#328 added tests for example command line

* fixed: date not defined when not required causes failure

.travis.yml

@@ -47,7 +47,7 @@ install:
   - python -m easy_install -U setuptools
   # command to install dependencies
   #  - python setup.py install
-  - pip install -e .
+  - pip install -e .[test]
 
 script:
   # for codecov support

appveyor.yml

@@ -17,7 +17,7 @@ install:
   - python -m pip install -U pip
   - python -m easy_install -U setuptools
   # command to install dependencies
-  - python setup.py install
+  - pip install -e .[test]
   # also need to download punkt tokeniser data
   - python -m nltk.downloader punkt averaged_perceptron_tagger wordnet
 

scripts/pipeline.py

@@ -62,12 +62,16 @@ def __init__(self, data_filename, docs_mask_dict, pick_method='sum', ngram_range
                       f'to {number_of_ngrams_after:,}')
 
             self.__cpc_dict = utils.cpc_dict(dataframe)
-            self.__dates = scripts.utils.date_utils.generate_year_week_dates(dataframe, docs_mask_dict['date_header'])
-
-            min_date = min(self.__dates)
-            max_date = max(self.__dates)
+            if docs_mask_dict['date_header'] is None:
+                self.__cached_folder_name = path.join('cached', output_name + f'-mdf-{max_df}')
+                self.__dates = None
+            else:
+                self.__dates = scripts.utils.date_utils.generate_year_week_dates(dataframe,
+                                                                                 docs_mask_dict['date_header'])
+                min_date = min(self.__dates)
+                max_date = max(self.__dates)
+                self.__cached_folder_name = path.join('cached', output_name + f'-mdf-{max_df}-{min_date}-{max_date}')
 
-            self.__cached_folder_name = path.join('cached', output_name + f'-mdf-{max_df}-{min_date}-{max_date}')
             utils.pickle_object('tfidf', self.__tfidf_obj, self.__cached_folder_name)
             utils.pickle_object('dates', self.__dates, self.__cached_folder_name)
             utils.pickle_object('cpc_dict', self.__cpc_dict, self.__cached_folder_name)

setup.py

@@ -72,6 +72,7 @@ def setup_package():
                           'xlrd', 'python-Levenshtein', 'gensim==3.4.0', 'statsmodels', 'keras', 'tensorflow',
                           'keras_tqdm', 'patsy', 'humanfriendly', 'psutil', 'jinja2', 'urllib3==1.22'],
         # extras_require={'dev': ['check-manifest'],'test': ['coverage'],},
+        extras_require={'test': ['pytest']},
         python_requires='>=3.6',
         cmdclass={
             'install': CustomInstaller,

tests/test_readme.py

@@ -0,0 +1,30 @@
+import os
+import unittest
+
+import pytest
+
+import pygrams
+
+
+@pytest.mark.skipif('TRAVIS' not in os.environ, reason="Only execute with Travis due to speed")
+class TestReadme(unittest.TestCase):
+    """
+    Batch of tests to execute same commands as mentioned in the README.md, to ensure they work without crashing
+    """
+
+    def test_no_arguments_and_use_cache(self):
+        # clear cached result
+        import shutil
+        shutil.rmtree(os.path.join('cached', 'out-mdf-0.05'), ignore_errors=True)
+
+        # should make cache
+        pygrams.main([])
+
+        # load cache
+        pygrams.main(['-uc', 'out-mdf-0.05'])
+
+    def test_10000_patents(self):
+        pygrams.main(['-ds', 'USPTO-random-10000.pkl.bz2'])
+
+    def test_mn_mx(self):
+        pygrams.main(['-mn', '1', '-mx', '3'])