aboutsummaryrefslogtreecommitdiff
path: root/python/pyspark
diff options
context:
space:
mode:
Diffstat (limited to 'python/pyspark')
-rw-r--r--python/pyspark/rdd.py2
1 files changed, 1 insertions, 1 deletions
diff --git a/python/pyspark/rdd.py b/python/pyspark/rdd.py
index 4aafe35d13..8734cacb0b 100644
--- a/python/pyspark/rdd.py
+++ b/python/pyspark/rdd.py
@@ -160,7 +160,7 @@ class RDD(object):
>>> sorted(sc.parallelize([1, 1, 2, 3]).distinct().collect())
[1, 2, 3]
"""
- return self.map(lambda x: (x, "")) \
+ return self.map(lambda x: (x, None)) \
.reduceByKey(lambda x, _: x) \
.map(lambda (x, _): x)