From 07e1db72fa2c89ebbf15003878a20e0d3a3053d2 Mon Sep 17 00:00:00 2001 From: Chris Snow Date: Wed, 11 Nov 2015 15:56:40 +0000 Subject: [PATCH] Fix for SPARK-11658 --- python/pyspark/rdd.py | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/python/pyspark/rdd.py b/python/pyspark/rdd.py index 56e892243c79..7b20ad137a4d 100644 --- a/python/pyspark/rdd.py +++ b/python/pyspark/rdd.py @@ -1760,9 +1760,8 @@ def combineByKey(self, createCombiner, mergeValue, mergeCombiners, In addition, users can control the partitioning of the output RDD. >>> x = sc.parallelize([("a", 1), ("b", 1), ("a", 1)]) - >>> def f(x): return x >>> def add(a, b): return a + str(b) - >>> sorted(x.combineByKey(str, add, add).collect()) + >>> x.combineByKey(str, add, add).collect() [('a', '11'), ('b', '1')] """ if numPartitions is None: