zCo>713%{?F0i>6RO@&qVTWNrRmxKUht$`=V%e_I$o`uURwoMwV4cj<?3V{n`N#w-7
zLlW3M2nz^c@W0I-ry|qJOnfTYf=d)x8Zp2Fv!_SR;-9F0d3VT7&O}SF+t-jqp11~n
zAfzRS&#<}ne#;U=!0)RA2lRR&w6fXCq|a$K32Qg!+87#slL!Fr_-|m#%YOm^bZd01
zU@0*`<yVi9Z6=THaL@}|n-x&v-pedXu0PdgE?j-h;J<jis{O;VG^J^SEE|t?_d)(=
z)M#_BZ{=3jN6thmTJ^9&Jw0KW50QSpw5hd+y-65gW)YRqHi*zLM(iEZ6AdQw>H${$
zzA^?-9N(i+*8V3Dz_x~%Hz+p+?^3KH^tXC5$JC)adwaJENozk2vp1^nQTTsu<gXWL
znc0F7I-N9-L-FyB52(rMws}@sd}I!V4G3-&r86zWPfxd;-Y{$}w%CV#GnwhbKCu8y
zb2hMez(5+MI0}8!qI+9nP>lhYWqfPdS5pU3et}xL<7HOq@=33Mkr*J|?+Q7Z)*E`4
zo)v~cD+lb9<$pxr9~g_n4b6XBYPC{lRJN%Nay_ii>_LQ_<D+p<Su6tCn(4P2r0WA{
z&}sE=N8~&96vg5OzupB*-rf?^><3i;OKii=)nFOa5(w~$udexhJ1_trF4fi_wy|Iw
zcD7hF_D3uUrkECs9`eKhX^XTanvWuaq_!QlD$UtrDEd7;STY6Wv;3?J--hJNY281O
z`Q!>Znsr3e9&{~IBfzm<pi83}MEVbgwoa7!3*bMjXj#?4zTQ86ebnw+VrZ~s%er04
zDv<2E(IoGmOHIGl*ie-LnDkF@do6Hd2T{c!z|uC$g6T=Ge~}m<?T@r3(i2_nJ|WZ4
zXm<vv^1U(^&pIgN9FVnzmwh*}1d``<XMo|>>$z^vMXU7_E6$c^tCB%RG?#dZhBo#L
z>ypkjVnVP;PU*t?AMZcEf4_f;4?;|T2SXCTxneL#A;6m_QGUj)nE?U=ux@$>?~Gdu
z0h<cO{cl-RzgQKYBp3pa7gS0NQ0OcKdd*;DYJ*V+XMm)?Yl;4af|d_Jr%@zd{=J@|
z8M`~EU}<ETCN02<6iv24{g<FF(<F{Nohb8~{+Zgt+=k4z_VxbjH(5XL75ayE-^GDO
zj%Xz6zq0S=t>7C?KLrEu>%UWG%ZUdmhk#4~s2HGPmOyywl+x>8BnHU4*KW{A>uZ*K
zzFb-jK~K`(mC^Yksu}syD{N4revb5cVp#-&O>|_y4Szs#LO&H5Vju)k$l)>vk*nM3
zsmLJB$p7*4o34)n0to$eXXt?wz_x1{Lo$A)xnVHkw>>LZV1Pr>O;24xU%g_Im+-0;
zB?tIn8U17W!-}Q{mJ$P`$VF7>!3ePFa_+(a(t%IAJFYd*DRHz+0bQY?K1X+t;{Sly
z{;Mnof0A%&tPW|i4!)L7>;U9Pr_wXhmZ22=+4_^~ffpELLC)C?zzLj)0obkLd+yH;
zS-}DW<jpkMO4@tENP9+PJgHy+Ke*#ZenJqRK<p@?ShPqCxXX6BBnNkdUPzj`@4^9D
z|14q4wR@Y(;Hy;ntO)S9$D5^T<~h`@vitQWsw)J~)Kjc!<BaEMfa2vkt`@xK=+D=$
z_kxFQ%d_>q=E3acn(svg0WTEka0U>%=}|kXr6Gi*XGCc~QVswI^Cc6s&`N}-udcW^
zsKpfAL?{}Kl7Ps<Rx`k>4}4-geyn{i=Ya2}JZ={O1laxL(zDa~sLTLF+*eG2)eU_p
zahEqvnQIaU!Xih1zL*}!^gqKGCfIVI#cIv>BGp;arjUx90qWiKBnh^)B_^y^cT;Bo
zKYXz00%O#BDL#RyGq^P|V1s(5ZQ^Hd-l=V2b>I_&f7u1i2Hpx~{n?67wr1nU(KSy;
zBu@4$@x$i+^YQCluJ~lr8?Q*8iwv-Mf3K3CsDX4S3{Hmq5tWM<<1?(gUll&rs41!{
zWq`dT?E`YF+MEHEoON+GA_P$M&u6T{fs|Yn+#BTP9RuXuvNuSJPQzg!%b%94Z8=Gp
zsyK?_O&L=X!#Syg&j!@L^AQbfv{{LNDvH3-?bpYje}28ozJN~PdqR~Pio_J+kN01H
z{t@U806?_TzBTOYN!WLKFr0FSTbkBq>)tqUq{aa9ZhG|VS|&x5AV8vy0QonWzszUo
z&)*0(YPE6|(JHahC;=&@2m%aIs%uVZU~|(dl7tz?DUT&HsBXdJAlmRyX_xd&Wc8xD
zT@`04#qxCg`1KE2G7gB@=nx2K9)<cLK!12!nE|L3KvbB(AUr^HK-XcDOfH3O<~K!L
z;-=iH8UySU-SoOR19AwEZHM-HWR{ihW$4f7lGL@7JJkR_n@zzLnwtZ|@bJay;0o{x
zhamNDx2Md0uMQJ&5EbkE8R@ze$)dj}_Jph3Z$`*}{(O9huQ_JSSCh_w{`6gC2Ke|O
z<OiGF>)|0WKD2}fjDpOrX^FSd{(qer;Gv59H_Xm1Lx6g0DsVuGubVRZdo0taUb_@i
z4IpXp2Cb2=IXCPXniF<X16YzUga7v4HDnv!WPYp?7&vE*<~EW?|5G4sM8rR*<UfA|
zH2^yEbLJDJGev)a{y*>U5CR6#pXj!p;ER^Ke^@G3d${$eFr=gmppN@@a0Za`P1O4V
z4gd<=$|=PAJHGEFKCF~#07YVe{0Sm7Pm!e!y`G(P5(3~5q%y8!`TA)#*%iD;bvF?6
zYg8@$Ez$Re5flH}`l)aL75|xU_+Gx68TyyW|L23q|Lx&?u|uf-(Cj3!?VJGu+%)5@
zSlKLq_O(2|HN<r<4OJ6ec0`rH&GA-7m>uJ{I@fHd22e^2kb>9}rDNSB$iAD0orOR*
z_~%~$%^)*U)1+R894lp~%GDF6O#I6@fQtXz^9<d2bMj~C|Bs;lLF((p(xCKbW@y@=
zB<&KFn^ah*j;|xS*jqy*_*Q2CO&h*Lb4xkAG9#c8-rRA$y#C@VEf)1!Ou-czjZg||
z*{ECZTAth1k^Y1cgURIjMYF5v<-N5c$NG0p%A5nTza6Wthh=^>3-m9Ge;Nr4LUV{i
zL+?{p+pe4e)fECZonA*viQk%zvDq2G8wSt@1*j?RRC(8#iIqA8te6JS;thgno$(5a
z^3EL+Lp*8=LN#FbJS8-rOh%AgO}j93u%|vm`sb!VN&NH0uV#V%74@G80LlPbh-b5~
zuaEH|yi^Eq>uBMn?XP2vB%W`Lr`O~RC}tB6G=0>>0Tl??KA2dkzwAWgK}BMK!ke*L
z5#X|IoP^!<z#X0k=T}k{52MNCldJ#74)iaH|9nwXfO1eZGz?dB4Gi#)g#N#n12DK4
zHm(03>;0b4tnARy$#ZIZ-SULP`2(L;Z!L$Xat5%Xk;mx>RZ9M})}vHd6<E2*Az=BW
z@t`6xK<?0lK&RacXHHik5bj`XbY}?oqGP66&+B&0f!t*Y{fQ~?!8j-tj)h-giS_sM
z!DB$dGcYyUJLh0oD<Ng5i<4)G?k&u_M9<4?GTE)AIf3O>jHIb7<~#zomc1vo>Isbo
zs8Qzlm1j^u080;SP7Hwf@qMTnhVAIvPTnA5Q^TbB*>~6VHJ(i7O24s4|6daF6D8oC
zO^&J&fjemy?|($`pXY%P9x*M=A$Q^T@4raM4{C>i)#-_!a50t6plN)+K@|}#B57d&
zxif%O3}077Uh4Cw+kZ&PRMZ^6$~7g<LvRRR%83E>_&lV!#ArU8pF$%bLSVn$wL67B
zp<R=r)q`{e^9gQg^~sk+{*&wf>;0oNIZAj&hAY5074L6OXnN<cXBgh`HxlxLzP{QZ
zU_%VoJ3-?HXV7$V^D^?cGJwn(z$=D<;Am)~Q=s9i)q(&O4oFn~tQeoc-B~n_5+Io9
zE#N|g<~&i)#o_Std~Poj@Mh!jICw=5T;Yo{ZqUvF<oYjY^k3?F;!YX@0n+PF6@736
zC5~pJzm@!;uXmy(HbMX-oZi@>Ayrg8rgMCE+0ShZP;&+_^yleDXx>BUt_9ecx8@%e
z9})1VR{b@1TwRsuEKPFciKJ*S7@E5EnQRB`#=vY0<9@p9fvgGNt=o%h3_z~`HzYbL
z@`k}l1Hka{OLqOK0I)S^R{NaxfdPJJ*&#Gz=z~JQQMwZ-0l=qC>3bw944vdTnH7QT
zRt6B#!x;K!uG|QsGjn3K+^?++P=bI9b3W9sWF#;^8O7pKk|T1po<k(XWw!59CgAON
zlX=(`0<tE2$4;+aR5^gCa^U<}KA#PlK}5Ut{r9r-FJHv+9$LvvGk1T}>)+frK*&#H
z#sm*SxpZGcC#CYZh?4{Yhys143Q^%GYGr_mGk~LiF4|UTZuFpB+4EGcQW*!Ry+J7}
z70z2m<cXJHwH7=U6ZP|S$1~mRP$>rMJe%xy-5`L@S36y?A~Q|G0e{5n55i0tjR7Wy
zF?S3Ce*LNlc`&>B9(Eiq0DdzFC=$j#zTigIKAg4+t=_>^O^c=-WWD*P>rNl}-`W|V
zNDteFCG_WXLDASFU+x$dYPFe4^k8~LT`$`(Z;+T6P(pw9a~vO!eqSFyE{ATG08E+g
zqz6*tEuvkjpWV_b3P%9H{@-Bjso#5NrnOJB00RCWzHrvK?}i5c+Z$vI@ayBFNEnkr
z05$v48oQ=~KNyud$QFO=zyMiPeJ^W5xQf%DuS0+J(F;N#^9I#H`AUs|QeprwYILuq
zxW~xR2jsYdu$wKo_qquI#OVLASa(+gat?UUBEg%cq%86k4~ps^AJq~7X5`^nI2zvn
z7=QofIieqxWB~yJR!0#15`B|9owA?qTy<Z3e0-FA#T^)c3W0#3|KlKj%?eqAxi!SY
z0cyQ4e(56>bvWE1JS!yztYigFab!-@3sIMhc{dKYOeTkRAwZ+Q>ko1<7jb7bfN+2i
z132N$$GfU5VvBhIP9T2}K=1{u09SXd-d~i{yqqv9K)?n>zvAkZ{Kok>j|D-KUu17N
z1ax5lT0l>!ao*M&=c0jwjy+c&rN>qdC_a;WgX&lEM7=?!#DJ5uz-fh0ih4v`dV09`
zw(UHy3+K0_1p=7wp3wh?+`2_~HQ+mQ2W811>HR~Q9!L!<>By=OTtJ#WhT4(7|F=Z*
z-!%we@-_xvy;AhXnZ>x|(<4?39)tRMUuA#m!T{7Z#XM<TJi;ZK>r>w(hRZf;O+zUl
zfO~`LSCXd(7CGXIQ0_WDS_7a_|MRf#5*A=hPMbJ@MSmAS|35$Puc!eT2mIj>kfw_d
zAuphG0<<queSh;_fJgmstoOseWTArQm84Mu0cWb<Q_+8Ia=&nkG2-Jq7DWj1*L&tr
z>cRl5T?p;7BvGR_&@<OO;835o=OGmuyV4tkXt8KpVgQ}hG({;+bng<n9m=ekGTXoa
zH2Rx@a~~GDz%Qr)nJK_&P8i^woN_HWjNgEpEX*G6Eo}%zKw)2Z)4%0Q|EsJ7{C@ue
z4nox9+svQT@5~3eqQ!d=fhL@qWhZrDfH0rABtO0w4Mr$UOy}AGFiWVS@CGgKG$g!h
z%MmBa#}FNH=sb4=y$b{EaAU$ei~cUiDY5nbni{|$;Da*&{+2R84u2Sn#_Ns<fSC>@
zfcWY3%l9ADz&}+8U`Y<GS~u;j#(WwT@&g2Xa0qB+0M;)6ctAB10!nsHN82V}gCce2
z3|oZ|P<n%677{KJ1CENXjSOp;Le$jsIz@)VCZSGKcgQ*YaQagr@Ul06D**_Dhww*8
z5H6m*URJjwn#?RoEYJXszyDSMKu`lY1a!#@KwObte^kj|f`GPQP}VE%){tko+8{LS
zU9jg&Pe;^Z43sXU${Td2A>l(yjyU)rhNE<6>a%mFN+Alpst{Rb{^tNdg}^J`0G1Tq
zzyKwK|18#c5EWH7b=ozuAEF<jP()Az83c4m`&@AyY9Yy4`Cti(%?z;5TY?9;Db*Oc
zn$_1#Yn*P|qC$S@6co8ZEIqI_F@RXWY3OL0Gdpy12GAPqqx7SWG<LUG5IrepfIlCv
zcmo&&{NxNk7(!rxGQF|b(|T|4L>K^p-(snd@Cyb3U7(3~+FyJ~G8Pd1TN49t$1mII
zrRgpp*BVX<hF(4+`*dvFSr>0mO8o$r){X%iWcFO!=<B-IAvff^Hh!jjPQ?79^#3Us
z;59XX8Umc=zyRdTl?(u<Sy2PS5e$sM!+t+_xL<#(kS~LPj_ILm_P|93QaNdfMvNO6
zfH{6MS34M=N);-i^V1=R>6E5^V}js!`3vYF)Gdpc`2pHG1`s{aM=)p_hr4zLfH%}y
z_R&Sn|2xp1TLAw`4WPFS7yw*tAMd~qY6jQ~mSE^u<S9&JXz6QW0amp>83c4q59PHe
zlC*^%1_4S2C{KyV`9a;rk*ERFp6=o_wlu#vDo}if+#5u*v7kU8X>A_2j$v9OZcSg$
zzhoo1(A@lAP&2u@UQq)W%)Y<Be|-G<sThTPRh<6!YOdYI(;P>)$@BK6e`{JF4I2GB
z2!O*`7QV^~1S|jo6b!H}O#gf}>4D#IWNEPfk#5eL5unW*#JpC5H%RrxbaFQc@G~9t
z)Xo7%Tx<Tz%zqL7b0N@G4PXrL^QUseN(KmdK!6|j9nboG$OC-n)CE|Dd};~){&x^?
