aboutsummaryrefslogtreecommitdiff
path: root/python/pyspark/rdd.py
diff options
context:
space:
mode:
authorJyotiska NK <jyotiska123@gmail.com>2014-03-19 14:04:45 -0700
committerMatei Zaharia <matei@databricks.com>2014-03-19 14:04:45 -0700
commit67fa71cba2cc07a65478899592e6ebad000e24c5 (patch)
treee1905d8e7cdd14bfa2575d4a3855985c8cc219ce /python/pyspark/rdd.py
parent79d07d66040f206708e14de393ab0b80020ed96a (diff)
downloadspark-67fa71cba2cc07a65478899592e6ebad000e24c5.tar.gz
spark-67fa71cba2cc07a65478899592e6ebad000e24c5.tar.bz2
spark-67fa71cba2cc07a65478899592e6ebad000e24c5.zip
Added doctest for map function in rdd.py
Doctest added for map in rdd.py Author: Jyotiska NK <jyotiska123@gmail.com> Closes #177 from jyotiska/pyspark_rdd_map_doctest and squashes the following commits: a38527f [Jyotiska NK] Added doctest for map function in rdd.py
Diffstat (limited to 'python/pyspark/rdd.py')
-rw-r--r--python/pyspark/rdd.py4
1 files changed, 4 insertions, 0 deletions
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)