1 files changed, 13 insertions, 0 deletions
diff --git a/python/pyspark/mllib/linalg.py b/python/pyspark/mllib/linalg.py
index 24c5480b2f..773d8d3938 100644
--- a/python/pyspark/mllib/linalg.py
+++ b/python/pyspark/mllib/linalg.py
@@ -29,6 +29,8 @@ import copy_reg
 
 import numpy as np
 
+from pyspark.serializers import AutoBatchedSerializer, PickleSerializer
+
 __all__ = ['Vector', 'DenseVector', 'SparseVector', 'Vectors']
 
 
@@ -50,6 +52,17 @@ except:
     _have_scipy = False
 
 
+# this will call the MLlib version of pythonToJava()
+def _to_java_object_rdd(rdd):
+    """ Return an JavaRDD of Object by unpickling
+
+    It will convert each Python object into Java object by Pyrolite, whenever the
+    RDD is serialized in batch or not.
+    """
+    rdd = rdd._reserialize(AutoBatchedSerializer(PickleSerializer()))
+    return rdd.ctx._jvm.SerDe.pythonToJava(rdd._jrdd, True)
+
+
 def _convert_to_vector(l):
     if isinstance(l, Vector):
         return l