texmex-python as extra package

.github/workflows/test.yml

@@ -13,7 +13,7 @@ jobs:
       max-parallel: 3
       matrix:
         platform: [ubuntu-latest]
-        python-version: [3.7, 3.8, 3.9, 3.10]
+        python-version: ["3.7", "3.8", "3.9", "3.10"]
 
     steps:
     - uses: actions/checkout@v2

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/)

pqkmeans/evaluation.py

@@ -3,10 +3,6 @@
 import os
 import six.moves.urllib
 import tarfile
-try:
-    import texmex_python
-except ImportError:
-    pass
 
 
 def get_gmm_random_dataset(k, dimension=100, test_size=5000, train_size=500):
@@ -42,6 +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))

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"],
+    },
 )