diff --git a/python/pyspark/rdd.py b/python/pyspark/rdd.py index e1043ad56461149b5acf770f45c3335739b03434..39916d21c76c552e8b982f933d4961b601d7c3f7 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): """