From 58e58c6d86b7120ec6ce5d5875bd6d8fbc82f1db Mon Sep 17 00:00:00 2001 From: Prashant Sharma Date: Wed, 26 Mar 2014 11:22:31 +0530 Subject: [PATCH] SPARK-1322, top in pyspark should sort result in descending order. --- python/pyspark/rdd.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/python/pyspark/rdd.py b/python/pyspark/rdd.py index ca2dc119a461a..598b5ddd6f962 100644 --- a/python/pyspark/rdd.py +++ b/python/pyspark/rdd.py @@ -697,7 +697,7 @@ def top(self, num): >>> 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 @@ def topIterator(iterator): 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): """