From d8c4b00a234514cc3a877e3daed5d1378a2637e8 Mon Sep 17 00:00:00 2001
From: Sean Owen <sowen@cloudera.com>
Date: Tue, 19 Jan 2016 09:34:49 +0000
Subject: [PATCH] [SPARK-7683][PYSPARK] Confusing behavior of fold function of
RDD in pyspark
Fix order of arguments that Pyspark RDD.fold passes to its op - should be (acc, obj) like other implementations.
Obviously, this is a potentially breaking change, so can only happen for 2.x
CC davies
Author: Sean Owen <sowen@cloudera.com>
Closes #10771 from srowen/SPARK-7683.
---
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 a019c05862..c285946254 100644
--- a/python/pyspark/rdd.py
+++ b/python/pyspark/rdd.py
@@ -861,7 +861,7 @@ class RDD(object):
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
--
GitLab