add repartition

markhamstra · Jan 27, 2015 · 257b9e6 · 257b9e6
1 parent 6bf2b73
commit 257b9e6
Showing 1 changed file with 6 additions and 4 deletions.
diff --git a/python/pyspark/sql.py b/python/pyspark/sql.py
@@ -2043,10 +2043,12 @@ def unpersist(self, blocking=True):
     #     rdd = self._jdf.coalesce(numPartitions, shuffle, None)
     #     return DataFrame(rdd, self.sql_ctx)
 
-    # def repartition(self, numPartitions):
-    #     rdd = self._jdf.repartition(numPartitions, None)
-    #     return DataFrame(rdd, self.sql_ctx)
-    #
+    def repartition(self, numPartitions):
+        """ Return a new :class:`DataFrame` that has exactly `numPartitions`
+        partitions.
+        """
+        rdd = self._jdf.repartition(numPartitions, None)
+        return DataFrame(rdd, self.sql_ctx)
 
     def sample(self, withReplacement, fraction, seed=None):
         """