Investigate build and cicd issues

.travis.yml

@@ -26,4 +26,4 @@ install:
 # 'python3' is a 'command not found' error on Windows but 'py' works on Windows only
 script:
   - black --check . 
-  - python -m unittest discover -s tests -t . || python3 -m unittest discover -s tests -t .
+  - python -m unittest discover -s tests -t . || python3 -m unittest discover -s tests -t .

setup.cfg

@@ -29,13 +29,13 @@ python_requires = >=3.6.1
 install_requires =
     numpy>=1.17
     scikit-learn>=0.22
-    spacy>=2.2.2
+    spacy<3.0.0
     tqdm>=4.3
     nltk>=3.3
     plotly>=4.2.0
     pandas>=1.0.2
     wordcloud>=1.5.0
-    gensim>=3.6.0
+    gensim>=3.6.0,<4.0
     matplotlib>=3.1.0
 # TODO pick the correct version.
 [options.extras_require]

tests/test_representation.py

@@ -222,6 +222,29 @@ def test_dim_reduction_and_clustering_with_vector_series_input(
         else:
             result_s = test_function(vector_s, random_state=42)
 
+        # Binary categories: also test if it equals with
+        # the category labels inverted (e.g. [0, 1, 0] instead
+        # of [1, 0, 1], which makes no difference functionally)
+        if pd.api.types.is_categorical_dtype(result_s):
+            if len(result_s.cat.categories) == 2 and all(
+                result_s.cat.categories == [0, 1]
+            ):
+                try:
+                    result_s_inverted = result_s.apply(lambda category: 1 - category)
+                    pd.testing.assert_series_equal(
+                        s_true,
+                        result_s_inverted,
+                        check_dtype=False,
+                        rtol=0.1,
+                        atol=0.1,
+                        check_category_order=False,
+                        check_categorical=False,
+                    )
+                    return
+                # inverted comparison fails -> continue to normal comparison
+                except AssertionError:
+                    pass
+
         pd.testing.assert_series_equal(
             s_true,
             result_s,
@@ -248,13 +271,37 @@ def test_dim_reduction_and_clustering_with_dataframe_input(
         else:
             result_s = test_function(df, random_state=42)
 
+        # Binary categories: also test if it equals with
+        # the category labels inverted (e.g. [0, 1, 0] instead
+        # of [1, 0, 1], which makes no difference functionally)
+        if pd.api.types.is_categorical_dtype(result_s):
+            if len(result_s.cat.categories) == 2 and all(
+                result_s.cat.categories == [0, 1]
+            ):
+                try:
+                    result_s_inverted = result_s.apply(lambda category: 1 - category)
+                    pd.testing.assert_series_equal(
+                        s_true,
+                        result_s_inverted,
+                        check_dtype=False,
+                        rtol=0.1,
+                        atol=0.1,
+                        check_category_order=False,
+                        check_categorical=False,
+                    )
+                    return
+                # inverted comparison fails -> continue to normal comparison
+                except AssertionError:
+                    pass
+
         pd.testing.assert_series_equal(
             s_true,
             result_s,
             check_dtype=False,
             rtol=0.1,
             atol=0.1,
             check_category_order=False,
+            check_categorical=False,
         )
 
     def test_normalize_DataFrame_also_as_output(self):

texthero/_types.py

@@ -70,7 +70,7 @@ def tfidf(s: TokenSeries) -> DataFrame:
 # This class is mainly for documentation in the docstring.
 
 
-class HeroTypes(pd.Series, pd.DataFrame):
+class HeroTypes:
     """
     Hero Series Types
     =================

texthero/representation.py

@@ -632,7 +632,7 @@ def kmeans(
     >>> s = s.pipe(hero.clean).pipe(hero.tokenize).pipe(
     ...                                         hero.term_frequency
     ...                                             )
-    >>> hero.kmeans(s, n_clusters=2, random_state=42)
+    >>> hero.kmeans(s, n_clusters=2, random_state=42) # doctest: +SKIP
     0    1
     1    0
     2    1