scikit-learn
diff --git a/‎sklearn/feature_extraction/text.py
Copy file name to clipboardExpand all lines: sklearn/feature_extraction/text.py
+1-1Lines changed: 1 addition & 1 deletion b/‎sklearn/feature_extraction/text.py
Copy file name to clipboardExpand all lines: sklearn/feature_extraction/text.py
+1-1Lines changed: 1 addition & 1 deletion
@@ -869,7 +869,7 @@ class CountVectorizer(_VectorizerMixin, BaseEstimator):
         in the range [0.7, 1.0) to automatically detect and filter stop
         words based on intra corpus document frequency of terms.
 
-    token_pattern : string
+    token_pattern : string, default=r"(?u)/b/w/w+/b"
         Regular expression denoting what constitutes a "token", only used
         if ``analyzer == 'word'``. The default regexp select tokens of 2
         or more alphanumeric characters (punctuation is completely ignored