Merge branch 'SummerOfCode-NoHate-travis_ci_reorg'

.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

@@ -49,4 +49,4 @@ dev =
     nbsphinx
     parameterized>=0.7.4
     coverage
-    pre-commit
+    pre-commit

tests/test_nlp.py

@@ -97,4 +97,4 @@ def test_pos(self):
             ]
         )
 
-        self.assertEquals(pos_tagging, s_true)
+        self.assertEqual(pos_tagging, s_true)

tests/test_representation.py

@@ -201,7 +201,7 @@ def test_vectorization_not_tokenized_yet_warning(self, name, test_function, *arg
     @parameterized.expand(test_cases_vectorization)
     def test_vectorization_arguments_to_sklearn(self, name, test_function, *args):
         try:
-            test_function(s_not_tokenized, max_features=1, min_df=1, max_df=1.0)
+            test_function(s_tokenized, max_features=1, min_df=1, max_df=1.0)
         except TypeError:
             self.fail("Sklearn arguments not handled correctly.")
 

texthero/_helper.py

@@ -43,7 +43,7 @@ def handle_nans(replace_nans_with):
     ... def replace_b_with_c(s):
     ...     return s.str.replace("b", "c")
     >>> s_with_nan = pd.Series(["Test b", np.nan])
-    >>> replace_b_with_c(s_with_nan)
+    >>> replace_b_with_c(s_with_nan) # doctest: +SKIP
     0            Test c
     1    I was missing!
     dtype: object

texthero/nlp.py

@@ -4,8 +4,8 @@
 
 import spacy
 import pandas as pd
+import en_core_web_sm
 from nltk.stem import PorterStemmer, SnowballStemmer
-
 from texthero._types import TextSeries, InputSeries
 
 
@@ -54,9 +54,9 @@ def named_entities(s: TextSeries, package="spacy") -> pd.Series:
     """
     entities = []
 
-    nlp = spacy.load("en_core_web_sm", disable=["tagger", "parser"])
-    # nlp.pipe is now 'ner'
+    nlp = en_core_web_sm.load(disable=["tagger", "parser"])
 
+    # nlp.pipe is now 'ner'
     for doc in nlp.pipe(s.astype("unicode").values, batch_size=32):
         entities.append(
             [(ent.text, ent.label_, ent.start_char, ent.end_char) for ent in doc.ents]
@@ -93,9 +93,9 @@ def noun_chunks(s: TextSeries) -> pd.Series:
 
     noun_chunks = []
 
-    nlp = spacy.load("en_core_web_sm", disable=["ner"])
-    # nlp.pipe is now "tagger", "parser"
+    nlp = en_core_web_sm.load(disable=["ner"])
 
+    # nlp.pipe is now "tagger", "parser"
     for doc in nlp.pipe(s.astype("unicode").values, batch_size=32):
         noun_chunks.append(
             [
@@ -131,7 +131,8 @@ def count_sentences(s: TextSeries) -> pd.Series:
     """
     number_of_sentences = []
 
-    nlp = spacy.load("en_core_web_sm", disable=["tagger", "parser", "ner"])
+    nlp = en_core_web_sm.load(disable=["tagger", "parser", "ner"])
+
     nlp.add_pipe(nlp.create_pipe("sentencizer"))  # Pipe is only "sentencizer"
 
     for doc in nlp.pipe(s.values, batch_size=32):
@@ -204,9 +205,9 @@ def pos_tag(s: TextSeries) -> pd.Series:
 
     pos_tags = []
 
-    nlp = spacy.load("en_core_web_sm", disable=["parser", "ner"])
-    # nlp.pipe is now "tagger"
+    nlp = en_core_web_sm.load(disable=["parser", "ner"])
 
+    # nlp.pipe is now "tagger"
     for doc in nlp.pipe(s.astype("unicode").values, batch_size=32):
         pos_tags.append(
             [