Improve combineByKey docs

David Gingrich · David Gingrich · commit 74691d121aea · 2017-04-05T12:47:39.000-07:00
* Add note on memory allocation
* Change example code to use different mergeValue and mergeCombiners
diff --git a/python/pyspark/rdd.py b/python/pyspark/rdd.py
@@ -1804,17 +1804,31 @@ def combineByKey(self, createCombiner, mergeValue, mergeCombiners,
               a one-element list)
             - C{mergeValue}, to merge a V into a C (e.g., adds it to the end of
               a list)
-            - C{mergeCombiners}, to combine two C's into a single one.
+            - C{mergeCombiners}, to combine two C's into a single one (e.g., merges
+              the lists)
+
+        To avoid memory allocation, both mergeValue and mergeCombiners are allowed to
+        modify and return their first argument instead of creating a new C.
 
         In addition, users can control the partitioning of the output RDD.
 
         .. note:: V and C can be different -- for example, one might group an RDD of type
             (Int, Int) into an RDD of type (Int, List[Int]).
 
-        >>> x = sc.parallelize([("a", 1), ("b", 1), ("a", 1)])
-        >>> def add(a, b): return a + str(b)
-        >>> sorted(x.combineByKey(str, add, add).collect())
-        [('a', '11'), ('b', '1')]
+        >>> x = sc.parallelize([("a", 1), ("b", 1), ("a", 2)])
+        >>> def to_list(a):
+        ...     return [a]
+        ...
+        >>> def append(a, b):
+        ...     a.append(b)
+        ...     return a
+        ...
+        >>> def extend(a, b):
+        ...     a.extend(b)
+        ...     return a
+        ...
+        >>> sorted(x.combineByKey(to_list, append, extend).collect())
+        [('a', [1, 2]), ('b', [1])]
         """
         if numPartitions is None:
             numPartitions = self._defaultReducePartitions()