zr?;mPvMfWuUCsdIX<!8=H0gnHH1N{9XBuPFmK#JMAUlh?H;Bb7o>y8d+SW0E_U~{J
zt=~D1hWid2079TbPHz4a`hV2vPlZ5NHQ-%x$CM0^2L$LUa-i(~-{Wr?1bm1P&@n?i
zX1C|#M+O1p3uO!-nG(TpssRkw=nCjROdhB9#DM%TL~l^$wOTG&>#+7w0x`7A1)S>>
zGpa2v1aFA2m}Uaze@*<Cg+NC&K*9hOPmnJjW}b1+UG3O)`n~wCMC+^n;{B^*hWHW-
ziRfhrILR1btLzlos0Xf&u5QxmzBW$)UHLJTyg_{EA@y&vVo~fiH;;q%-J4~Et~k_o
z;mBz72f#b7Wg(E6|1$W`ZNZLeK>dh+H821ea@ioJZ0zyOaW<I?NVEh$J_LT~lp+3I
zOGGcPccKN<7+^0de`U$gBzMr<y{1FmFwFL#P<|Ra-pQSQ02TgOSNj{y3Tf*YKv@sD
z&OOnd=dkzL<`Dem{!#wc6F2|W^nXDOc#Q!V?4Pq^<y`(JcLDxX3I6L{fP~Hvz!T9w
ze#sypItdK0tBeS%ttLHijZRm~FhXoQFF-)T>JEG!vMOSm+#57&GX+`Oh$A*;_YMpI
z98d^>%=}lte?<*A?AxB`U2?z;48U7f?f48HdhJTBg8q~t;Me=dj{pgsA%G{M%hW(H
zQ>qNm(k8ye9~k?ZKeVuCc3}WNlL4Rx`0Gsg7cWR@v1nVz0LlRR6kTlxf9gUdoq_{W
zhUmQZx8nX)ssZ6-(x%(W62zMrfORc;gt@Kz_%7e_A_Vx0_K^CiK|n1x%$GI};q{0z
z89+8zW`Ll*PjsU{FrJ#|*qd2)7Y5+xL0frkPKEH#7takUO_fu8&>EtV$mx^UCj0iN
zkWa^eq`CRu1pm1ZSls86dCOD1%m8_LEni{fl5=O!pI=!Eu^I#jxncg+lcv6Jn5dAs
z0{*-&3I<Tm2r6&+(EvMfWcX;RnMt>13^_}2h!@j-j?@*{VUz%*q(r7oEP;{Hp<d9Z
z9%0C&!`CkKr$S);n6wRLt24kKfdODH^w!(%iYs;~#wFp~S5@qT;RodZQ-cH<1o+v*
z)fdkTk;#Bx?{C$uT-tK1oAkgnA_PF6bXV&*ZmX<fTi&uP{JX4*iV}a<GD?6pa@V!q
z0VkGbcWE2p^RAs>{x^#MvJi+blSy+{u>@nQ48Z1{9Kv$`QlS9gK)B*W3n-Ca&<X?y
zD9}Z+vCI|lO9la)0aT`cecc-r;t0)0)Gv38QRH{56<VKe_%2l}Sg~kp#{e3Nm|xSm
zVcK@5u%N$YA187Cs%^pRell5qH_YX0VSr^EI)>JB&lh`C6tm>{@AzEz{glc7yY3u%
z_e0uo#4igM2?X$BB$+GVpI@v|WHs*7xEl39=-xnG`KOU?wiXIxEjpF!{s0>w$uEi8
z4HaLJ4fRx=`ba|sHZ}h{z<*f{@FuhANWEK$vyHj}m#n++8reNBbhRL{oiO8o0s!v5
z==!OtePW2{*9SNg#E}z{on4g?p@06+Mv<%}udO*SUzfHnbekuJQUP;>x(NYwn%)Kr
zOR0XWkky-CacgVC(y<fzcY*(k8ZeqT4GfS&?9b27FS5x0tX6T%8>kRt#SO#rXb!pT
zXU+h*euMY#A^_B{d>sNL!<%Zy>C@PwA|mw98%O^~*TbWy*I<6G$OA)N6Vc3~j<rJS
zzo#Mxs90(ReLUl|OIVP@?vv<$-S9tG1J;v#HtUMEjjuL+{P;zwPRRcA8~t7^=u1w~
zbUrZM6ZzN8>NBK;=70DG7Hi=Gx(FJe6avJb83c%SPnG)gRzK9PfH$^>GnE3Jn(j3F
z1D6O9^fzZ10`(o!#MQdhigD&6*8)`Dpe6E$Xan|L+nj^^)MKInc4q((0#i3HtKT5U
zaYjYv!*aEWqo2j^-|W7RX7}T9-qZB)eXjLqV~q`|>uaX%aRvaQ7Xsk1ttA0TEWi5C
zG6>j;=j-u2a+wVH^G0{J>(m!ATTOc43OV}l=ov{0g~M$Oz|+LlLg0vJ`-&;3wm_gd
z71WQmIR|upB#gdXEIO+ITnH?J*<`n344_$#1+9_Rl;SW0VCo-FBX^(~W1|n_Wpo#N
zT9N?qd)%Ly%pBc)jQX7LB?~|X09_$KG4`~i8txc))-uD$bG_wJ|DgTw_-fJvmnb5q
zks9W3p!*$S0ut1!eBAR=^#-XkQ?sJSW+4C#q{&O*L^dzU044-*c%V&=2?I<)%1uwm
zcbw_*YTHI%n?D`h!xkZVsF6*R^VB>H1H${m`}LS!U`F&vzs$^V9~^GDSZBYM0@M`(
zB!irR0sN}lNg5HNkM&kKe%t#(dc`Z1dLYqyV&oWZ-<r27f#2<VAmZMjTnIGk75?tg
zECi_c6=n%ts2AuJ89;5pn7M3Dr;|2~H%H65d-`xhsNV0xNHdD=9*p=RWDhLE)aQ47
zc7*D=B~eqXkT8I8nQ1TteOqwAef#lCN`J|f7k|zh2$wma=5##NBSQSC-U^a;7!px>
zrCJXp@>qu(dvDJS$RMDhUgu67!tIFxoSVW%9HRpxsk4hJ#xKbLW(xt%Br)6ObFQ^H
zQ|D|4<B>(~IQ?nVC*oX7)2lwe5)p_@CpE!OZJ`x7EJ19zmvc{pfd_>jIPl(oD^|@p
zBp`(p0wlnPxf&>t|IeRtEZ{%V12<@3UZ25m=(e{EphRn|*o+wd7dhe$as?=xG~gIj
z|GBLL{?S(q!AuQ683TBX0s8jPGBrGO?&-Xj&JCgsXppKpPIZ^u1Sjn~gaIHvwhs3r
zXXsH^AaDQA1%UVUOT_>p1XR-kh+O&#I#KOXi3pV*suB(CFeJjuk58!wZjcqEwq_3v
zr!_kaIH09yKcy;Qkr>dFn$e77RE%UsQ%Ehrmt+7{0}$S<qvMU~bwlgfH=XI!PYH?9
zRJ+bJV1OyT`a{jsZ95%Lsgg)`y`!WLylnupPjdhus<%P|kU+ps>7{>Icad8c;089y
zB0`mCdJ|vuU+96y)X}%l?!4U-@V#gmG5ft{(SRZ`puq{@d+PqSO#RRA3i#2Z7i9nl
z0R#y|ixo0wr(<M{Q)@s-?xthH0CVlS0|rd58A<>EAOJ~3K~xybi7h<661#x>a6J-B
zA&%DHLd)C&0Ct|-1dvPpTwD0bn#+izdz4oe2v+0xYCb@RArX8v>VfFgb0ON+o3=4P
z%Y<3FPBa?OAu)iT@lEQ~q&nAqS9yZli!uO&z!HFCu|(!@>h?@@^>xb~^sY0&e&=+W
zM${~f$$uN74zJ6llHvh!4bW?l0J0De`+ueGBKIy35M~h}kpYB8zFjm5%D_!};075!
zI$>8oUt9FRMF$R8K54ONVG1_n!)N997ukNRqePh{_?ip=A%HLf2Cz*N)VmFsfg`x*
z<evx;ny;2Cg^&_Yny*6>0uY`Pqrg8^@^^#)UQAYd;I}GY9&p3_0Fk2_yfV%p@`sv>
zXDu}Xi!L01s0v8Ch_cnvm|7wPXpy796$z~de@zAuTkz+H@D20xqIgBSR+9g(>X@%$
zfWiq3a3ysEGAaM@ON4-rAF;PkCkVJ?t^k1n7T@BjbPNjJ8?IuEY)vygf&pz>Ko<u1
zzEc&jlo-%*$~7TC)qhdDfnP3PlmSEyc>nl$E(r##R;!NfLnI79M;p&M3WO>M_@T)_
zwL}oHwUl~{Z|!mGGT?2osJyJhu(0e>HF#x~;1WOG1I;_O<b`yCfQYGp?TG>3av^ZR
zQeXqU=v5i;&!3+^A3wJ)Y}>>Dgk&(9gb3VF2?0OZJi&T8sIZzQc^4~>2#E|(g@EqP
zfTTeWTy8e;X|B8Yj?jO=0V!1hOQvA6H>fHEwh5N|2B;<Yk~{d%A8JK?{675~4yaHJ
zT9^|C2pI9c-j(E+<$_6`q#Xjz%ybuI0AYYdRS)bO6oPwpR6gwr&GoT2vWylX(1`)o
zY?{>Pt^)+*LV%N;wm6Yyx`KNwdQAo}EBfah#s7i>$^--Y69z~a@pfKK(7%^6#KlCA
ze+2<WL`Y<Ssu1Yz3<$A0Ko6FHuJwneee9wIw4LRNdV@+G0~*9{CIlD<Q1w5NUyloI
z3iUbz{Q3Dno7Xv@La$&13=n*Luo=u12>AJ^W{1=uz?YEX;kB(>O%43{^-dX}W}$Wq
z3T^L=<r?lBorZm!wv~!?GX<eowA3-6sUiZXec&7rO4R=fudiQ{0ht@^=lyRd^|i*C
z`OTS6$R-o-ohJ6-G6aa^mq0*G2JCPL>+Qg1mVNyCC!_xR$AU6IRS0ws3bpEiqh5k%
z4(cET+71s<6|h5MKz7wA2OLymQA>B?6&X<YQGY&;ojG7p%u&t(Ael@62EKj~JinJA
z;LnF7H%x$lKQ%SblO%@JFKiYO0t}$kCyOyaT@O5mZT0rBn)E<oAy4(8r5ldlK?t-R
z;_^-df)oenx=vfJT9$A7P~ME)j<$?p*?T`-90Dar`p?Jjt{hNe0LlY!zTO1No*)SD
z?y~``l<q)&NnGGRf&d;70v3Q~xQl`T7Pa(&%g}MWRt{*?12@PttTB1o>$<}MwVh&2
zi$zO`0e(Y<Hn4j()$D!=L#W57twR_B1Hja~`1i*<917ust_<+cuV0(?jW5b8V@^=B
zCzBh`17Z-6c>X*1eSXQqLceOY!T$yVf?RnjHYL#kphjq{8@AP2Z{Ms3vc$=|x}c+S
zOs)4QrB+~(7;tNXfJ3$DiXuS*Glqgv&l}e?`+Z#_%R<Wq?Gf?8TfF?J7@+j;Umwey
zuBs=HF~ETWfJXt~hpKceqD#K~L*Wsu1OZ`vNFkuLFtQk3%XakTj%t1YIGKH)Sn%f#
z_4dtrAoxd@YurA{njO!gIWo9mR$!4Bpn`xE%5rT|bj6aDBoq|Fy)$wQFZ?^wzZe7X
z^`U};YABU(K!pM7Jg|`bno{9G0btJ@fCK^(1_3Ja|E^_(OCX?2Vn|qcQOUNZ<B{`!
zZ=w|lO$(hKgv$1zF>e(sO?n_(N8Db<zF5dlu(D3v8}w*`fXy+RJH+RwY#>E3eaaXC
zKkj!Uz%HTxdQn>vI1pm#KOd>U0Hp`;<)yj|00IDjd#3p_2sn5j4M9N>0_x77E{P!&
zCfK&7?r8LX|2O)2t4n|&)IR}1FMGY60h;wdSmlNctqjn_0jnpq0*l0eK!AW{bjk?*
zJc$9L<z|D>HN6QuFtlCWJ4MUoLb1wlAmmcKBWNyDdw|9|J>R2Qi6F8Mnc~kN;O_bF
zY6cJ?pzaLn1Oeo0&vS44H64u!`Nw2K5*+|$*B*ebcCSMV)@FYotQfbq*y#iT5$zjS
zBnCXn5U?uX{(fxKIyajb9aCO&l4v^Z(DS^f2yHfMHu&IdP>6+J?~6O$z>a;t+6^jW
z0o7@+T^2X~-DgUClMJXq0DMVBckcoL5LKPd#$%U|pPe3KfC>i$p*ad^YRJAzrCp;x
zkgl{{5A4JM)5ji=sVJuk*)x0*i!;C3X{Y7{jAx=#Y6JbR>E6mD$34BOIAQa5QGx?n
zEry?gl+?bG0rJUshvLGM>r8t_eZ2+&U+-0ypei@4G)`lRFSC*RIr=}x<=f+afJ&$`
zoEr{I7Q?r5hbGL8dLUh$^}rSm_$tz<3O(>^`gO>~ep~*D$N|VUKpP(oeG6^A*Bj_}
znz7O?J)yY530J%<!2$K7M2gWjN(PVtKn4NfD-b~A(p7&zJu!qfBsk>d==13`Iqd!6
z{|%@4{xSxrv@#Co1JikiBj>YA8}@cR@YLRAs~ZG}68uD{pZ)HB>^R@0%m8kf?rq(0
zPscKFFm)kgt28~LXhYP*=dF$kclp!<iq48=4IBW<nV{r4gP-#y2!NL2f=f_H4B66t
z1n09m3J=@)eCoQ?H-elwe}SJfK#c>!OET8Xp<#C!%b2u5Jm`Vf@8*?h(@n4W@>x06
zA@>I57D1OHl=?#He4tq#zF(#Dj;P{TG9m6r6b=3b%jW2OZxzK(Q2_vzM8J2S1@xLB
zK*AIa5U>sRmZ1&2WZau?eRn*Xap&l?ME?>4l*P$5IJ;2Xk?39r2-vkkysAt0i!1s{
zF5nF+HIJi;-0mgdFRk^_wsv<S0|w2hYb$C@QmnaO(Iz(;zR8(~p4WXWaasa^GOY;&
z(3pNxe(-Mzcl<O!z&`9*USJvCK>PpJt_Qx2`nm^7M}?R}ijzRo(1k9DQaaMKP1a-;
zG!v~wAWNzwt4L#7T8}y`>1MBSp&i&G%#9fhrM5<`ELGHPsKUv?X$_7Ri`lbHh`9=S
z*IaC*$-*~t%`Jin%W^IKKA*k!yOVU1PPXjq_aU-4NvG4j@9+Em{NC?9XAj%M=T}k%
zhAmw4l3qgua9{{Z8QPI)egM#9;<+h4U0s8Nio@sgp^q02s)3+FVgN|r=L;<Mv?0*>
z$#9F!>Ihb4I}S(U6b0F&iUPE6WOlxt4Z6?k2%va}M<=T;3on!cIs<wRC`t?w{8oYI
zSZ2iI@T(-27K1(x{Qw<ibpR;ZPAb;>MVW-HoK%Glz-v#=`^&4?DoU@y5CCr6nVlxV
zIL!&r<%n~>>P~As`r|M^8d>6URI`Ug`z>Qpbs{G*-z}Y8z}Mvopp5LnoTJOab5TH-
z0RV=&I!gp0sybX?IL7K85#$Wrv`8{i(C1?q7Q4m<nSzE|(rbtSPHb)Dd6%s{D_3I&
z3Tc*|+XSn^4y*`({)mJvue~fu4EQoM8dOLOAb~~Ce;g5Ca}Wavp6UTW$G})bwGFb>
z_7?2Z5kR@QhvwYu+!Qcm_|j0$6&%48FQkC5zzM8}^Cz+{tF57-RU{sVGy>A6Z}Y)h
z6sB;KivXbO>L!R-$)txUjV_U6x%uJ&lGiI<wjF4Qfc`OAV7y*n00y_@1cG$->k<Q$
z#cO~*wbcbyC{HfTfz+;Tl%gP6Ep{ps0Hpw7ZVDJGdu3>_E1x1vP5v+jgLsA;X=#z@
zau~~c8XYok)pgYhV7#bsO?d#Q2+&PxQR0-0+h(n2r1?_=xUiSWQM|EAtlkdPeLgf6
zLFvQf=Ui^}GJOKwAyP;TKwt1O5P)sYuyw}3@bK^g)4bI&oU9fCa}YqD0+h-WP`o6p
z3cp|gaAI?-sIY89W1~}2n%h-VBO!)4Yme+~_T=3;Mk&gtDgl5F0byBYowgp*?o{Mf
zX1**z?9Wc`9}<$`&#&GN%mH8&xVZ<VFGfPWuH1F{Bs%*Gi2)=XxGXzBqbFRuUX(9c
zH3W17V6g536oB?^xZ*ysLL{hE_#?a^ND?^hT&t~BRva$et)3P{rdbe0#yTQ1^{rzA
z`KeuGvKIhQiU3Y*x3<vaAjawN&j)}JPy$HtR96^MK=pPYr2uVVhhzC@@lstNFoHP&
zyhrB<UY;cw!WO);)9R?Iq{X5kpd$dIWgnyfMP{VRTZIQPX{c2A;O?Q68QJZyx?~QE
zQ?NFn!O#1AeAwy0IyPfNG>b96fH<pPy(t4g9swgF%ZMU4$*tB_e*RS<f%USZIV;i-
z0SmAL2Xc$LnRt0rKETl~0)@l?1nK3dfw72>kXC1~y_((3i-&-Y01Rh2P(T=NB0pEL
zfX-s!hXnytHPhpCT3gc@plf1dvvH}Vz8>9oFbiC*t`My@3;-C+EgcjUnbrZI6agF!
