diff options
Diffstat (limited to 'python/pyspark/rdd.py')
| -rw-r--r-- | python/pyspark/rdd.py | 4 |
1 files changed, 3 insertions, 1 deletions
diff --git a/python/pyspark/rdd.py b/python/pyspark/rdd.py index a5e6e2b054..291c1caaae 100644 --- a/python/pyspark/rdd.py +++ b/python/pyspark/rdd.py @@ -2072,10 +2072,12 @@ class RDD(object): batchSize = min(10, self.ctx._batchSize or 1024) ser = BatchedSerializer(PickleSerializer(), batchSize) selfCopy = self._reserialize(ser) + jrdd_deserializer = selfCopy._jrdd_deserializer jrdd = selfCopy._jrdd.coalesce(numPartitions, shuffle) else: + jrdd_deserializer = self._jrdd_deserializer jrdd = self._jrdd.coalesce(numPartitions, shuffle) - return RDD(jrdd, self.ctx, self._jrdd_deserializer) + return RDD(jrdd, self.ctx, jrdd_deserializer) def zip(self, other): """ |