From 5dec3d402b6974c5b059286c47b48ffd6e14ae5e Mon Sep 17 00:00:00 2001
From: Jeremy Silver <jeremy@udacity.com>
Date: Wed, 11 Feb 2015 15:30:24 -0800
Subject: [PATCH] Add key sort flag in feature format and final project

---
 final_project/poi_id.py | 2 +-
 final_project/tester.py | 2 +-
 tools/feature_format.py | 9 +++++++--
 3 files changed, 9 insertions(+), 4 deletions(-)

diff --git a/final_project/poi_id.py b/final_project/poi_id.py
index d7067c4080c..60b9e10428e 100644
--- a/final_project/poi_id.py
+++ b/final_project/poi_id.py
@@ -21,7 +21,7 @@
 my_dataset = data_dict
 
 ### Extract features and labels from dataset for local testing
-data = featureFormat(my_dataset, features_list)
+data = featureFormat(my_dataset, features_list, sort_keys = True)
 labels, features = targetFeatureSplit(data)
 
 ### Task 4: Try a varity of classifiers
diff --git a/final_project/tester.py b/final_project/tester.py
index a037dc61c7a..6895e978fd7 100644
--- a/final_project/tester.py
+++ b/final_project/tester.py
@@ -24,7 +24,7 @@
 RESULTS_FORMAT_STRING = "\tTotal predictions: {:4d}\tTrue positives: {:4d}\tFalse positives: {:4d}\tFalse negatives: {:4d}\tTrue negatives: {:4d}"
 
 def test_classifier(clf, dataset, feature_list, folds = 1000):
-    data = featureFormat(dataset, feature_list)
+    data = featureFormat(dataset, feature_list, sort_keys = True)
     labels, features = targetFeatureSplit(data)
     cv = StratifiedShuffleSplit(labels, folds, random_state = 42)
     true_negatives = 0
diff --git a/tools/feature_format.py b/tools/feature_format.py
index 372372dea16..a771251989e 100644
--- a/tools/feature_format.py
+++ b/tools/feature_format.py
@@ -33,7 +33,7 @@
 
 import numpy as np
 
-def featureFormat( dictionary, features, remove_NaN=True, remove_all_zeroes=True, remove_any_zeroes=False ):
+def featureFormat( dictionary, features, remove_NaN=True, remove_all_zeroes=True, remove_any_zeroes=False, sort_keys = False):
     """ convert dictionary to numpy array of features
         remove_NaN=True will convert "NaN" string to 0.0
         remove_all_zeroes=True will omit any data points for which
@@ -45,7 +45,12 @@ def featureFormat( dictionary, features, remove_NaN=True, remove_all_zeroes=True
 
     return_list = []
 
-    for key in sorted(dictionary.keys()):
+    if sort_keys:
+        keys = sorted(dictionary.keys())
+    else:
+        keys = dictionary.keys()
+
+    for key in keys:
         tmp_list = []
         append = False
         for feature in features: