diff options
| -rw-r--r-- | python/pyspark/rdd.py | 5 |
1 files changed, 4 insertions, 1 deletions
diff --git a/python/pyspark/rdd.py b/python/pyspark/rdd.py index f3b1f1a665..1b3c460dd6 100644 --- a/python/pyspark/rdd.py +++ b/python/pyspark/rdd.py @@ -1062,7 +1062,7 @@ class RDD(object): return python_right_outer_join(self, other, numPartitions) # TODO: add option to control map-side combining - def partitionBy(self, numPartitions, partitionFunc=hash): + def partitionBy(self, numPartitions, partitionFunc=None): """ Return a copy of the RDD partitioned using the specified partitioner. @@ -1073,6 +1073,9 @@ class RDD(object): """ if numPartitions is None: numPartitions = self.ctx.defaultParallelism + + if partitionFunc is None: + partitionFunc = lambda x: 0 if x is None else hash(x) # Transferring O(n) objects to Java is too expensive. Instead, we'll # form the hash buckets in Python, transferring O(numPartitions) objects # to Java. Each object is a (splitNumber, [objects]) pair. |