zBzkNOY*lUf&<^x6mE~Wx9hjFsk$JYSw|w~c;=}-I3NGFm=#RA9WP)`Z8t1QTHV*{m
zV37U-0T@qmqyW5$l_&u7ICa7Yt6vaVzn>RdZ2k;uBUr2?+t|u8yy&z70D=Lv369!^
z5|z%Nihx4*aRdN~Rzv{Hi)_8s(T>@3^Dhg69q4uSuya&>tHuu0NnfDfX#jwLuOvsD
z-qzq^)j)rw-V+C{8I82IUIqXt1hSP85TAztC<UM~Ef~Fg7MQ;)@1~D%BQU)s#qVf#
zG-rB1_%QW}$4Rp7PBA<JdVj1R*<x@gUun8ieN^YF&Kz5!c1$W>h$+yzwb}2iueUZ<
zu_QpPb^n}U(fRDag7njQ&IuYJfKe+3D0&1Cagl0(wjs~9wx@%R%V7W<V{_Ec(-VNP
zp<j^#sPsd$t_a8;{!)*x*^_m!L~(c&tC&ePwkAfb3gN80Ff#nA_3Y4K(U%N$;Yqb^
z#k9g~0RZI)$RQ0FKxDDb9a9AWdR%C*&lwe+(+(WXOP>^_wiqe_wzzoQWkm$~Bh9Um
zL~A?oHzcBqv;uP@Q7JhlkZTNuTL3D#`Wgj@MLq(Ret=gijca;YtoQIz152z}c(8dE
z%TcvE<MDb&3vu(p+1Fgo5(t6)I7o|+s}vv?BDYJ@dIaPyw}1e#y%Ae3SF=|v2rgTA
zk@3JnGFLj%k89>SqqElt0X?*MoKTE_#i@Z%1g5^n<^j<pqt&OA7@up_cu~ZsuLx7o
z)29^B<JF~#sM1G4cpO$NhA**=wt7Zsucy@~t+vK?CYo$%#QHR&iBYic(n9bxw<B=2
zIB3v0goOq=hlW%N&@~-g(u)X)mLec;W{M8FC?s=WZ_ddAIQ1naJh!WFYzG!e9}gsp
zid7jZ0iO%o@4DGy1d#AzNMJbPaoAcxhd7$+7Z?#P8)JqP=hGDhrY&OLjtpXhS+%_I
z;E*~f1&jzlq^?1|^wFO8*!&{zY>`-yhuaoLN8c)^onW~}+LJvt_`^iT#?a0PvqNvc
z{WdrZU4^hgC$#|a8#D?iG#vyl01<#u)*tP;=QA6({Z&AZfUwvo3L-Vg{p?(;0+jj(
zNM@ny!lAK5PWp-b>>D6O`?-viK){1>fJ~34*bZ1+Sa38FO(Y51Y<2po0ze4EhkXOX
z!|-2e1UYVS1AK*`70GnnckjLT-q$sYX~O|^P%O|aBM=Yg_If>FzU8G)#ZceQGb4T`
z-Gfc0TUv-{W317*$L8|2I^$8_s{kUr6dFqm3`J<XU{I4jc#ePo)eO`qpb!i~HxPC2
z=uhscg<&?EKY9R<=T;an3XE=p;IP?RM4oM`!SOvK@%L5Z>KEC8ApP8ZDNg2!5`AWa
z5e4)H)Y;Gdzo>zMc--x<wRmWcgU}cq0|R4Y#=j*5^DT;H;G>C%Zr@`+mWCP#hQ|hc
zKD|>K@aaK{;>U4cg$=kp?YQm<E?iNtCv5cyJkC@sMVe;7ZS^>@AepDWzBP3AwO3zz
z4RaJ#D+_m-(RMR1<*D>Bc@W^GDg})K@>@iffd0qssm!glw>G`-tJi<J%WU3$N{4_j
zH-Z_W;9l@fk2qoofV|~5zpIZ|n4t5fqV%=%=#ra^D4^Hprjej>HNY*L1aKEyJGQ4m
z0vL{<Kf^~89B)i#{gDoDl8q+pOv3J^0O%i!V&V`_`&-buAHhHl1%W`OME>`6{WV2^
zv1^Uq6y3kX%Zh^Tx8Ln%C8taMJZqB$(Qg%J38<?Orm9EZ#(lnBT8pZrnqN-K3#if$
z20;BI5>y0e6p#-FEy1$s16gjpWzQrblkoYYtIgXG0r|`0MJG?%TP4v`FNT|H4w8q8
z0iZYh=XUjnBZ)$KmG(CqA2nEqi;$ue=U!t3P|;`n{!B3fqy?vl(9UzXWlt>xU1zu3
z>pGJ5j!0-2t3QQsr6|;=K8A)zBleDD9ZLbgM2Gu_RV4H9u{tmD+H=}S2nK@v!Jz)?
zMnUj7Aaqr*tVcL+SkCQjlR*0Tw51ttS(<e#j&@OOZ4}3d!bE6~65QrHID|D|u~RKh
zFf2PpSB^S^IQgmcF^^d_KGj%2J{Yuw{vFt9X&^I?+-_d6jXAo~{Fi-w|Mu*&FRIsb
z+<(}?XFbl@@RM5#065`3_EMSn`{r=<hofcPAB^^I=+C3WSOo;A767YT7}9QAaA6P_
zh`5-@sHPVI06?zZx@0^OjpVBS0oT(CfDu|13;+;O8GuRTF<sXI6jE361JlKu(?IU|
zXZK|ci!qIa6-D=ZG!55d6D3Y;tydVEv);i*LJ^V}8l<i1X!TcoJc~*oP7UbJA&mm)
zZbMc5Ys-meRSJ+bL17$VtnaCno8`>jmFAmPm{+a<`Tuy^3bT3Tj$`ag&3DwSx$4SC
zCq>KNwO3qeS$jPNz}~w-58V9Fi{)XT3a<Wut~7RBOS7yjeeFE+*nwyVsG^rjLP9wG
z76t*--nsT_DgYvN$&QXBZ?CKCNW?qfF`j@&yO4lGlpd(`?Q923c>D(hfZy98v37!Q
z#D@;T!a+EIr}2_B`SO>(^yS=ur=&#o94{6cB*|?4SEVIMbT*5igk6%v`~9K_tdyNC
zh#qFY3Wnakej>_PbBN}Tb!s6cb?z5YfL1rKZwbm`Y`ghUa@b;B`H7E$6}bEpp8y=(
zdFRTd*FU<Yrsj^jEmy4Bapa1c_14X6*QfxfsadmSb4`u)WcjT$v;%V$mXpyO-}evC
zV{XTb>XZa~gN7LJxXShl<VJcS5D1}JuXWi~0nkAKV7Ev3I?ik7VbTlmm^-8aAY*5h
zI)&8XMX(z6QvgVy2^3=Q&;VfX0B*<z$(M?U4gg_6(t|j|dEB{%LNcfB)o|8>87`nd
z&U1*_q}l;S?Nv3{rM3YC13K)551<`*7W{}VEe>$jhypMev;-}{?49P5WT)l0Wu;jg
z`(b8D4NGfk)*pvUaG7p4E%~mDi|{WlqX0Mv|HJ-?dAq@_EVl#I>7QJfi(O&|Rx|~D
z`Hf<i2Z6qPmt6n=3_FVesPjf5tOUkDgyWNZM~B@`57`j_X*)~sKQCXGR?<ZPfTtjH
zB1swmI_f&8#cIR=BVkc4+3zqtDatd2|5apJR%T`-NuHUO)p7CCrAwKq@u^fQH8Bnk
zsi_z~refol-cv4IxG;G!HWiDF$5OE=dVG9BeVIN^#PAf;aOVHLbZJQ+BEY(wC!e;+
z7K`*2jFaXAL~4CpBHylA%ah|Resb=LB@IM+{GdY4Q2;cP^DU20zp>i<Z24_0vjge$
z&n|e^Mu{B=cgk1|<eV%ITZRCVSy*5wO7)_q0wQq)02_%!(He|I5-{(*IsmBBXJM*$
zbcjJ;kf}?|=2U<N0FqMyga_zon!jKJkc=qGvt`#Ti<8qOM-TziION;_03@>$F}>(x
zF%WI+-Agh6K$v`IVrnWiKCZp0{ZVl+6?+Fy0W)S60f5YB`}pf*<3~7)<vjnJ-;g(M
zlrL^Hn>QpUR~{toH8t0}$U%!DU%%vvP2?O^0iwL_x?R5_2h4j6Zey_>s80XHA~NpE
z>eU4+Ab@7l7<dEpsNk!9p}3zKL<oSf;ein4dl0>y>#&1L@G|&lR}XcN901ZnT^;@Y
zSx^!Y5V!^a`p=7o0k{Qr&=J%`=+b!sod$Xfq^~mra$`m=8%P1OgwF5S)C35Bd}0b7
z;qN8s!UYkKqQ0idd_o0)N&)abL==8a5&;0}_5sTgvfsSRVzI1U{zv46t>l<_<3{t(
z$QS*@TC>-(gZOuoC$HGN$#k9qU=w+v=?!vj|7!D12Dedf2Zo}HoBp};h*cl}ya9Dp
zh;_?G_Y|gQwIHC4wh;hGVF&;gJ;H<t4|Y+)=XQFiP6I&J?oDLun&q##fvi2zVV@-m
zz8TB_IA$ka{Af<__kovw-@SP%&<1<;J~AzJU-g{9PjI?asY|;H2)J}+*EQE}dw%Ne
zubWI?dpq{Tb=N$Rnn(@b`pUafv&qyvEx$9KdhfvM4}JVQQ>x6T=-i)3O#w}eAK9U*
zm<$C#DDATBCgLZ}A4dc<k*2NWsQL300RK$3+_Db<aNI@?uid%X!m}y>$V~S(Fcoh4
zeudkp*@45ei=F;B5@q!-D<VMk2L*QplTZl<s)`LD<_3l%UKIcw7YBEcMRmY>BhhHY
z%kgX?t+0wD5ndr-As&YB?dZr0kyT`{+0q;{8kkkXLWJcN9^<pQ{H1&(FkXC#?9FR|
z`X5-=od@o8UJ*FE6)N=b%>@9QzU7Hu|F`?LpFefifA($o;i>ChKE3Kp%Kxbky%J-t
z<6KvsKnnQkT_;EX<<`e21t15E$3Xb82_TCj4iF)p|9u2N-+;2o@*Fw60T6J<cV{L)
zx%#)i{jAx%5mZ1EI0qKXVe&nbGP&MjaS{YT!-}^Ei2wHOX7e_q+nBQhFK7DW=r6Ma
zD<J^<LFz9no}P>`1k{ZY^AZ8*t7u?sj7BC0)Nt_FXsCY_%fMqhtaw3XCpZzco8qmL
z%D!wiA(2X>lLiAz_&*~bU%P`LnJv4!Nz=`yor-(MCe!^C0S}q1+q*LlU2k$suDfcj
zOrHP%cKd(0#?*ZNi(mqdKiu@Ud!|y~Zc6R>`Hio{{{17bb8Aij1)RF(E#Us2A4;W~
zmM+~N8$V!P`fzNj!SvZ(k3F+1^Sx!)?gQyi0Q5zkv#dKtGA|tZN1iCV&E_WZ)+0@C
zkpnku5Q(SdIN{eV+egkn+9rby&_upv{uU7*Y2wK)^G3tlsM>+*^pEDIe{a`9ORH)n
z6pLMf3K0RHi`CRX<y%h_Avg~a;7WAGwS>@EUi@hx7*wY)Z}%2`hZGo%Br(F{&yV6?
