From a0853a39e1907700737ec924367cd2610da8395a Mon Sep 17 00:00:00 2001
From: Prashant Sharma <prashant.s@imaginea.com>
Date: Wed, 26 Mar 2014 09:16:37 -0700
Subject: [PATCH] SPARK-1322, top in pyspark should sort result in descending
order.
Author: Prashant Sharma <prashant.s@imaginea.com>
Closes #235 from ScrapCodes/SPARK-1322/top-rev-sort and squashes the following commits:
f316266 [Prashant Sharma] Minor change in comment.
58e58c6 [Prashant Sharma] SPARK-1322, top in pyspark should sort result in descending order.
---
python/pyspark/rdd.py | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/python/pyspark/rdd.py b/python/pyspark/rdd.py
index ca2dc119a4..019c249699 100644
--- a/python/pyspark/rdd.py
+++ b/python/pyspark/rdd.py
@@ -693,11 +693,11 @@ class RDD(object):
"""
Get the top N elements from a RDD.
- Note: It returns the list sorted in ascending order.
+ Note: It returns the list sorted in descending order.
>>> sc.parallelize([10, 4, 2, 12, 3]).top(1)
[12]
>>> sc.parallelize([2, 3, 4, 5, 6]).cache().top(2)
- [5, 6]
+ [6, 5]
"""
def topIterator(iterator):
q = []
@@ -711,7 +711,7 @@ class RDD(object):
def merge(a, b):
return next(topIterator(a + b))
- return sorted(self.mapPartitions(topIterator).reduce(merge))
+ return sorted(self.mapPartitions(topIterator).reduce(merge), reverse=True)
def take(self, num):
"""
--
GitLab