diff options
Diffstat (limited to 'python/pyspark/rdd.py')
| -rw-r--r-- | python/pyspark/rdd.py | 7 |
1 files changed, 3 insertions, 4 deletions
diff --git a/python/pyspark/rdd.py b/python/pyspark/rdd.py index fe2264a63c..4eaf589ad5 100644 --- a/python/pyspark/rdd.py +++ b/python/pyspark/rdd.py @@ -844,8 +844,7 @@ class RDD(object): def fold(self, zeroValue, op): """ Aggregate the elements of each partition, and then the results for all - the partitions, using a given associative and commutative function and - a neutral "zero value." + the partitions, using a given associative function and a neutral "zero value." The function C{op(t1, t2)} is allowed to modify C{t1} and return it as its result value to avoid object allocation; however, it should not @@ -1558,7 +1557,7 @@ class RDD(object): def reduceByKey(self, func, numPartitions=None, partitionFunc=portable_hash): """ - Merge the values for each key using an associative reduce function. + Merge the values for each key using an associative and commutative reduce function. This will also perform the merging locally on each mapper before sending results to a reducer, similarly to a "combiner" in MapReduce. @@ -1576,7 +1575,7 @@ class RDD(object): def reduceByKeyLocally(self, func): """ - Merge the values for each key using an associative reduce function, but + Merge the values for each key using an associative and commutative reduce function, but return the results immediately to the master as a dictionary. This will also perform the merging locally on each mapper before |