zpk9fjADl;&Us`{7A36Troi6w0-~4*RGtZbj;q`5R=I%}BU%Iy2V-<wW$AAI4H{lZi
zz;^kzGnd{c_YY5{-dy$af$xl`e((*L=&Rn0#lCUX)qj2g?1m?{qSgl+;HS5pd2_>|
zBe$J8{n^K!`c$9)_n$oGIJSiob{r-|1wdcopyiH+b8uxd{<|$3R+yWxmdF8630q!-
zgFWk)u3Gg7;L$&QZYcu5ynhm2-)~;|OvQ;bOQ-*A-X8#;w6kwPgVhq{t3m*%0o4W+
z-2OQrKuDYm%s~XcOnK!QI<!3?+Bv}JPnVxsLaBQ=__!M`G$&og=kvJT?jAh={JP<B
zx&8k0=RIrBU4MS(@w=aV=c!#AKJ@f6e<sUqyFtM;JWj~{-K5*O>FUF%0uJL73V`)5
zpZP*&?`Z7TpF1?ZzbQ8Lg9kz0H@-Q3<n}XfZ2miWT7Kd#nEN06z?#&9KS-sX{_5A8
z##2x4+S4>c9%%30vF|Dvd-DJY&9<$xtoY2<FRor|*&#f=!hGY_t+!g%xprGtZ`{7V
z##~#wyms~7*7cbaH>-hyk8a(1qj}|H74Bm$1G+H%JG;)l*4ed?>5r>Xs5phH5ui<e
zejW(WJ(3kb5Ew0~JVSp?B%yQGGNR8XWXgr_cllB3awb5xvFF}RYnjp73;|VVsDsaE
zGiCU+B2FtO?vS^5Hp$!n;jvF0@_*&&quVaZZBB635dihwhu63JceDcl+Sawf6I1~w
z+Lv8-^bK3)7q|aYD)#-aPsKn5q*AM1Nj-ev-Ak>zFU%+}nnvNsFIJ_#0RZ^nuCFys
z#2)*~18pSxK-+UW_BEj=kOx5D0O6b0qhvq-_h29Tw=KV6?Hzm1k>qziW?s7VV-MHX
z9(rrzQlS4f%MI|RJ@+g(o0s47<4V%&pDmjHSe*1VZMmvS@oUmH>R%D8fPjF<rKO7V
zZg(MPJSZ8N1xgq|fH24n9R+aODqa8=3F5_5UE+Mf67vo06u--puS`l5U!jminx0tu
zH4LBtGy1||*6rbOaABSwf#ZxU_gLh|Z+kel?Z~(Gy!A8Fp`)hfPp@m6lxL2u6VBCi
z?|Wd{V`}4<Ne|pF9W%9o?9N%*gwZ3n^+>lo57zyu51%}B!$}bLn*W$Ma_gx#zR-4I
zaz@^L=gI$h`N2N~6>$2^4c~w2mQ!aw*LG|(&s+-tIJWErXM1!e4*;sSUq158zk*Mo
z{wP)^*+_5iFP}Z~lVA33tNkYV?a>}GX|?#(sdD5<MIH@Bvij-Y+tsNxtn8|i0(6^H
zi9!F0N(dMTcya+$$)AG&8h=622m_gTJWj=dsTmXwI7F;JhtLReLdo(KGDqpDWUj~U
z>G8nZ3z6I~gL)mW)DKV=$XWmZ0~<+1K~&`LDjq-+J@gp9;?50GJia#i%I`ft^_3&1
zKW*Cn?E^=@u)*|ANjg87X*R9j+0CstIsRgwylKr#cbK*}>_a!;+|FxFTm0|syZQqk
z{Js6-kA3(WB!JYKH)B%|Uvtgg_rc9qCjVyDl^@=FdMb6`I@5#yB{$WW_GPmBuHAh1
z;pcY92bY=lPAUZepwp#B@IpEKCJMFFezK}|`|DsJ+y(yPe3`SObo!@r(;utf=Gs+u
zR%Hk33l$jHftYx1B>zx08$f-_NE!s#T#sfHoS=~T2Ver<7LS)}c<>|xT=6-m@L2&Y
z%K)08X_-TfjzWfkJ0v)kYMSCYy!aUk4wr|?ACxb?6B}2fw(2;#9qhMvWLYd|vy5Rl
z=y&9IF*VXRKCT9O$ERYkci&S#fF>Y~0#3v(($Ejal-TQ;{268n06^zW%@GLE9KG41
zJvmR^R9joS!fgIiX`Y&319aMCb0`7juWML5ScMWOzFi};M%C|vMutEf+j#{7KDfhb
zk0>S&0pJ0!{eoheENV~|DeCr26u!spW_SfGf<R6IxmiIf3Powwgpv3?E|2bLAQqcQ
z6%7Qy6bMb03Y0T#gaD8<N*-4Pw77o^LxKPdTtv7SqXz&I7jbnVqkyWpy5^wn3<UsC
z%S}xdhTk(>T08Scd;Xxd_Ky#on!D_y>iQShzq6!Y^&AwSR#hr%g@8=X8vvjT0mIl3
zo{A#C_*G4yFm7FkUK$b%hNT6f06aclu*9mAsPNUb25NwUJbk`!=|@##B3LGV#^ciY
zhM2N5l`<L=$N`h*bG(yP$^f8T0#|SrB@h25Gz!3Vpm#52DFuvE3V`$Erhn<s0f3qT
zk-kb+HXW*`Tu}+A%0ItBO2_`%s9*=?N-OpmWJxIo{cMAM<(HWxdCG#x-s7evkrdYL
zW_4MEX$g(LU@#o76fi0wei96X^~A66v>6FKl&0LTN}s}@M9U~81dtQI&L?Eml$}>o
zsmchD^R!~TCXgZTj;qoB90g2F00q3Saz+gJVf-C!`WuY@124w6n<s0oX8-^I07*qo
IM6N<$f-E&DFaQ7m

literal 0
HcmV?d00001

diff --git a/p values and confidence in Python Statistics.ipynb b/p values and confidence in Python Statistics.ipynb
new file mode 100644
index 0000000..2a46c4a
--- /dev/null
+++ b/p values and confidence in Python Statistics.ipynb	
@@ -0,0 +1,269 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# The Engineering World - A Place for Learning And Exploring\n",
+    "\n",
+    "## p values & confidence Intervals"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Standard imports"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import math\n",
+    "import io"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "\n",
+    "import matplotlib\n",
+    "import matplotlib.pyplot as pp\n",
+    "\n",
+    "%matplotlib inline"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import scipy.stats\n",
+    "import scipy.optimize\n",
+    "import scipy.spatial"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "poll = pd.read_csv('poll.csv')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Brown    0.511\n",
+       "Green    0.489\n",
+       "Name: vote, dtype: float64"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "poll.vote.value_counts(normalize=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def sample(brown, n=1000):\n",
+    "    return pd.DataFrame({'vote':np.where(np.random.rand(n) < brown, 'Brown', 'Green')})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dist = pd.DataFrame({'Brown': [sample(0.50,1000).vote.value_counts(normalize=True)['Brown'] for i in range(10000)]})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<matplotlib.axes._subplots.AxesSubplot at 0x1ed98198978>"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "dist.Brown.hist(histtype='step', bins=20)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "25.045"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "100 - scipy.stats.percentileofscore(dist.Brown,0.511)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "largepoll = pd.read_csv('poll-larger.csv')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Green    0.5181\n",
+       "Brown    0.4819\n",
+       "Name: vote, dtype: float64"
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "largepoll.vote.value_counts(normalize=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dist = pd.DataFrame({'Green': [sample(0.50,10000).vote.value_counts(normalize=True)['Green'] for i  in range(1000)]})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<matplotlib.lines.Line2D at 0x1ed97f18470>"
+      ]
+     },
+     "execution_count": 21,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "dist.Green.hist(histtype='step',bins=20)\n",
+    "\n",
+    "pp.axvline(0.5181,c='C1')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.5"
+  },
+  "toc": {
+   "base_numbering": 1,
+   "nav_menu": {},
+   "number_sections": true,
+   "sideBar": true,
+   "skip_h1_title": false,
+   "title_cell": "Table of Contents",
+   "title_sidebar": "Contents",
+   "toc_cell": false,
+   "toc_position": {},
+   "toc_section_display": true,
+   "toc_window_display": false
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/poll-larger.xls b/poll-larger.xls
new file mode 100644
index 0000000..9bdbee7
--- /dev/null
+++ b/poll-larger.xls
@@ -0,0 +1,10001 @@
+vote
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
diff --git a/poll.xls b/poll.xls
new file mode 100644
index 0000000..f49dcc2
--- /dev/null
+++ b/poll.xls
@@ -0,0 +1,1001 @@
+vote
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Green
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Brown
+Green
+Brown
+Green
+Green
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Brown
+Green
+Brown
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Green
+Green
+Green
+Green
+Green
+Green
+Brown
+Brown
+Green
+Green
+Brown
+Green
+Brown
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Brown
+Green
+Brown
+Brown
+Brown
+Green
+Green
+Brown
+Brown
+Brown
+Brown
+Brown
diff --git a/pumps.xls b/pumps.xls
new file mode 100644
index 0000000..33d6911
--- /dev/null
+++ b/pumps.xls
@@ -0,0 +1,9 @@
+lat,lon,x,y
+51.513341,-0.136668,0.0,0.0
+51.513876,-0.139586,-0.20185816177777613,0.05946924171285328
+51.514906,-0.139671,-0.20773819733333182,0.17396142669138093
+51.512354,-0.13163,0.3485131662222233,-0.10971241414875793
+51.512139,-0.133594,0.21264975644444595,-0.1336112682952367
+51.511542,-0.135919,0.05181348977777778,-0.19997227259821615
+51.510019,-0.133962,0.18719266133333434,-0.36926508592069096
+51.511295,-0.138199,-0.10590981688888729,-0.22742816550101644
diff --git a/whickham.xls b/whickham.xls
index b6b9ac6..37bd95b 100644
--- a/whickham.xls
+++ b/whickham.xls
@@ -1,1315 +1,1315 @@
-outcome,smoker,age
-Alive,Yes,23
-Alive,Yes,18
-Dead,Yes,71
-Alive,No,67
-Alive,No,64
-Alive,Yes,38
-Alive,Yes,45
-Dead,No,76
-Alive,No,28
-Alive,No,27
-Alive,No,28
-Alive,Yes,34
-Alive,No,20
-Dead,Yes,72
-Alive,Yes,48
-Alive,Yes,45
-Dead,No,66
-Alive,Yes,30
-Alive,No,67
-Alive,Yes,33
-Dead,No,68
-Dead,No,72
-Alive,Yes,34
-Dead,No,61
-Dead,No,66
-Alive,No,43
-Dead,No,71
-Alive,Yes,47
-Dead,No,67
-Alive,No,22
-Alive,No,39
-Dead,Yes,71
-Alive,Yes,38
-Dead,No,80
-Dead,Yes,59
-Alive,Yes,47
-Dead,Yes,56
-Dead,No,62
-Alive,Yes,30
-Alive,Yes,51
-Alive,No,34
-Alive,No,39
-Dead,No,56
-Alive,No,32
-Dead,No,56
-Alive,Yes,60
-Dead,Yes,60
-Alive,No,30
-Alive,Yes,33
-Alive,No,37
-Dead,No,66
-Dead,Yes,71
-Alive,Yes,23
-Alive,No,38
-Alive,Yes,36
-Dead,Yes,38
-Alive,Yes,50
-Alive,No,45
-Alive,Yes,36
-Dead,No,55
-Dead,Yes,73
-Dead,Yes,52
-Alive,No,52
-Alive,Yes,37
-Alive,No,61
-Alive,No,39
-Alive,No,72
-Alive,Yes,25
-Alive,Yes,50
-Dead,No,68
-Alive,Yes,53
-Alive,No,31
-Dead,No,73
-Alive,No,54
-Alive,Yes,56
-Alive,Yes,51
-Dead,No,76
-Alive,No,55
-Dead,Yes,56
-Alive,No,56
-Dead,Yes,69
-Dead,No,79
-Dead,Yes,75
-Dead,No,67
-Alive,No,20
-Alive,No,20
-Dead,No,68
-Dead,Yes,68
-Alive,No,21
-Alive,Yes,29
-Alive,Yes,33
-Alive,Yes,30
-Alive,Yes,24
-Dead,Yes,61
-Alive,Yes,54
-Alive,No,26
-Dead,No,68
-Alive,Yes,49
-Dead,No,72
-Alive,No,21
-Alive,No,28
-Alive,No,47
-Dead,No,68
-Dead,No,71
-Alive,Yes,59
-Alive,No,64
-Alive,Yes,47
-Dead,No,84
-Alive,No,28
-Alive,No,67
-Alive,No,30
-Dead,Yes,33
-Dead,No,68
-Dead,No,55
-Dead,No,79
-Alive,No,40
-Alive,No,43
-Alive,Yes,37
-Dead,No,73
-Dead,Yes,45
-Alive,No,49
-Alive,Yes,44
-Alive,Yes,74
-Alive,Yes,20
-Alive,Yes,31
-Alive,No,20
-Alive,No,61
-Dead,Yes,66
-Alive,No,53
-Alive,Yes,36
-Dead,No,71
-Dead,Yes,64
-Alive,No,52
-Alive,No,37
-Alive,Yes,34
-Alive,No,61
-Alive,Yes,46
-Alive,Yes,26
-Alive,No,33
-Alive,No,32
-Alive,Yes,47
-Alive,No,27
-Alive,No,25
-Dead,No,69
-Dead,Yes,43
-Dead,Yes,71
-Alive,No,33
-Dead,No,73
-Dead,No,68
-Alive,No,31
-Alive,No,35
-Dead,No,73
-Dead,Yes,59
-Alive,No,31
-Dead,No,77
-Alive,Yes,33
-Alive,Yes,48
-Alive,Yes,34
-Alive,No,43
-Dead,No,68
-Alive,Yes,29
-Dead,No,71
-Dead,Yes,21
-Alive,No,18
-Alive,No,24
-Alive,Yes,30
-Alive,No,24
-Dead,No,74
-Alive,Yes,57
-Alive,No,23
-Alive,No,42
-Alive,No,34
-Alive,Yes,46
-Alive,No,40
-Alive,Yes,64
-Dead,Yes,20
-Alive,Yes,30
-Dead,Yes,81
-Dead,Yes,45
