diff options
| author | Joseph K. Bradley <joseph@databricks.com> | 2016-04-15 11:50:21 -0700 |
|---|---|---|
| committer | Joseph K. Bradley <joseph@databricks.com> | 2016-04-15 11:50:21 -0700 |
| commit | d6ae7d4637d23c57c4eeab79d1177216f380ec9c (patch) | |
| tree | 0779a958d56eb4d7664c5cf3fe238aa42b94a2af /python/pyspark/ml/tests.py | |
| parent | 83af297ac42546580983f91079f74e3a4cf25050 (diff) | |
| download | spark-d6ae7d4637d23c57c4eeab79d1177216f380ec9c.tar.gz spark-d6ae7d4637d23c57c4eeab79d1177216f380ec9c.tar.bz2 spark-d6ae7d4637d23c57c4eeab79d1177216f380ec9c.zip | |
[SPARK-14665][ML][PYTHON] Fixed bug with StopWordsRemover default stopwords
## What changes were proposed in this pull request?
The default stopwords were a Java object. They are no longer.
## How was this patch tested?
Unit test which failed before the fix
Author: Joseph K. Bradley <joseph@databricks.com>
Closes #12422 from jkbradley/pyspark-stopwords.
Diffstat (limited to 'python/pyspark/ml/tests.py')
| -rw-r--r-- | python/pyspark/ml/tests.py | 3 |
1 files changed, 3 insertions, 0 deletions
diff --git a/python/pyspark/ml/tests.py b/python/pyspark/ml/tests.py index 86c0254a2b..85ad949c5a 100644 --- a/python/pyspark/ml/tests.py +++ b/python/pyspark/ml/tests.py @@ -22,6 +22,7 @@ import array import sys if sys.version > '3': xrange = range + basestring = str try: import xmlrunner @@ -398,6 +399,8 @@ class FeatureTests(PySparkTestCase): 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) |