From db6f67e73bdc96b65650ed9712474144c88d2a3d Mon Sep 17 00:00:00 2001 From: Prashant Sharma Date: Mon, 10 Mar 2014 12:54:21 +0530 Subject: [PATCH] SPARK-1168, Added foldByKey to pyspark. --- python/pyspark/rdd.py | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/python/pyspark/rdd.py b/python/pyspark/rdd.py index e72f57d9d1ab0..ecd0d0c753f9a 100644 --- a/python/pyspark/rdd.py +++ b/python/pyspark/rdd.py @@ -939,7 +939,21 @@ def _mergeCombiners(iterator): combiners[k] = mergeCombiners(combiners[k], v) return combiners.iteritems() return shuffled.mapPartitions(_mergeCombiners) + + def foldByKey(self, zeroValue, func, numPartitions=None): + """ + Merge the values for each key using an associative function "func" and a neutral "zeroValue" + which may be added to the result an arbitrary number of times, and must not change + the result (e.g., 0 for addition, or 1 for multiplication.). + >>> rdd = sc.parallelize([("a", 1), ("b", 1), ("a", 1)]) + >>> from operator import add + >>> rdd.foldByKey(0, add).collect() + [('a', 2), ('b', 1)] + """ + return self.combineByKey(lambda v: func(zeroValue, v), func, func, numPartitions) + + # TODO: support variant with custom partitioner def groupByKey(self, numPartitions=None): """