-Alive,No,26
-Dead,No,77
-Alive,Yes,53
-Alive,Yes,46
-Dead,No,69
-Alive,Yes,44
-Dead,Yes,50
-Alive,Yes,50
-Dead,No,62
-Dead,Yes,60
-Alive,No,19
-Alive,Yes,21
-Alive,Yes,50
-Alive,Yes,33
-Dead,No,59
-Dead,No,81
-Alive,Yes,31
-Dead,No,77
-Alive,Yes,23
-Alive,No,55
-Alive,No,51
-Alive,No,26
-Alive,No,20
-Alive,No,57
-Dead,No,67
-Alive,No,29
-Alive,Yes,28
-Alive,Yes,26
-Dead,No,76
-Alive,No,32
-Dead,Yes,40
-Alive,No,40
-Alive,No,52
-Dead,No,35
-Alive,Yes,27
-Alive,Yes,33
-Alive,Yes,20
-Alive,Yes,31
-Alive,No,28
-Alive,No,22
-Dead,Yes,73
-Alive,No,23
-Alive,Yes,24
-Alive,No,48
-Alive,No,60
-Alive,Yes,50
-Alive,Yes,37
-Alive,Yes,29
-Alive,No,35
-Dead,No,67
-Alive,No,33
-Alive,Yes,36
-Dead,No,64
-Alive,Yes,59
-Alive,No,23
-Alive,Yes,63
-Alive,No,26
-Dead,No,50
-Dead,No,36
-Dead,Yes,51
-Alive,No,25
-Alive,No,48
-Alive,No,24
-Dead,Yes,42
-Alive,No,64
-Alive,No,36
-Alive,Yes,47
-Alive,No,64
-Alive,No,22
-Alive,No,31
-Alive,No,55
-Dead,Yes,78
-Alive,No,27
-Alive,No,63
-Dead,Yes,83
-Alive,No,55
-Alive,Yes,57
-Alive,Yes,31
-Dead,No,64
-Alive,Yes,25
-Alive,No,38
-Dead,No,68
-Alive,No,59
-Alive,Yes,63
-Alive,Yes,18
-Alive,Yes,44
-Alive,No,38
-Dead,Yes,72
-Alive,Yes,28
-Alive,Yes,37
-Dead,No,51
-Dead,Yes,53
-Alive,Yes,31
-Dead,No,69
-Alive,Yes,51
-Alive,Yes,36
-Alive,No,27
-Alive,Yes,24
-Alive,Yes,64
-Alive,No,64
-Alive,Yes,64
-Dead,No,64
-Alive,Yes,46
-Alive,Yes,67
-Alive,Yes,40
-Alive,Yes,49
-Alive,Yes,25
-Alive,Yes,36
-Dead,No,82
-Alive,Yes,56
-Dead,Yes,56
-Alive,No,37
-Dead,Yes,59
-Alive,Yes,42
-Alive,No,44
-Alive,Yes,18
-Alive,Yes,44
-Alive,No,32
-Alive,Yes,38
-Alive,Yes,32
-Alive,Yes,29
-Alive,No,51
-Alive,Yes,34
-Alive,Yes,32
-Alive,No,23
-Alive,Yes,48
-Alive,Yes,24
-Alive,Yes,21
-Alive,No,54
-Dead,No,68
-Alive,Yes,26
-Alive,No,51
-Alive,Yes,45
-Alive,No,31
-Alive,Yes,43
-Alive,Yes,30
-Dead,No,72
-Alive,No,19
-Alive,No,31
-Dead,No,70
-Alive,No,58
-Alive,No,27
-Alive,No,56
-Dead,Yes,46
-Dead,No,75
-Alive,No,35
-Alive,No,30
-Dead,No,47
-Alive,No,63
-Alive,No,66
-Alive,Yes,41
-Dead,Yes,82
-Alive,Yes,39
-Alive,Yes,33
-Dead,Yes,60
-Dead,No,73
-Alive,Yes,26
-Alive,No,21
-Alive,Yes,39
-Dead,Yes,51
-Alive,No,28
-Alive,Yes,54
-Alive,No,51
-Dead,No,69
-Alive,Yes,63
-Alive,Yes,47
-Alive,No,38
-Dead,Yes,61
-Alive,Yes,31
-Alive,Yes,62
-Alive,No,62
-Alive,Yes,21
-Alive,Yes,32
-Alive,No,38
-Dead,No,67
-Alive,No,59
-Dead,No,71
-Alive,No,35
-Alive,Yes,28
-Alive,Yes,31
-Dead,Yes,58
-Alive,Yes,53
-Alive,No,48
-Alive,No,27
-Alive,No,30
-Dead,Yes,50
-Dead,Yes,43
-Alive,No,41
-Alive,No,37
-Alive,No,31
-Alive,No,30
-Alive,Yes,52
-Alive,Yes,37
-Alive,No,45
-Alive,Yes,36
-Alive,Yes,34
-Alive,Yes,39
-Alive,No,30
-Dead,Yes,57
-Alive,No,40
-Dead,Yes,62
-Alive,Yes,62
-Alive,Yes,60
-Alive,No,56
-Alive,No,45
-Alive,No,22
-Alive,No,27
-Alive,Yes,18
-Alive,Yes,26
-Dead,No,77
-Alive,No,33
-Alive,No,35
-Alive,No,33
-Dead,No,55
-Alive,No,45
-Alive,No,32
-Alive,No,34
-Alive,No,67
-Alive,No,35
-Dead,Yes,72
-Dead,No,79
-Alive,Yes,35
-Alive,No,38
-Alive,Yes,25
-Alive,Yes,37
-Alive,No,56
-Dead,No,66
-Dead,No,49
-Alive,Yes,33
-Dead,No,59
-Alive,No,44
-Alive,No,39
-Dead,No,58
-Alive,No,64
-Alive,No,18
-Alive,Yes,45
-Alive,No,33
-Alive,No,32
-Dead,No,80
-Alive,Yes,44
-Alive,Yes,25
-Alive,No,68
-Alive,Yes,34
-Alive,Yes,29
-Dead,Yes,72
-Alive,Yes,32
-Alive,Yes,56
-Alive,Yes,43
-Dead,Yes,60
-Alive,Yes,53
-Alive,Yes,41
-Alive,Yes,63
-Dead,Yes,57
-Alive,No,24
-Alive,Yes,39
-Alive,Yes,39
-Alive,No,31
-Alive,Yes,45
-Alive,No,66
-Alive,No,18
-Dead,No,72
-Alive,No,49
-Alive,No,37
-Dead,No,68
-Dead,Yes,69
-Alive,No,27
-Alive,Yes,20
-Alive,No,52
-Alive,Yes,62
-Alive,Yes,64
-Alive,Yes,42
-Alive,No,66
-Dead,No,78
-Alive,No,33
-Alive,No,31
-Alive,Yes,49
-Alive,No,58
-Alive,Yes,23
-Alive,Yes,41
-Alive,Yes,34
-Alive,Yes,30
-Alive,Yes,24
-Alive,Yes,31
-Alive,Yes,64
-Dead,Yes,81
-Dead,No,79
-Alive,No,54
-Alive,Yes,47
-Alive,Yes,25
-Dead,Yes,68
-Alive,Yes,23
-Alive,No,74
-Alive,Yes,25
-Alive,Yes,54
-Dead,No,78
-Dead,No,65
-Alive,Yes,39
-Dead,No,73
-Alive,No,27
-Alive,Yes,62
-Alive,Yes,26
-Dead,Yes,57
-Alive,No,41
-Alive,No,41
-Dead,Yes,66
-Dead,Yes,48
-Dead,Yes,68
-Alive,Yes,43
-Alive,No,28
-Alive,Yes,58
-Dead,Yes,56
-Dead,Yes,40
-Dead,No,69
-Alive,Yes,47
-Alive,Yes,52
-Alive,Yes,52
-Dead,No,80
-Alive,Yes,64
-Alive,No,39
-Alive,Yes,54
-Alive,No,55
-Alive,No,51
-Alive,Yes,28
-Dead,No,77
-Alive,Yes,27
-Dead,No,82
-Dead,No,65
-Dead,No,80
-Alive,No,46
-Alive,Yes,38
-Alive,Yes,28
-Dead,No,49
-Alive,Yes,44
-Alive,No,30
-Alive,No,63
-Alive,No,63
-Dead,Yes,68
-Alive,Yes,46
-Alive,No,52
-Alive,No,52
-Alive,No,55
-Alive,No,74
-Alive,Yes,44
-Alive,No,51
-Alive,Yes,35
-Alive,Yes,36
-Alive,Yes,33
-Alive,No,26
-Alive,No,21
-Alive,No,18
-Alive,No,30
-Dead,No,81
-Alive,Yes,63
-Dead,Yes,42
-Alive,No,35
-Alive,Yes,38
-Alive,No,28
-Alive,Yes,62
-Alive,No,39
-Alive,No,39
-Alive,No,61
-Alive,Yes,19
-Alive,Yes,46
-Dead,Yes,70
-Alive,Yes,38
-Alive,No,33
-Alive,Yes,53
-Alive,No,19
-Dead,No,82
-Alive,Yes,49
-Alive,Yes,47
-Dead,No,78
-Alive,Yes,22
-Alive,Yes,31
-Alive,No,31
-Alive,No,57
-Alive,No,65
-Dead,No,68
-Alive,Yes,22
-Alive,Yes,27
-Alive,Yes,50
-Dead,Yes,53
-Alive,No,34
-Alive,Yes,37
-Alive,No,35
-Alive,No,38
-Dead,No,43
-Alive,Yes,34
-Alive,No,64
-Alive,No,43
-Dead,Yes,57
-Alive,Yes,55
-Alive,Yes,34
-Alive,No,29
-Alive,No,18
-Dead,No,38
-Alive,Yes,40
-Alive,No,44
-Dead,No,71
-Dead,Yes,61
-Alive,Yes,26
-Dead,No,35
-Alive,No,26
-Alive,No,39
-Alive,Yes,43
-Alive,Yes,44
-Alive,No,38
-Alive,No,37
-Dead,Yes,52
-Alive,No,56
-Dead,No,70
-Alive,Yes,39
-Dead,Yes,57
-Alive,Yes,46
-Alive,Yes,28
-Alive,No,21
-Dead,Yes,66
-Alive,Yes,38
-Alive,Yes,32
-Alive,Yes,23
-Alive,No,61
-Alive,Yes,32
-Alive,No,27
-Dead,Yes,73
-Alive,Yes,36
-Alive,No,33
-Alive,No,28
-Alive,No,43
-Alive,Yes,56
-Alive,No,27
-Alive,No,36
-Alive,No,20
-Dead,No,69
-Alive,No,44
-Alive,Yes,26
-Dead,Yes,31
-Dead,No,72
-Dead,No,84
-Alive,Yes,48
-Alive,No,18
-Dead,Yes,82
-Alive,Yes,51
-Alive,Yes,33
-Alive,No,56
-Alive,No,74
-Alive,No,24
-Dead,No,74
-Alive,No,28
-Alive,Yes,58
-Alive,Yes,49
-Dead,Yes,64
-Alive,No,34
-Dead,No,84
-Dead,Yes,47
-Alive,Yes,58
-Dead,Yes,63
-Dead,No,57
-Alive,Yes,18
-Alive,No,23
-Alive,No,51
-Alive,No,55
-Alive,No,49
-Dead,No,60
-Alive,No,39
-Alive,No,48
-Alive,No,28
-Dead,No,74
-Alive,Yes,61
-Alive,Yes,33
-Dead,No,64
-Dead,No,77
-Alive,Yes,51
-Alive,Yes,23
-Dead,No,43
-Alive,No,47
-Alive,No,27
-Alive,No,48
-Alive,Yes,29
-Alive,No,45
-Alive,Yes,31
-Dead,Yes,60
-Alive,No,53
-Alive,No,26
-Dead,Yes,61
-Alive,No,38
-Alive,No,22
-Alive,Yes,41
-Alive,Yes,27
-Alive,No,63
-Dead,Yes,60
-Dead,No,64
-Alive,No,58
-Alive,No,42
-Dead,No,82
-Dead,No,62
-Alive,No,64
-Alive,No,34
-Alive,No,58
-Alive,Yes,63
-Dead,No,63
-Dead,No,79
-Alive,No,44
-Alive,No,41
-Alive,No,34
-Alive,Yes,38
-Alive,Yes,54
-Alive,No,53
-Dead,No,80
-Dead,Yes,46
-Alive,Yes,61
-Dead,No,72
-Alive,Yes,61
-Alive,Yes,28
-Alive,Yes,20
-Dead,Yes,46
-Dead,No,56
-Dead,No,84
-Dead,Yes,64
-Dead,No,42
-Alive,No,30
-Alive,No,48
-Alive,Yes,25
-Dead,No,76
-Dead,Yes,61
-Alive,No,41
-Alive,No,29
-Dead,No,80
-Alive,Yes,56
-Alive,Yes,58
-Dead,No,73
-Alive,No,18
-Alive,No,42
-Dead,No,67
-Alive,No,30
-Dead,No,78
-Dead,Yes,36
-Dead,No,78
-Alive,No,44
-Alive,No,35
-Alive,Yes,53
-Dead,No,52
-Alive,Yes,63
-Dead,No,79
-Alive,No,51
-Alive,No,59
-Alive,No,62
-Alive,No,35
-Alive,No,32
-Alive,Yes,48
-Dead,Yes,53
-Dead,Yes,49
-Alive,Yes,23
-Alive,Yes,50
-Alive,No,26
-Dead,Yes,44
-Dead,Yes,71
-Dead,No,78
-Alive,No,40
-Alive,No,71
-Alive,Yes,62
-Alive,No,30
-Alive,No,32
-Dead,No,71
-Alive,No,70
-Alive,No,27
-Dead,Yes,60
-Dead,No,65
-Dead,No,72
-Alive,No,22
-Alive,Yes,26
-Alive,No,26
-Alive,Yes,30
-Alive,Yes,21
-Alive,Yes,28
-Alive,No,60
-Alive,No,53
-Alive,Yes,59
-Dead,Yes,63
-Alive,Yes,36
-Alive,No,34
-Alive,Yes,61
-Dead,No,65
-Dead,Yes,59
-Dead,No,70
-Dead,Yes,48
-Alive,Yes,50
-Dead,No,83
-Alive,No,51
-Alive,Yes,24
-Alive,No,46
-Alive,No,19
-Alive,Yes,36
-Alive,No,33
-Dead,No,56
-Alive,No,57
-Alive,No,44
-Alive,No,53
-Alive,Yes,30
-Alive,No,42
-Alive,Yes,42
-Alive,Yes,58
-Alive,No,32
-Alive,No,30
-Dead,No,73
-Alive,No,34
-Dead,Yes,76
-Alive,Yes,51
-Dead,No,71
-Dead,No,60
-Alive,No,36
-Alive,Yes,18
-Alive,No,34
-Dead,No,70
-Alive,Yes,50
-Alive,Yes,41
-Alive,No,55
-Alive,No,36
-Dead,Yes,66
-Alive,No,58
-Alive,Yes,31
-Alive,No,36
-Dead,No,68
-Alive,No,24
-Alive,No,25
-Alive,Yes,42
-Alive,No,31
-Alive,Yes,18
-Alive,Yes,27
-Alive,No,20
-Alive,No,40
-Alive,Yes,57
-Alive,No,73
-Alive,No,44
-Alive,No,63
-Alive,No,19
-Dead,Yes,49
-Alive,No,59
-Alive,Yes,23
-Alive,Yes,53
-Alive,Yes,51
-Alive,Yes,22
-Alive,No,24
-Alive,Yes,51
-Alive,Yes,26
-Dead,No,68
-Dead,No,56
-Alive,No,47
-Alive,Yes,36
-Alive,Yes,46
-Alive,No,26
-Alive,Yes,74
-Alive,No,26
-Alive,Yes,52
-Alive,No,57
-Alive,Yes,34
-Alive,No,60
-Alive,Yes,32
-Alive,Yes,41
-Dead,No,82
-Alive,Yes,31
-Alive,No,68
-Alive,No,25
-Dead,No,84
-Alive,No,37
-Alive,No,37
-Dead,No,83
-Alive,No,62
-Alive,No,25
-Alive,Yes,55
-Alive,No,23
-Alive,Yes,52
-Alive,Yes,33
-Alive,Yes,53
-Alive,No,55
-Alive,Yes,45
-Alive,Yes,19
-Alive,Yes,53
-Alive,No,18
-Alive,Yes,32
-Alive,No,32
-Dead,No,67
-Dead,Yes,60
-Alive,Yes,35
-Alive,Yes,60
-Alive,Yes,56
-Alive,No,28
-Dead,No,61
-Alive,Yes,46
-Alive,No,22
-Dead,No,55
-Dead,No,66
-Dead,Yes,71
-Dead,No,68
-Alive,No,50
-Alive,Yes,32
-Alive,No,24
-Alive,No,38
-Alive,No,64
-Dead,Yes,51
-Alive,Yes,29
-Dead,No,77
-Alive,No,25
-Alive,No,50
-Alive,No,61
-Alive,Yes,23
-Dead,No,67
-Dead,No,73
-Alive,No,23
-Alive,Yes,59
-Dead,No,61
-Alive,Yes,43
-Alive,No,25
-Alive,No,39
-Alive,No,45
-Alive,No,25
-Alive,Yes,52
-Dead,No,46
-Alive,No,25
-Alive,No,30
