From f5fdf63fe0d0ea091c01a4144585276a7db63625 Mon Sep 17 00:00:00 2001 From: Davies Liu Date: Thu, 13 Nov 2014 12:54:14 -0800 Subject: [PATCH] fix bug with int in weights --- 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 4b2043ff9b465..0e8920281e842 100644 --- a/python/pyspark/rdd.py +++ b/python/pyspark/rdd.py @@ -325,13 +325,13 @@ def randomSplit(self, weights, seed=None): :return: split RDDs in a list >>> rdd = sc.parallelize(range(5), 1) - >>> rdd1, rdd2 = rdd.randomSplit([2.0, 3.0], 101) + >>> rdd1, rdd2 = rdd.randomSplit([2, 3], 101) >>> rdd1.collect() [2, 3] >>> rdd2.collect() [0, 1, 4] """ - s = sum(weights) + s = float(sum(weights)) cweights = [0.0] for w in weights: cweights.append(cweights[-1] + w / s)