[SPARK-14665][ML][PYTHON] Fixed bug with StopWordsRemover default stopwords

The default stopwords were a Java object.  They are no longer.

Unit test which failed before the fix

Author: Joseph K. Bradley <[email protected]>

Closes #12422 from jkbradley/pyspark-stopwords.

(cherry picked from commit d6ae7d4)
Signed-off-by: Joseph K. Bradley <[email protected]>

Conflicts:
	python/pyspark/ml/feature.py
	python/pyspark/ml/tests.py

Author: jkbradley

python/pyspark/ml/feature.py

@@ -1402,7 +1402,7 @@ def __init__(self, inputCol=None, outputCol=None, stopWords=None,
         self.caseSensitive = Param(self, "caseSensitive", "whether to do a case " +
                                    "sensitive comparison over the stop words")
         stopWordsObj = _jvm().org.apache.spark.ml.feature.StopWords
-        defaultStopWords = stopWordsObj.English()
+        defaultStopWords = list(stopWordsObj.English())
         self._setDefault(stopWords=defaultStopWords)
         kwargs = self.__init__._input_kwargs
         self.setParams(**kwargs)

python/pyspark/ml/tests.py

@@ -20,6 +20,9 @@
 """
 
 import sys
+if sys.version > '3':
+    basestring = str
+
 try:
     import xmlrunner
 except ImportError:
@@ -283,6 +286,8 @@ def test_stopwordsremover(self):
         self.assertEqual(stopWordRemover.getInputCol(), "input")
         transformedDF = stopWordRemover.transform(dataset)
         self.assertEqual(transformedDF.head().output, ["panda"])
+        self.assertEqual(type(stopWordRemover.getStopWords()), list)
+        self.assertTrue(isinstance(stopWordRemover.getStopWords()[0], basestring))
         # Custom
         stopwords = ["panda"]
         stopWordRemover.setStopWords(stopwords)