-Alive,Yes,62
-Alive,No,58
-Alive,Yes,25
-Alive,No,31
-Dead,No,46
-Dead,Yes,27
-Dead,No,68
-Alive,Yes,35
-Alive,No,25
-Alive,Yes,42
-Dead,No,72
-Alive,Yes,55
-Alive,No,29
-Alive,Yes,29
-Alive,Yes,36
-Dead,No,51
-Dead,No,80
-Dead,No,74
-Alive,No,20
-Dead,No,45
-Alive,No,46
-Alive,Yes,43
-Alive,No,66
-Dead,Yes,45
-Alive,Yes,71
-Alive,No,43
-Alive,Yes,27
-Alive,No,22
-Alive,Yes,41
-Alive,No,60
-Alive,Yes,46
-Alive,No,29
-Dead,Yes,55
-Alive,Yes,36
-Dead,No,84
-Alive,No,67
-Dead,No,45
-Alive,No,34
-Dead,No,65
-Alive,Yes,32
-Dead,No,71
-Alive,No,26
-Alive,Yes,26
-Dead,No,72
-Alive,No,45
-Alive,No,27
-Alive,Yes,36
-Alive,No,34
-Dead,No,78
-Alive,Yes,20
-Alive,Yes,46
-Alive,No,27
-Alive,No,74
-Alive,Yes,46
-Alive,Yes,31
-Alive,Yes,46
-Alive,No,58
-Dead,No,72
-Dead,Yes,56
-Alive,No,45
-Alive,No,60
-Dead,No,65
-Dead,No,71
-Dead,No,76
-Alive,No,55
-Alive,No,35
-Alive,Yes,44
-Dead,Yes,47
-Dead,Yes,63
-Alive,Yes,32
-Alive,No,43
-Alive,Yes,35
-Dead,Yes,63
-Alive,No,29
-Alive,No,51
-Alive,Yes,42
-Dead,Yes,45
-Alive,Yes,19
-Dead,No,69
-Alive,Yes,39
-Dead,Yes,61
-Alive,Yes,19
-Alive,No,53
-Alive,Yes,61
-Alive,No,40
-Alive,No,37
-Alive,No,37
-Dead,No,65
-Alive,No,74
-Alive,Yes,50
-Alive,Yes,25
-Alive,No,32
-Alive,No,28
-Alive,No,71
-Dead,No,27
-Alive,No,23
-Alive,Yes,64
-Alive,No,28
-Dead,No,56
-Alive,No,25
-Dead,Yes,61
-Alive,No,63
-Alive,No,24
-Alive,No,64
-Dead,No,58
-Alive,No,34
-Alive,No,31
-Alive,Yes,33
-Alive,Yes,48
-Alive,Yes,55
-Alive,No,72
-Alive,No,43
-Alive,Yes,20
-Alive,Yes,62
-Alive,No,18
-Alive,Yes,21
-Alive,No,38
-Alive,Yes,45
-Dead,Yes,81
-Alive,Yes,66
-Alive,No,33
-Alive,Yes,32
-Alive,No,29
-Alive,Yes,53
-Alive,No,21
-Alive,No,61
-Alive,No,24
-Dead,No,54
-Alive,Yes,46
-Alive,No,58
-Dead,No,65
-Dead,No,82
-Alive,No,53
-Dead,No,33
-Alive,Yes,49
-Alive,No,42
-Alive,Yes,43
-Alive,Yes,20
-Dead,No,56
-Dead,No,82
-Dead,No,72
-Alive,No,20
-Dead,No,82
-Alive,No,62
-Alive,Yes,54
-Alive,No,54
-Dead,Yes,82
-Alive,Yes,47
-Alive,Yes,18
-Dead,No,72
-Alive,Yes,35
-Dead,No,69
-Alive,No,52
-Dead,No,59
-Dead,Yes,52
-Alive,Yes,29
-Alive,No,21
-Alive,No,28
-Alive,Yes,25
-Alive,Yes,25
-Alive,Yes,58
-Alive,Yes,43
-Alive,No,62
-Dead,No,67
-Alive,Yes,48
-Alive,Yes,54
-Alive,Yes,42
-Alive,No,66
-Alive,Yes,23
-Alive,Yes,67
-Alive,No,47
-Alive,No,28
-Alive,No,38
-Alive,No,64
-Dead,No,57
-Alive,No,56
-Alive,No,34
-Alive,Yes,50
-Alive,No,58
-Alive,No,32
-Dead,No,77
-Alive,Yes,23
-Alive,Yes,36
-Dead,No,18
-Alive,No,47
-Dead,No,70
-Dead,Yes,60
-Dead,No,71
-Dead,Yes,56
-Alive,Yes,32
-Alive,No,28
-Alive,No,51
-Alive,No,37
-Alive,No,30
-Dead,No,77
-Dead,No,70
-Alive,No,41
-Alive,No,32
-Alive,Yes,48
-Alive,No,53
-Dead,Yes,65
-Dead,No,66
-Dead,Yes,59
-Dead,No,60
-Dead,Yes,58
-Alive,No,64
-Alive,Yes,61
-Dead,No,62
-Alive,No,58
-Alive,No,37
-Dead,Yes,53
-Alive,No,65
-Alive,No,27
-Dead,No,72
-Dead,Yes,60
-Alive,Yes,45
-Alive,Yes,63
-Alive,No,32
-Alive,No,18
-Alive,Yes,49
-Alive,No,34
-Alive,No,23
-Alive,No,61
-Alive,No,44
-Alive,No,66
-Alive,No,28
-Alive,Yes,44
-Alive,Yes,29
-Alive,Yes,38
-Alive,Yes,52
-Alive,Yes,54
-Alive,Yes,63
-Dead,Yes,45
-Dead,No,74
-Alive,No,24
-Alive,No,40
-Alive,No,28
-Alive,Yes,30
-Alive,Yes,43
-Dead,Yes,63
-Alive,Yes,33
-Alive,Yes,41
-Alive,No,60
-Alive,Yes,31
-Alive,Yes,47
-Dead,No,81
-Dead,No,78
-Alive,No,56
-Dead,No,73
-Alive,No,56
-Alive,Yes,28
-Alive,Yes,22
-Alive,No,34
-Alive,No,48
-Alive,No,27
-Alive,Yes,47
-Alive,No,31
-Alive,No,47
-Dead,No,60
-Dead,No,59
-Dead,No,80
-Alive,Yes,41
-Dead,Yes,46
-Alive,Yes,50
-Alive,No,48
-Alive,No,37
-Alive,Yes,50
-Alive,Yes,25
-Alive,No,25
-Alive,No,41
-Alive,No,24
-Alive,Yes,57
-Dead,No,71
-Alive,Yes,26
-Dead,No,32
-Alive,No,25
-Dead,No,84
-Alive,Yes,19
-Alive,No,26
-Alive,Yes,58
-Dead,Yes,67
-Alive,No,24
-Dead,Yes,74
-Alive,Yes,58
-Alive,No,57
-Alive,Yes,52
-Alive,Yes,42
-Alive,No,42
-Dead,No,69
-Dead,Yes,39
-Dead,Yes,84
-Alive,Yes,57
-Alive,No,42
-Alive,No,35
-Alive,No,23
-Alive,No,65
-Alive,Yes,28
-Alive,No,39
-Alive,Yes,36
-Alive,No,40
-Alive,No,39
-Alive,No,19
-Alive,No,61
-Alive,Yes,37
-Alive,Yes,52
-Alive,Yes,62
-Alive,No,30
-Alive,Yes,23
-Dead,Yes,72
-Alive,Yes,46
-Alive,No,33
-Alive,No,32
-Alive,No,27
-Dead,Yes,72
-Dead,Yes,53
-Dead,Yes,58
-Alive,Yes,32
-Alive,No,25
-Dead,No,71
-Alive,Yes,37
-Alive,Yes,41
-Dead,No,75
-Alive,No,29
-Dead,Yes,62
-Alive,Yes,30
-Alive,No,20
-Alive,Yes,26
-Dead,No,60
-Dead,No,65
-Dead,Yes,63
-Alive,No,19
-Dead,Yes,55
-Alive,Yes,45
-Alive,No,28
-Alive,Yes,21
-Alive,No,35
-Alive,No,24
-Dead,No,74
-Dead,No,63
-Alive,No,44
-Alive,Yes,26
-Dead,No,84
-Alive,Yes,27
-Alive,No,28
-Dead,Yes,60
-Alive,No,44
-Dead,No,82
-Dead,No,29
-Alive,Yes,52
-Alive,Yes,42
-Alive,Yes,18
-Dead,No,61
-Dead,No,60
-Alive,Yes,19
-Dead,No,84
-Dead,No,72
-Alive,No,59
-Dead,No,78
-Alive,No,41
-Alive,No,21
-Alive,No,31
-Dead,No,83
-Alive,No,62
-Dead,No,76
-Dead,Yes,63
-Alive,No,44
-Dead,No,65
-Alive,No,33
-Alive,Yes,40
-Alive,No,50
-Dead,No,74
-Alive,No,19
-Alive,No,50
-Dead,Yes,62
-Alive,Yes,25
-Dead,Yes,66
-Alive,No,67
-Alive,Yes,18
-Alive,Yes,28
-Alive,Yes,49
-Alive,Yes,39
-Alive,Yes,33
-Alive,No,44
-Alive,No,48
-Alive,Yes,37
-Dead,Yes,71
-Dead,No,66
-Alive,Yes,34
-Dead,Yes,77
-Alive,No,48
-Alive,Yes,60
-Alive,No,41
-Alive,No,55
-Alive,Yes,46
-Alive,No,55
-Alive,No,20
-Dead,Yes,80
-Alive,Yes,57
-Alive,No,52
-Alive,Yes,48
-Alive,No,30
-Alive,Yes,57
-Alive,Yes,37
-Alive,No,27
-Alive,No,37
-Alive,No,36
-Alive,No,23
-Dead,No,55
-Alive,No,40
-Alive,No,33
-Alive,No,23
-Alive,Yes,35
-Alive,No,33
-Alive,Yes,21
-Alive,No,46
-Alive,Yes,41
+outcome,smoker,age
+Alive,Yes,23
+Alive,Yes,18
+Dead,Yes,71
+Alive,No,67
+Alive,No,64
+Alive,Yes,38
+Alive,Yes,45
+Dead,No,76
+Alive,No,28
+Alive,No,27
+Alive,No,28
+Alive,Yes,34
+Alive,No,20
+Dead,Yes,72
+Alive,Yes,48
+Alive,Yes,45
+Dead,No,66
+Alive,Yes,30
+Alive,No,67
+Alive,Yes,33
+Dead,No,68
+Dead,No,72
+Alive,Yes,34
+Dead,No,61
+Dead,No,66
+Alive,No,43
+Dead,No,71
+Alive,Yes,47
+Dead,No,67
+Alive,No,22
+Alive,No,39
+Dead,Yes,71
+Alive,Yes,38
+Dead,No,80
+Dead,Yes,59
+Alive,Yes,47
+Dead,Yes,56
+Dead,No,62
+Alive,Yes,30
+Alive,Yes,51
+Alive,No,34
+Alive,No,39
+Dead,No,56
+Alive,No,32
+Dead,No,56
+Alive,Yes,60
+Dead,Yes,60
+Alive,No,30
+Alive,Yes,33
+Alive,No,37
+Dead,No,66
+Dead,Yes,71
+Alive,Yes,23
+Alive,No,38
+Alive,Yes,36
+Dead,Yes,38
+Alive,Yes,50
+Alive,No,45
+Alive,Yes,36
+Dead,No,55
+Dead,Yes,73
+Dead,Yes,52
+Alive,No,52
+Alive,Yes,37
+Alive,No,61
+Alive,No,39
+Alive,No,72
+Alive,Yes,25
+Alive,Yes,50
+Dead,No,68
+Alive,Yes,53
+Alive,No,31
+Dead,No,73
+Alive,No,54
+Alive,Yes,56
+Alive,Yes,51
+Dead,No,76
+Alive,No,55
+Dead,Yes,56
+Alive,No,56
+Dead,Yes,69
+Dead,No,79
+Dead,Yes,75
+Dead,No,67
+Alive,No,20
+Alive,No,20
+Dead,No,68
+Dead,Yes,68
+Alive,No,21
+Alive,Yes,29
+Alive,Yes,33
+Alive,Yes,30
+Alive,Yes,24
+Dead,Yes,61
+Alive,Yes,54
+Alive,No,26
+Dead,No,68
+Alive,Yes,49
+Dead,No,72
+Alive,No,21
+Alive,No,28
+Alive,No,47
+Dead,No,68
+Dead,No,71
+Alive,Yes,59
+Alive,No,64
+Alive,Yes,47
+Dead,No,84
+Alive,No,28
+Alive,No,67
+Alive,No,30
+Dead,Yes,33
+Dead,No,68
+Dead,No,55
+Dead,No,79
+Alive,No,40
+Alive,No,43
+Alive,Yes,37
+Dead,No,73
+Dead,Yes,45
+Alive,No,49
+Alive,Yes,44
+Alive,Yes,74
+Alive,Yes,20
+Alive,Yes,31
+Alive,No,20
+Alive,No,61
+Dead,Yes,66
+Alive,No,53
+Alive,Yes,36
+Dead,No,71
+Dead,Yes,64
+Alive,No,52
+Alive,No,37
+Alive,Yes,34
+Alive,No,61
+Alive,Yes,46
+Alive,Yes,26
+Alive,No,33
+Alive,No,32
+Alive,Yes,47
+Alive,No,27
+Alive,No,25
+Dead,No,69
+Dead,Yes,43
+Dead,Yes,71
+Alive,No,33
+Dead,No,73
+Dead,No,68
+Alive,No,31
+Alive,No,35
+Dead,No,73
+Dead,Yes,59
+Alive,No,31
+Dead,No,77
+Alive,Yes,33
+Alive,Yes,48
+Alive,Yes,34
+Alive,No,43
+Dead,No,68
+Alive,Yes,29
+Dead,No,71
+Dead,Yes,21
+Alive,No,18
+Alive,No,24
+Alive,Yes,30
+Alive,No,24
+Dead,No,74
+Alive,Yes,57
+Alive,No,23
+Alive,No,42
+Alive,No,34
+Alive,Yes,46
+Alive,No,40
+Alive,Yes,64
+Dead,Yes,20
+Alive,Yes,30
+Dead,Yes,81
+Dead,Yes,45
+Alive,No,26
+Dead,No,77
+Alive,Yes,53
+Alive,Yes,46
+Dead,No,69
+Alive,Yes,44
+Dead,Yes,50
+Alive,Yes,50
+Dead,No,62
+Dead,Yes,60
+Alive,No,19
+Alive,Yes,21
+Alive,Yes,50
+Alive,Yes,33
+Dead,No,59
+Dead,No,81
+Alive,Yes,31
+Dead,No,77
+Alive,Yes,23
+Alive,No,55
+Alive,No,51
+Alive,No,26
+Alive,No,20
+Alive,No,57
+Dead,No,67
+Alive,No,29
+Alive,Yes,28
+Alive,Yes,26
+Dead,No,76
+Alive,No,32
+Dead,Yes,40
+Alive,No,40
+Alive,No,52
+Dead,No,35
+Alive,Yes,27
+Alive,Yes,33
+Alive,Yes,20
+Alive,Yes,31
+Alive,No,28
+Alive,No,22
+Dead,Yes,73
+Alive,No,23
+Alive,Yes,24
+Alive,No,48
+Alive,No,60
+Alive,Yes,50
+Alive,Yes,37
+Alive,Yes,29
+Alive,No,35
+Dead,No,67
+Alive,No,33
+Alive,Yes,36
+Dead,No,64
+Alive,Yes,59
+Alive,No,23
+Alive,Yes,63
+Alive,No,26
+Dead,No,50
+Dead,No,36
+Dead,Yes,51
+Alive,No,25
+Alive,No,48
+Alive,No,24
+Dead,Yes,42
+Alive,No,64
+Alive,No,36
+Alive,Yes,47
+Alive,No,64
+Alive,No,22
+Alive,No,31
+Alive,No,55
+Dead,Yes,78
+Alive,No,27
+Alive,No,63
+Dead,Yes,83
+Alive,No,55
+Alive,Yes,57
+Alive,Yes,31
+Dead,No,64
+Alive,Yes,25
+Alive,No,38
+Dead,No,68
+Alive,No,59
+Alive,Yes,63
+Alive,Yes,18
+Alive,Yes,44
+Alive,No,38
+Dead,Yes,72
+Alive,Yes,28
+Alive,Yes,37
+Dead,No,51
+Dead,Yes,53
+Alive,Yes,31
+Dead,No,69
+Alive,Yes,51
+Alive,Yes,36
+Alive,No,27
+Alive,Yes,24
+Alive,Yes,64
+Alive,No,64
+Alive,Yes,64
+Dead,No,64
+Alive,Yes,46
+Alive,Yes,67
+Alive,Yes,40
+Alive,Yes,49
+Alive,Yes,25
+Alive,Yes,36
+Dead,No,82
+Alive,Yes,56
+Dead,Yes,56
+Alive,No,37
+Dead,Yes,59
+Alive,Yes,42
+Alive,No,44
+Alive,Yes,18
+Alive,Yes,44
+Alive,No,32
+Alive,Yes,38
+Alive,Yes,32
+Alive,Yes,29
+Alive,No,51
+Alive,Yes,34
+Alive,Yes,32
