From a59419c27e45f06be5143c58d48affb0a5158bdf Mon Sep 17 00:00:00 2001 From: Prashant Sharma Date: Mon, 10 Mar 2014 13:37:11 -0700 Subject: SPARK-1168, Added foldByKey to pyspark. Author: Prashant Sharma Closes #115 from ScrapCodes/SPARK-1168/pyspark-foldByKey and squashes the following commits: db6f67e [Prashant Sharma] SPARK-1168, Added foldByKey to pyspark. --- python/pyspark/rdd.py | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'python/pyspark/rdd.py') diff --git a/python/pyspark/rdd.py b/python/pyspark/rdd.py index e1043ad564..39916d21c7 100644 --- a/python/pyspark/rdd.py +++ b/python/pyspark/rdd.py @@ -946,7 +946,21 @@ class RDD(object): 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): """ -- cgit v1.2.3