aboutsummaryrefslogtreecommitdiff
path: root/python/pyspark/rdd.py
diff options
context:
space:
mode:
authorMatthew Farrellee <matt@redhat.com>2014-09-16 11:39:57 -0700
committerJosh Rosen <joshrosen@apache.org>2014-09-16 11:39:57 -0700
commit9d5fa763d8559ac412a18d7a2f43c4368a0af897 (patch)
treee42e70e02055cedbce87e5ab7889743700c57ef4 /python/pyspark/rdd.py
parent86d253ec4e2ed94c68687d575f9e2dfbb44463e1 (diff)
downloadspark-9d5fa763d8559ac412a18d7a2f43c4368a0af897.tar.gz
spark-9d5fa763d8559ac412a18d7a2f43c4368a0af897.tar.bz2
spark-9d5fa763d8559ac412a18d7a2f43c4368a0af897.zip
[SPARK-3519] add distinct(n) to PySpark
Added missing rdd.distinct(numPartitions) and associated tests Author: Matthew Farrellee <matt@redhat.com> Closes #2383 from mattf/SPARK-3519 and squashes the following commits: 30b837a [Matthew Farrellee] Combine test cases to save on JVM startups 6bc4a2c [Matthew Farrellee] [SPARK-3519] add distinct(n) to SchemaRDD in PySpark 7a17f2b [Matthew Farrellee] [SPARK-3519] add distinct(n) to PySpark
Diffstat (limited to 'python/pyspark/rdd.py')
-rw-r--r--python/pyspark/rdd.py4
1 files changed, 2 insertions, 2 deletions
diff --git a/python/pyspark/rdd.py b/python/pyspark/rdd.py
index 21f182b0ff..cb09c191be 100644
--- a/python/pyspark/rdd.py
+++ b/python/pyspark/rdd.py
@@ -301,7 +301,7 @@ class RDD(object):
return ifilter(f, iterator)
return self.mapPartitions(func, True)
- def distinct(self):
+ def distinct(self, numPartitions=None):
"""
Return a new RDD containing the distinct elements in this RDD.
@@ -309,7 +309,7 @@ class RDD(object):
[1, 2, 3]
"""
return self.map(lambda x: (x, None)) \
- .reduceByKey(lambda x, _: x) \
+ .reduceByKey(lambda x, _: x, numPartitions) \
.map(lambda (x, _): x)
def sample(self, withReplacement, fraction, seed=None):