From 530f8f9e91002faad01bb32ba82e106353c14a15 Mon Sep 17 00:00:00 2001
From: Keisuke OGAKI <hikingko1@gmail.com>
Date: Sun, 15 Oct 2023 23:45:53 +0900
Subject: [PATCH] Fix some dependencies for easy installation (#47)

* :art: lessen dependencies

* :fire: remove py3.5 tests

* texmex-python as extra package

* cannot installed with python3.10

---------

Co-authored-by: Keisuke Ogaki <keisuke-ogaki@m3.com>
---
 .github/workflows/test.yml | 2 +-
 README.md                  | 2 ++
 pqkmeans/evaluation.py     | 5 ++++-
 requirements.txt           | 5 ++---
 setup.py                   | 3 +++
 5 files changed, 12 insertions(+), 5 deletions(-)

diff --git a/.github/workflows/test.yml b/.github/workflows/test.yml
index edd2b0c..6146d03 100644
--- a/.github/workflows/test.yml
+++ b/.github/workflows/test.yml
@@ -13,7 +13,7 @@ jobs:
       max-parallel: 3
       matrix:
         platform: [ubuntu-latest]
-        python-version: [3.5, 3.7, 3.8, 3.9]
+        python-version: ["3.7", "3.8", "3.9"]
 
     steps:
     - uses: actions/checkout@v2
diff --git a/README.md b/README.md
index fbc51a4..b922c3d 100644
--- a/README.md
+++ b/README.md
@@ -56,6 +56,8 @@ python setup.py install
 
 
 ```
+# evaluation needs extra texmex package
+pip install pqkmeans[texmex]
 # with artificial data
 python bin/run_experiment.py --dataset artificial --algorithm bkmeans pqkmeans --k 100
 # with texmex dataset (http://corpus-texmex.irisa.fr/)
diff --git a/pqkmeans/evaluation.py b/pqkmeans/evaluation.py
index e91d7a7..1c573e9 100644
--- a/pqkmeans/evaluation.py
+++ b/pqkmeans/evaluation.py
@@ -3,7 +3,6 @@
 import os
 import six.moves.urllib
 import tarfile
-import texmex_python
 
 
 def get_gmm_random_dataset(k, dimension=100, test_size=5000, train_size=500):
@@ -39,6 +38,10 @@ def get_sift1m_dataset(cache_directory="."):
 
 
 def get_texmex_dataset(url, filename, member_names, cache_directory="."):
+    try:
+        import texmex_python
+    except ImportError:
+        raise ImportError("Missing optional dependency 'texmex_python'. You must install it to use this dataset.")
     path = os.path.join(cache_directory, filename)
     if not os.path.exists(path):
         print("downloading {}".format(url))
diff --git a/requirements.txt b/requirements.txt
index 29656d8..53751e4 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,6 +1,5 @@
-numpy
+numpy<1.21
 scikit-learn
-pipe
+pipe<2.0
 scipy
 six
-texmex_python==1.0.0
diff --git a/setup.py b/setup.py
index 953ed25..97b7ca4 100644
--- a/setup.py
+++ b/setup.py
@@ -92,4 +92,7 @@ def build_extension(self, ext):
     cmdclass=dict(build_ext=CMakeBuild),
     test_suite='test',
     zip_safe=False,
+    extras_require={
+        "texmex": ["texmex-python>=1.0.0"],
+    },
 )