+Alive,No,23
+Alive,Yes,48
+Alive,Yes,24
+Alive,Yes,21
+Alive,No,54
+Dead,No,68
+Alive,Yes,26
+Alive,No,51
+Alive,Yes,45
+Alive,No,31
+Alive,Yes,43
+Alive,Yes,30
+Dead,No,72
+Alive,No,19
+Alive,No,31
+Dead,No,70
+Alive,No,58
+Alive,No,27
+Alive,No,56
+Dead,Yes,46
+Dead,No,75
+Alive,No,35
+Alive,No,30
+Dead,No,47
+Alive,No,63
+Alive,No,66
+Alive,Yes,41
+Dead,Yes,82
+Alive,Yes,39
+Alive,Yes,33
+Dead,Yes,60
+Dead,No,73
+Alive,Yes,26
+Alive,No,21
+Alive,Yes,39
+Dead,Yes,51
+Alive,No,28
+Alive,Yes,54
+Alive,No,51
+Dead,No,69
+Alive,Yes,63
+Alive,Yes,47
+Alive,No,38
+Dead,Yes,61
+Alive,Yes,31
+Alive,Yes,62
+Alive,No,62
+Alive,Yes,21
+Alive,Yes,32
+Alive,No,38
+Dead,No,67
+Alive,No,59
+Dead,No,71
+Alive,No,35
+Alive,Yes,28
+Alive,Yes,31
+Dead,Yes,58
+Alive,Yes,53
+Alive,No,48
+Alive,No,27
+Alive,No,30
+Dead,Yes,50
+Dead,Yes,43
+Alive,No,41
+Alive,No,37
+Alive,No,31
+Alive,No,30
+Alive,Yes,52
+Alive,Yes,37
+Alive,No,45
+Alive,Yes,36
+Alive,Yes,34
+Alive,Yes,39
+Alive,No,30
+Dead,Yes,57
+Alive,No,40
+Dead,Yes,62
+Alive,Yes,62
+Alive,Yes,60
+Alive,No,56
+Alive,No,45
+Alive,No,22
+Alive,No,27
+Alive,Yes,18
+Alive,Yes,26
+Dead,No,77
+Alive,No,33
+Alive,No,35
+Alive,No,33
+Dead,No,55
+Alive,No,45
+Alive,No,32
+Alive,No,34
+Alive,No,67
+Alive,No,35
+Dead,Yes,72
+Dead,No,79
+Alive,Yes,35
+Alive,No,38
+Alive,Yes,25
+Alive,Yes,37
+Alive,No,56
+Dead,No,66
+Dead,No,49
+Alive,Yes,33
+Dead,No,59
+Alive,No,44
+Alive,No,39
+Dead,No,58
+Alive,No,64
+Alive,No,18
+Alive,Yes,45
+Alive,No,33
+Alive,No,32
+Dead,No,80
+Alive,Yes,44
+Alive,Yes,25
+Alive,No,68
+Alive,Yes,34
+Alive,Yes,29
+Dead,Yes,72
+Alive,Yes,32
+Alive,Yes,56
+Alive,Yes,43
+Dead,Yes,60
+Alive,Yes,53
+Alive,Yes,41
+Alive,Yes,63
+Dead,Yes,57
+Alive,No,24
+Alive,Yes,39
+Alive,Yes,39
+Alive,No,31
+Alive,Yes,45
+Alive,No,66
+Alive,No,18
+Dead,No,72
+Alive,No,49
+Alive,No,37
+Dead,No,68
+Dead,Yes,69
+Alive,No,27
+Alive,Yes,20
+Alive,No,52
+Alive,Yes,62
+Alive,Yes,64
+Alive,Yes,42
+Alive,No,66
+Dead,No,78
+Alive,No,33
+Alive,No,31
+Alive,Yes,49
+Alive,No,58
+Alive,Yes,23
+Alive,Yes,41
+Alive,Yes,34
+Alive,Yes,30
+Alive,Yes,24
+Alive,Yes,31
+Alive,Yes,64
+Dead,Yes,81
+Dead,No,79
+Alive,No,54
+Alive,Yes,47
+Alive,Yes,25
+Dead,Yes,68
+Alive,Yes,23
+Alive,No,74
+Alive,Yes,25
+Alive,Yes,54
+Dead,No,78
+Dead,No,65
+Alive,Yes,39
+Dead,No,73
+Alive,No,27
+Alive,Yes,62
+Alive,Yes,26
+Dead,Yes,57
+Alive,No,41
+Alive,No,41
+Dead,Yes,66
+Dead,Yes,48
+Dead,Yes,68
+Alive,Yes,43
+Alive,No,28
+Alive,Yes,58
+Dead,Yes,56
+Dead,Yes,40
+Dead,No,69
+Alive,Yes,47
+Alive,Yes,52
+Alive,Yes,52
+Dead,No,80
+Alive,Yes,64
+Alive,No,39
+Alive,Yes,54
+Alive,No,55
+Alive,No,51
+Alive,Yes,28
+Dead,No,77
+Alive,Yes,27
+Dead,No,82
+Dead,No,65
+Dead,No,80
+Alive,No,46
+Alive,Yes,38
+Alive,Yes,28
+Dead,No,49
+Alive,Yes,44
+Alive,No,30
+Alive,No,63
+Alive,No,63
+Dead,Yes,68
+Alive,Yes,46
+Alive,No,52
+Alive,No,52
+Alive,No,55
+Alive,No,74
+Alive,Yes,44
+Alive,No,51
+Alive,Yes,35
+Alive,Yes,36
+Alive,Yes,33
+Alive,No,26
+Alive,No,21
+Alive,No,18
+Alive,No,30
+Dead,No,81
+Alive,Yes,63
+Dead,Yes,42
+Alive,No,35
+Alive,Yes,38
+Alive,No,28
+Alive,Yes,62
+Alive,No,39
+Alive,No,39
+Alive,No,61
+Alive,Yes,19
+Alive,Yes,46
+Dead,Yes,70
+Alive,Yes,38
+Alive,No,33
+Alive,Yes,53
+Alive,No,19
+Dead,No,82
+Alive,Yes,49
+Alive,Yes,47
+Dead,No,78
+Alive,Yes,22
+Alive,Yes,31
+Alive,No,31
+Alive,No,57
+Alive,No,65
+Dead,No,68
+Alive,Yes,22
+Alive,Yes,27
+Alive,Yes,50
+Dead,Yes,53
+Alive,No,34
+Alive,Yes,37
+Alive,No,35
+Alive,No,38
+Dead,No,43
+Alive,Yes,34
+Alive,No,64
+Alive,No,43
+Dead,Yes,57
+Alive,Yes,55
+Alive,Yes,34
+Alive,No,29
+Alive,No,18
+Dead,No,38
+Alive,Yes,40
+Alive,No,44
+Dead,No,71
+Dead,Yes,61
+Alive,Yes,26
+Dead,No,35
+Alive,No,26
+Alive,No,39
+Alive,Yes,43
+Alive,Yes,44
+Alive,No,38
+Alive,No,37
+Dead,Yes,52
+Alive,No,56
+Dead,No,70
+Alive,Yes,39
+Dead,Yes,57
+Alive,Yes,46
+Alive,Yes,28
+Alive,No,21
+Dead,Yes,66
+Alive,Yes,38
+Alive,Yes,32
+Alive,Yes,23
+Alive,No,61
+Alive,Yes,32
+Alive,No,27
+Dead,Yes,73
+Alive,Yes,36
+Alive,No,33
+Alive,No,28
+Alive,No,43
+Alive,Yes,56
+Alive,No,27
+Alive,No,36
+Alive,No,20
+Dead,No,69
+Alive,No,44
+Alive,Yes,26
+Dead,Yes,31
+Dead,No,72
+Dead,No,84
+Alive,Yes,48
+Alive,No,18
+Dead,Yes,82
+Alive,Yes,51
+Alive,Yes,33
+Alive,No,56
+Alive,No,74
+Alive,No,24
+Dead,No,74
+Alive,No,28
+Alive,Yes,58
+Alive,Yes,49
+Dead,Yes,64
+Alive,No,34
+Dead,No,84
+Dead,Yes,47
+Alive,Yes,58
+Dead,Yes,63
+Dead,No,57
+Alive,Yes,18
+Alive,No,23
+Alive,No,51
+Alive,No,55
+Alive,No,49
+Dead,No,60
+Alive,No,39
+Alive,No,48
+Alive,No,28
+Dead,No,74
+Alive,Yes,61
+Alive,Yes,33
+Dead,No,64
+Dead,No,77
+Alive,Yes,51
+Alive,Yes,23
+Dead,No,43
+Alive,No,47
+Alive,No,27
+Alive,No,48
+Alive,Yes,29
+Alive,No,45
+Alive,Yes,31
+Dead,Yes,60
+Alive,No,53
+Alive,No,26
+Dead,Yes,61
+Alive,No,38
+Alive,No,22
+Alive,Yes,41
+Alive,Yes,27
+Alive,No,63
+Dead,Yes,60
+Dead,No,64
+Alive,No,58
+Alive,No,42
+Dead,No,82
+Dead,No,62
+Alive,No,64
+Alive,No,34
+Alive,No,58
+Alive,Yes,63
+Dead,No,63
+Dead,No,79
+Alive,No,44
+Alive,No,41
+Alive,No,34
+Alive,Yes,38
+Alive,Yes,54
+Alive,No,53
+Dead,No,80
+Dead,Yes,46
+Alive,Yes,61
+Dead,No,72
+Alive,Yes,61
+Alive,Yes,28
+Alive,Yes,20
+Dead,Yes,46
+Dead,No,56
+Dead,No,84
+Dead,Yes,64
+Dead,No,42
+Alive,No,30
+Alive,No,48
+Alive,Yes,25
+Dead,No,76
+Dead,Yes,61
+Alive,No,41
+Alive,No,29
+Dead,No,80
+Alive,Yes,56
+Alive,Yes,58
+Dead,No,73
+Alive,No,18
+Alive,No,42
+Dead,No,67
+Alive,No,30
+Dead,No,78
+Dead,Yes,36
+Dead,No,78
+Alive,No,44
+Alive,No,35
+Alive,Yes,53
+Dead,No,52
+Alive,Yes,63
+Dead,No,79
+Alive,No,51
+Alive,No,59
+Alive,No,62
+Alive,No,35
+Alive,No,32
+Alive,Yes,48
+Dead,Yes,53
+Dead,Yes,49
+Alive,Yes,23
+Alive,Yes,50
+Alive,No,26
+Dead,Yes,44
+Dead,Yes,71
+Dead,No,78
+Alive,No,40
+Alive,No,71
+Alive,Yes,62
+Alive,No,30
+Alive,No,32
+Dead,No,71
+Alive,No,70
+Alive,No,27
+Dead,Yes,60
+Dead,No,65
+Dead,No,72
+Alive,No,22
+Alive,Yes,26
+Alive,No,26
+Alive,Yes,30
+Alive,Yes,21
+Alive,Yes,28
+Alive,No,60
+Alive,No,53
+Alive,Yes,59
+Dead,Yes,63
+Alive,Yes,36
+Alive,No,34
+Alive,Yes,61
+Dead,No,65
+Dead,Yes,59
+Dead,No,70
+Dead,Yes,48
+Alive,Yes,50
+Dead,No,83
+Alive,No,51
+Alive,Yes,24
+Alive,No,46
+Alive,No,19
+Alive,Yes,36
+Alive,No,33
+Dead,No,56
+Alive,No,57
+Alive,No,44
+Alive,No,53
+Alive,Yes,30
+Alive,No,42
+Alive,Yes,42
+Alive,Yes,58
+Alive,No,32
+Alive,No,30
+Dead,No,73
+Alive,No,34
+Dead,Yes,76
+Alive,Yes,51
+Dead,No,71
+Dead,No,60
+Alive,No,36
+Alive,Yes,18
+Alive,No,34
+Dead,No,70
+Alive,Yes,50
+Alive,Yes,41
+Alive,No,55
+Alive,No,36
+Dead,Yes,66
+Alive,No,58
+Alive,Yes,31
+Alive,No,36
+Dead,No,68
+Alive,No,24
+Alive,No,25
+Alive,Yes,42
+Alive,No,31
+Alive,Yes,18
+Alive,Yes,27
+Alive,No,20
+Alive,No,40
+Alive,Yes,57
+Alive,No,73
+Alive,No,44
+Alive,No,63
+Alive,No,19
+Dead,Yes,49
+Alive,No,59
+Alive,Yes,23
+Alive,Yes,53
+Alive,Yes,51
+Alive,Yes,22
+Alive,No,24
+Alive,Yes,51
+Alive,Yes,26
+Dead,No,68
+Dead,No,56
+Alive,No,47
+Alive,Yes,36
+Alive,Yes,46
+Alive,No,26
+Alive,Yes,74
+Alive,No,26
+Alive,Yes,52
+Alive,No,57
+Alive,Yes,34
+Alive,No,60
+Alive,Yes,32
+Alive,Yes,41
+Dead,No,82
+Alive,Yes,31
+Alive,No,68
+Alive,No,25
+Dead,No,84
+Alive,No,37
+Alive,No,37
+Dead,No,83
+Alive,No,62
+Alive,No,25
+Alive,Yes,55
+Alive,No,23
+Alive,Yes,52
+Alive,Yes,33
+Alive,Yes,53
+Alive,No,55
+Alive,Yes,45
+Alive,Yes,19
+Alive,Yes,53
+Alive,No,18
+Alive,Yes,32
+Alive,No,32
+Dead,No,67
+Dead,Yes,60
+Alive,Yes,35
+Alive,Yes,60
+Alive,Yes,56
+Alive,No,28
+Dead,No,61
+Alive,Yes,46
+Alive,No,22
+Dead,No,55
+Dead,No,66
+Dead,Yes,71
+Dead,No,68
+Alive,No,50
+Alive,Yes,32
+Alive,No,24
+Alive,No,38
+Alive,No,64
+Dead,Yes,51
+Alive,Yes,29
+Dead,No,77
+Alive,No,25
+Alive,No,50
+Alive,No,61
+Alive,Yes,23
+Dead,No,67
+Dead,No,73
+Alive,No,23
+Alive,Yes,59
+Dead,No,61
+Alive,Yes,43
+Alive,No,25
+Alive,No,39
+Alive,No,45
+Alive,No,25
+Alive,Yes,52
+Dead,No,46
+Alive,No,25
+Alive,No,30
+Alive,Yes,62
+Alive,No,58
+Alive,Yes,25
+Alive,No,31
+Dead,No,46
+Dead,Yes,27
+Dead,No,68
+Alive,Yes,35
+Alive,No,25
+Alive,Yes,42
+Dead,No,72
+Alive,Yes,55
+Alive,No,29
+Alive,Yes,29
+Alive,Yes,36
+Dead,No,51
+Dead,No,80
+Dead,No,74
+Alive,No,20
+Dead,No,45
+Alive,No,46
+Alive,Yes,43
+Alive,No,66
+Dead,Yes,45
+Alive,Yes,71
+Alive,No,43
+Alive,Yes,27
+Alive,No,22
+Alive,Yes,41
+Alive,No,60
+Alive,Yes,46
+Alive,No,29
+Dead,Yes,55
+Alive,Yes,36
+Dead,No,84
+Alive,No,67
+Dead,No,45
+Alive,No,34
+Dead,No,65
+Alive,Yes,32
+Dead,No,71
+Alive,No,26
+Alive,Yes,26
+Dead,No,72
+Alive,No,45
+Alive,No,27
+Alive,Yes,36
+Alive,No,34
+Dead,No,78
+Alive,Yes,20
+Alive,Yes,46
+Alive,No,27
+Alive,No,74
+Alive,Yes,46
+Alive,Yes,31
+Alive,Yes,46
+Alive,No,58
+Dead,No,72
+Dead,Yes,56
+Alive,No,45
+Alive,No,60
+Dead,No,65
+Dead,No,71
+Dead,No,76
+Alive,No,55
+Alive,No,35
+Alive,Yes,44
+Dead,Yes,47
+Dead,Yes,63
+Alive,Yes,32
+Alive,No,43
+Alive,Yes,35
+Dead,Yes,63
+Alive,No,29
+Alive,No,51
+Alive,Yes,42
+Dead,Yes,45
+Alive,Yes,19
+Dead,No,69
+Alive,Yes,39
+Dead,Yes,61
+Alive,Yes,19
+Alive,No,53
+Alive,Yes,61
+Alive,No,40
+Alive,No,37
+Alive,No,37
+Dead,No,65
+Alive,No,74
+Alive,Yes,50
+Alive,Yes,25
+Alive,No,32
+Alive,No,28
+Alive,No,71
+Dead,No,27
+Alive,No,23
+Alive,Yes,64
+Alive,No,28
+Dead,No,56
+Alive,No,25
+Dead,Yes,61
+Alive,No,63
+Alive,No,24
+Alive,No,64
+Dead,No,58
+Alive,No,34
+Alive,No,31
+Alive,Yes,33
+Alive,Yes,48
+Alive,Yes,55
+Alive,No,72
+Alive,No,43
+Alive,Yes,20
+Alive,Yes,62
+Alive,No,18
+Alive,Yes,21
+Alive,No,38
+Alive,Yes,45
+Dead,Yes,81
+Alive,Yes,66
+Alive,No,33
+Alive,Yes,32
+Alive,No,29
+Alive,Yes,53
+Alive,No,21
