[SPARK-6660][MLLIB] pythonToJava doesn't recognize object arrays

davies

Author: Xiangrui Meng <meng@databricks.com>

Closes #5318 from mengxr/SPARK-6660 and squashes the following commits:

0f66ec2 [Xiangrui Meng] recognize object arrays
ad8c42f [Xiangrui Meng] add a test for SPARK-6660

1 files changed, 8 insertions, 0 deletions

diff --git a/python/pyspark/mllib/tests.py b/python/pyspark/mllib/tests.py
index 893fc6f491..6e9c68ec8a 100644
--- a/python/pyspark/mllib/tests.py
+++ b/python/pyspark/mllib/tests.py
@@ -36,6 +36,7 @@ if sys.version_info[:2] <= (2, 6):
 else:
     import unittest
 
+from pyspark.mllib.common import _to_java_object_rdd
 from pyspark.mllib.linalg import Vector, SparseVector, DenseVector, VectorUDT, _convert_to_vector,\
     DenseMatrix, Vectors, Matrices
 from pyspark.mllib.regression import LabeledPoint
@@ -641,6 +642,13 @@ class FeatureTest(PySparkTestCase):
         idf = model.idf()
         self.assertEqual(len(idf), 11)
 
+
+class SerDeTest(PySparkTestCase):
+    def test_to_java_object_rdd(self):  # SPARK-6660
+        data = RandomRDDs.uniformRDD(self.sc, 10, 5, seed=0L)
+        self.assertEqual(_to_java_object_rdd(data).count(), 10)
+
+
 if __name__ == "__main__":
     if not _have_scipy:
         print "NOTE: Skipping SciPy tests as it does not seem to be installed"