diff options
| -rw-r--r-- | python/pyspark/ml/feature.py | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/python/pyspark/ml/feature.py b/python/pyspark/ml/feature.py index 86e654dd07..015e7a9d49 100644 --- a/python/pyspark/ml/feature.py +++ b/python/pyspark/ml/feature.py @@ -525,7 +525,7 @@ class RegexTokenizer(JavaTransformer, HasInputCol, HasOutputCol): """ A regex based tokenizer that extracts tokens either by using the provided regex pattern (in Java dialect) to split the text - (default) or repeatedly matching the regex (if gaps is true). + (default) or repeatedly matching the regex (if gaps is false). Optional parameters also allow filtering tokens using a minimal length. It returns an array of strings that can be empty. |