+Alive,No,61
+Alive,No,24
+Dead,No,54
+Alive,Yes,46
+Alive,No,58
+Dead,No,65
+Dead,No,82
+Alive,No,53
+Dead,No,33
+Alive,Yes,49
+Alive,No,42
+Alive,Yes,43
+Alive,Yes,20
+Dead,No,56
+Dead,No,82
+Dead,No,72
+Alive,No,20
+Dead,No,82
+Alive,No,62
+Alive,Yes,54
+Alive,No,54
+Dead,Yes,82
+Alive,Yes,47
+Alive,Yes,18
+Dead,No,72
+Alive,Yes,35
+Dead,No,69
+Alive,No,52
+Dead,No,59
+Dead,Yes,52
+Alive,Yes,29
+Alive,No,21
+Alive,No,28
+Alive,Yes,25
+Alive,Yes,25
+Alive,Yes,58
+Alive,Yes,43
+Alive,No,62
+Dead,No,67
+Alive,Yes,48
+Alive,Yes,54
+Alive,Yes,42
+Alive,No,66
+Alive,Yes,23
+Alive,Yes,67
+Alive,No,47
+Alive,No,28
+Alive,No,38
+Alive,No,64
+Dead,No,57
+Alive,No,56
+Alive,No,34
+Alive,Yes,50
+Alive,No,58
+Alive,No,32
+Dead,No,77
+Alive,Yes,23
+Alive,Yes,36
+Dead,No,18
+Alive,No,47
+Dead,No,70
+Dead,Yes,60
+Dead,No,71
+Dead,Yes,56
+Alive,Yes,32
+Alive,No,28
+Alive,No,51
+Alive,No,37
+Alive,No,30
+Dead,No,77
+Dead,No,70
+Alive,No,41
+Alive,No,32
+Alive,Yes,48
+Alive,No,53
+Dead,Yes,65
+Dead,No,66
+Dead,Yes,59
+Dead,No,60
+Dead,Yes,58
+Alive,No,64
+Alive,Yes,61
+Dead,No,62
+Alive,No,58
+Alive,No,37
+Dead,Yes,53
+Alive,No,65
+Alive,No,27
+Dead,No,72
+Dead,Yes,60
+Alive,Yes,45
+Alive,Yes,63
+Alive,No,32
+Alive,No,18
+Alive,Yes,49
+Alive,No,34
+Alive,No,23
+Alive,No,61
+Alive,No,44
+Alive,No,66
+Alive,No,28
+Alive,Yes,44
+Alive,Yes,29
+Alive,Yes,38
+Alive,Yes,52
+Alive,Yes,54
+Alive,Yes,63
+Dead,Yes,45
+Dead,No,74
+Alive,No,24
+Alive,No,40
+Alive,No,28
+Alive,Yes,30
+Alive,Yes,43
+Dead,Yes,63
+Alive,Yes,33
+Alive,Yes,41
+Alive,No,60
+Alive,Yes,31
+Alive,Yes,47
+Dead,No,81
+Dead,No,78
+Alive,No,56
+Dead,No,73
+Alive,No,56
+Alive,Yes,28
+Alive,Yes,22
+Alive,No,34
+Alive,No,48
+Alive,No,27
+Alive,Yes,47
+Alive,No,31
+Alive,No,47
+Dead,No,60
+Dead,No,59
+Dead,No,80
+Alive,Yes,41
+Dead,Yes,46
+Alive,Yes,50
+Alive,No,48
+Alive,No,37
+Alive,Yes,50
+Alive,Yes,25
+Alive,No,25
+Alive,No,41
+Alive,No,24
+Alive,Yes,57
+Dead,No,71
+Alive,Yes,26
+Dead,No,32
+Alive,No,25
+Dead,No,84
+Alive,Yes,19
+Alive,No,26
+Alive,Yes,58
+Dead,Yes,67
+Alive,No,24
+Dead,Yes,74
+Alive,Yes,58
+Alive,No,57
+Alive,Yes,52
+Alive,Yes,42
+Alive,No,42
+Dead,No,69
+Dead,Yes,39
+Dead,Yes,84
+Alive,Yes,57
+Alive,No,42
+Alive,No,35
+Alive,No,23
+Alive,No,65
+Alive,Yes,28
+Alive,No,39
+Alive,Yes,36
+Alive,No,40
+Alive,No,39
+Alive,No,19
+Alive,No,61
+Alive,Yes,37
+Alive,Yes,52
+Alive,Yes,62
+Alive,No,30
+Alive,Yes,23
+Dead,Yes,72
+Alive,Yes,46
+Alive,No,33
+Alive,No,32
+Alive,No,27
+Dead,Yes,72
+Dead,Yes,53
+Dead,Yes,58
+Alive,Yes,32
+Alive,No,25
+Dead,No,71
+Alive,Yes,37
+Alive,Yes,41
+Dead,No,75
+Alive,No,29
+Dead,Yes,62
+Alive,Yes,30
+Alive,No,20
+Alive,Yes,26
+Dead,No,60
+Dead,No,65
+Dead,Yes,63
+Alive,No,19
+Dead,Yes,55
+Alive,Yes,45
+Alive,No,28
+Alive,Yes,21
+Alive,No,35
+Alive,No,24
+Dead,No,74
+Dead,No,63
+Alive,No,44
+Alive,Yes,26
+Dead,No,84
+Alive,Yes,27
+Alive,No,28
+Dead,Yes,60
+Alive,No,44
+Dead,No,82
+Dead,No,29
+Alive,Yes,52
+Alive,Yes,42
+Alive,Yes,18
+Dead,No,61
+Dead,No,60
+Alive,Yes,19
+Dead,No,84
+Dead,No,72
+Alive,No,59
+Dead,No,78
+Alive,No,41
+Alive,No,21
+Alive,No,31
+Dead,No,83
+Alive,No,62
+Dead,No,76
+Dead,Yes,63
+Alive,No,44
+Dead,No,65
+Alive,No,33
+Alive,Yes,40
+Alive,No,50
+Dead,No,74
+Alive,No,19
+Alive,No,50
+Dead,Yes,62
+Alive,Yes,25
+Dead,Yes,66
+Alive,No,67
+Alive,Yes,18
+Alive,Yes,28
+Alive,Yes,49
+Alive,Yes,39
+Alive,Yes,33
+Alive,No,44
+Alive,No,48
+Alive,Yes,37
+Dead,Yes,71
+Dead,No,66
+Alive,Yes,34
+Dead,Yes,77
+Alive,No,48
+Alive,Yes,60
+Alive,No,41
+Alive,No,55
+Alive,Yes,46
+Alive,No,55
+Alive,No,20
+Dead,Yes,80
+Alive,Yes,57
+Alive,No,52
+Alive,Yes,48
+Alive,No,30
+Alive,Yes,57
+Alive,Yes,37
+Alive,No,27
+Alive,No,37
+Alive,No,36
+Alive,No,23
+Dead,No,55
+Alive,No,40
+Alive,No,33
+Alive,No,23
+Alive,Yes,35
+Alive,No,33
+Alive,Yes,21
+Alive,No,46
+Alive,Yes,41

From 5c6f824bf3f36d9da365b0c3683eedfe9821ea3e Mon Sep 17 00:00:00 2001
From: Linagyu Min <siliconmagic@126.com>
Date: Tue, 16 Oct 2018 22:04:43 +0800
Subject: [PATCH 4/5] hypothesis_testing_and_p_value_Minux

---
 TEW_06_hypothesis_testing_p_value_CI.py | 55 +++++++++++++++++++++++++
 1 file changed, 55 insertions(+)
 create mode 100644 TEW_06_hypothesis_testing_p_value_CI.py

diff --git a/TEW_06_hypothesis_testing_p_value_CI.py b/TEW_06_hypothesis_testing_p_value_CI.py
new file mode 100644
index 0000000..6c49781
--- /dev/null
+++ b/TEW_06_hypothesis_testing_p_value_CI.py
@@ -0,0 +1,55 @@
+#coding:utf-8
+"""
+------------------------------------------------
+@File Name    : TEW_06_hypothesis_testing_p_value_CI
+@Function     : 
+@Author       : Minux
+@Date         : 2018/10/16
+@Revised Date : 2018/10/16
+------------------------------------------------
+"""
+import math
+import io
+import numpy as np
+import pandas as pd
+
+import matplotlib.pyplot as plt
+
+import scipy.stats
+import scipy.optimize
+import scipy.spatial
+
+cholera = pd.read_csv('cholera.csv') # 霍乱数据
+pumps = pd.read_csv('pumps.csv')     # 水泵数据
+
+def Plot_Cholera_func():
+    fig = plt.figure(figsize=(10, 10))
+    img = plt.imread('london.png')
+    plt.imshow(img, extent=[-0.38, 0.38, -0.38, 0.38])
+    plt.scatter(pumps.x, pumps.y, color='b')
+    plt.scatter(cholera.x, cholera.y, color='r', s=3)
+    plt.show()
+
+def Data_stat_info():
+    print(cholera.closest.value_counts())
+    print('-'*10,'GroupBy_Closest','-'*10)
+    print(cholera.groupby('closest').deaths.sum())
+
+def simulate(n):
+    return pd.DataFrame({'closest':np.random.choice([0,1,4,5], size=n, p=[0.65, 0.15, 0.10, 0.10])})
+
+def sampling_function():
+    sampling = pd.DataFrame({'counts':[simulate(489).closest.value_counts()[0] for _ in range(10000)]})
+    # sampling.counts.hist(histtype='step')
+    # plt.show()
+    # 计算p-value
+    # the smaller p-value the more strongly we can reject the null hypothesis
+    p_value = 100.0 - scipy.stats.percentileofscore(sampling.counts, score=340)
+    print(p_value)
+
+
+if __name__ == '__main__':
+    sampling_function()
+
+
+

From 32ad0ba9a8b59de376c5c2ba897df8cfb48362fd Mon Sep 17 00:00:00 2001
From: Linagyu Min <siliconmagic@126.com>
Date: Tue, 23 Oct 2018 15:37:03 +0800
Subject: [PATCH 5/5] ANOVA

---
 TEW_07_Anova_Fitting_Models.py | 100 +++++++++++++++++++++++++++++++++
 1 file changed, 100 insertions(+)
 create mode 100644 TEW_07_Anova_Fitting_Models.py

diff --git a/TEW_07_Anova_Fitting_Models.py b/TEW_07_Anova_Fitting_Models.py
new file mode 100644
index 0000000..5d8e96b
--- /dev/null
+++ b/TEW_07_Anova_Fitting_Models.py
@@ -0,0 +1,100 @@
+#coding:utf-8
+"""
+------------------------------------------------
+@File Name    : TEW_07_Anova_Fitting_Models
+@Function     : 
+@Author       : Minux
+@Date         : 2018/10/23
+@Revised Date : 2018/10/23
+------------------------------------------------
+"""
+import math
+import numpy
+import pandas as pd
+import matplotlib.pyplot as plt
+import statsmodels.api as sm
+import statsmodels.formula.api as smf
+import numpy as np
+
+gap_minder = pd.read_csv('gapminder.csv')
+g_data = gap_minder.query('year==1985')
+
+size = g_data.population * 1e-6
+colors = g_data.region.map({'Africa':'skyblue','Europe':'gold','America':'palegreen','Asia':'red'})
+
+def plot_data():
+    g_data.plot.scatter('age5_surviving','babies_per_woman',c=colors, s=size, linewidths=0.5, edgecolor='k', alpha=0.5)
+
+model = smf.ols(formula='babies_per_woman ~ 1', data=g_data)
+grand_mean = model.fit()
+
+def plot_fit(fit_model):
+    plot_data()
+    plt.scatter(g_data.age5_surviving, fit_model.predict(g_data), c=colors, s=30, linewidths=0.5,
+                edgecolors='k', marker='D')
+    plt.show()
+
+# plot_fit(grand_mean)
+print(np.char.center('mean', 30, '-'))
+'''mean'''
+print(grand_mean.params)
+print(g_data.babies_per_woman.mean())
+
+print(np.char.center('group mean', 30, '-'))
+
+'''group means'''
+group_means = smf.ols(formula='babies_per_woman ~ -1+region', data=g_data).fit()
+# plot_fit(group_means)
+
+print(group_means.params)
+print(g_data.groupby('region').babies_per_woman.mean())
+
+print(np.char.center('surviving', 30, '-'))
+surviving = smf.ols(formula='babies_per_woman ~ -1 + region + age5_surviving', data=g_data).fit()
+# plot_fit(surviving)
+
+'''add intersection term'''
+surviving_by_region_population = smf.ols(formula='babies_per_woman ~ -1+region+age5_surviving:region'
+                                      '-age5_surviving + population', data=g_data).fit()
+# plot_fit(surviving_by_region)
+print(surviving_by_region_population.params)
+
+'''
+Measure of Godness of Fit
+Mean Squared Error of Residuals
+R^2 = (Explained Variance)/(Total Variance)
+F-statistics : explanatory power of fit parameters compared to random fit vectors
+'''
+print(np.char.center('Statistics_Indicator',30,'-'))
+def statistics_indicator(*args):
+    for arg in args:
+        print(np.char.center(arg,30,'-'))
+        if arg is 'resid':
+            for model in [group_means, surviving, surviving_by_region_population]:
+                print(model.mse_resid)
+        elif arg is 'rsquared':
+            for model in [group_means, surviving, surviving_by_region_population]:
+                print(model.rsquared)
+        elif arg is 'f_value':
+            for model in [group_means, surviving, surviving_by_region_population]:
+                print(model.fvalue)
+        else:
+            continue
+
+statistics_indicator('resid','rsquared','f_value','xx')
+
+print(surviving.summary())
+
+print(sm.stats.anova_lm(group_means))
+
+
+
+
+
+
+
+
+
+
+
+