diff options
author | Michael Nazario <mnazario@palantir.com> | 2015-01-28 12:47:12 -0800 |
---|---|---|
committer | Josh Rosen <joshrosen@databricks.com> | 2015-01-28 12:47:12 -0800 |
commit | 456c11f15aec809044d8bdbdcce0ae05533fb44b (patch) | |
tree | fc9b57b8d87a4ebf30bda5dd0fda859e64ccf7ba /python | |
parent | 9b18009b835c784e9716594713f3d27d8e48d86c (diff) | |
download | spark-456c11f15aec809044d8bdbdcce0ae05533fb44b.tar.gz spark-456c11f15aec809044d8bdbdcce0ae05533fb44b.tar.bz2 spark-456c11f15aec809044d8bdbdcce0ae05533fb44b.zip |
[SPARK-5440][pyspark] Add toLocalIterator to pyspark rdd
Since Java and Scala both have access to iterate over partitions via the "toLocalIterator" function, python should also have that same ability.
Author: Michael Nazario <mnazario@palantir.com>
Closes #4237 from mnazario/feature/toLocalIterator and squashes the following commits:
1c58526 [Michael Nazario] Fix documentation off by one error
0cdc8f8 [Michael Nazario] Add toLocalIterator to PySpark
Diffstat (limited to 'python')
-rw-r--r-- | python/pyspark/rdd.py | 14 |
1 files changed, 14 insertions, 0 deletions
diff --git a/python/pyspark/rdd.py b/python/pyspark/rdd.py index efd2f35912..014c0aa889 100644 --- a/python/pyspark/rdd.py +++ b/python/pyspark/rdd.py @@ -2059,6 +2059,20 @@ class RDD(object): hashRDD = self.map(lambda x: portable_hash(x) & 0xFFFFFFFF) return hashRDD._to_java_object_rdd().countApproxDistinct(relativeSD) + def toLocalIterator(self): + """ + Return an iterator that contains all of the elements in this RDD. + The iterator will consume as much memory as the largest partition in this RDD. + >>> rdd = sc.parallelize(range(10)) + >>> [x for x in rdd.toLocalIterator()] + [0, 1, 2, 3, 4, 5, 6, 7, 8, 9] + """ + partitions = xrange(self.getNumPartitions()) + for partition in partitions: + rows = self.context.runJob(self, lambda x: x, [partition]) + for row in rows: + yield row + class PipelinedRDD(RDD): |