From 67fa71cba2cc07a65478899592e6ebad000e24c5 Mon Sep 17 00:00:00 2001 From: Jyotiska NK Date: Wed, 19 Mar 2014 14:04:45 -0700 Subject: Added doctest for map function in rdd.py Doctest added for map in rdd.py Author: Jyotiska NK Closes #177 from jyotiska/pyspark_rdd_map_doctest and squashes the following commits: a38527f [Jyotiska NK] Added doctest for map function in rdd.py --- python/pyspark/rdd.py | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'python/pyspark/rdd.py') diff --git a/python/pyspark/rdd.py b/python/pyspark/rdd.py index ae09dbff02..ca2dc119a4 100644 --- a/python/pyspark/rdd.py +++ b/python/pyspark/rdd.py @@ -180,6 +180,10 @@ class RDD(object): def map(self, f, preservesPartitioning=False): """ Return a new RDD by applying a function to each element of this RDD. + + >>> rdd = sc.parallelize(["b", "a", "c"]) + >>> sorted(rdd.map(lambda x: (x, 1)).collect()) + [('a', 1), ('b', 1), ('c', 1)] """ def func(split, iterator): return imap(f, iterator) return PipelinedRDD(self, func, preservesPartitioning) -- cgit v1.2.3