Github user mengxr commented on a diff in the pull request:
https://github.com/apache/spark/pull/21501#discussion_r194607278
--- Diff: python/pyspark/ml/feature.py ---
@@ -2582,25 +2582,31 @@ class StopWordsRemover(JavaTransformer,
HasInputCol, HasOutputCol, JavaMLReadabl
typeConverter=TypeConverters.toListString)
caseSensitive = Param(Params._dummy(), "caseSensitive", "whether to do
a case sensitive " +
"comparison over the stop words",
typeConverter=TypeConverters.toBoolean)
+ locale = Param(Params._dummy(), "locale", "locale of the input.
ignored when case sensitive " +
+ "is true", typeConverter=TypeConverters.toString)
@keyword_only
- def __init__(self, inputCol=None, outputCol=None, stopWords=None,
caseSensitive=False):
+ def __init__(self, inputCol=None, outputCol=None, stopWords=None,
caseSensitive=False,
+ locale=None):
"""
- __init__(self, inputCol=None, outputCol=None, stopWords=None,
caseSensitive=false)
+ __init__(self, inputCol=None, outputCol=None, stopWords=None,
caseSensitive=false,
+ locale=None)
"""
super(StopWordsRemover, self).__init__()
self._java_obj =
self._new_java_obj("org.apache.spark.ml.feature.StopWordsRemover",
self.uid)
self._setDefault(stopWords=StopWordsRemover.loadDefaultStopWords("english"),
- caseSensitive=False)
+ caseSensitive=False,
locale=StopWordsRemover.defaultLocale())
--- End diff --
You already have the `_java_obj`, call `_java_object.getLocale()` would
give you the default locale. And then Python users only need
`stopWordsRemover.getLocale()` to get the default value. In the param doc, we
should make it clear that the default would be the JVM default locale.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
