From 5fe0d4386c1f473b7012142759e50df73746024f Mon Sep 17 00:00:00 2001 From: Sean Owen Date: Fri, 15 Jan 2016 12:51:02 +0000 Subject: [PATCH] Fix order of arguments that Pyspark RDD.fold passes to its op - should be (acc, obj) like other implementations --- python/pyspark/rdd.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/python/pyspark/rdd.py b/python/pyspark/rdd.py index a019c05862549..c28594625457a 100644 --- a/python/pyspark/rdd.py +++ b/python/pyspark/rdd.py @@ -861,7 +861,7 @@ def fold(self, zeroValue, op): def func(iterator): acc = zeroValue for obj in iterator: - acc = op(obj, acc) + acc = op(acc, obj) yield acc # collecting result of mapPartitions here ensures that the copy of # zeroValue provided to each partition is unique from the one provided