[SPARK-12090] [PYSPARK] consider shuffle in coalesce()

Davies Liu · davies · commit ed7264ba20d1 · 2015-12-01T22:42:19.000-08:00
Author: Davies Liu <davies@databricks.com> Closes apache#10090 from davies/fix_coalesce. (cherry picked from commit 4375eb3) Signed-off-by: Davies Liu <davies.liu@gmail.com>
diff --git a/python/pyspark/rdd.py b/python/pyspark/rdd.py
@@ -2024,7 +2024,7 @@ def coalesce(self, numPartitions, shuffle=False):
         >>> 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):
