Repository: spark Updated Branches: refs/heads/master 0f37d1d7e -> 4375eb3f4
[SPARK-12090] [PYSPARK] consider shuffle in coalesce() Author: Davies Liu <dav...@databricks.com> Closes #10090 from davies/fix_coalesce. Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/4375eb3f Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/4375eb3f Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/4375eb3f Branch: refs/heads/master Commit: 4375eb3f48fc7ae90caf6c21a0d3ab0b66bf4efa Parents: 0f37d1d Author: Davies Liu <dav...@databricks.com> Authored: Tue Dec 1 22:41:48 2015 -0800 Committer: Davies Liu <davies....@gmail.com> Committed: Tue Dec 1 22:41:48 2015 -0800 ---------------------------------------------------------------------- python/pyspark/rdd.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/4375eb3f/python/pyspark/rdd.py ---------------------------------------------------------------------- diff --git a/python/pyspark/rdd.py b/python/pyspark/rdd.py index 4b4d596..00bb9a6 100644 --- a/python/pyspark/rdd.py +++ b/python/pyspark/rdd.py @@ -2015,7 +2015,7 @@ class RDD(object): >>> sc.parallelize([1, 2, 3, 4, 5], 3).coalesce(1).glom().collect() [[1, 2, 3, 4, 5]] """ - jrdd = self._jrdd.coalesce(numPartitions) + jrdd = self._jrdd.coalesce(numPartitions, shuffle) return RDD(jrdd, self.ctx, self._jrdd_deserializer) def zip(self, other): --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org