SPARK-1322, top in pyspark should sort result in descending order.

andrewor14 · Mar 26, 2014 · 58e58c6 · 58e58c6
1 parent 007a733
commit 58e58c6
Showing 1 changed file with 2 additions and 2 deletions.
diff --git 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):
         """