Github user mateiz commented on a diff in the pull request:
https://github.com/apache/spark/pull/1791#discussion_r16267032
--- Diff: python/pyspark/rdd.py ---
@@ -1685,11 +1813,69 @@ def zip(self, other):
>>> x.zip(y).collect()
[(0, 1000), (1, 1001), (2, 1002), (3, 1003), (4, 1004)]
"""
+ if self.getNumPartitions() != other.getNumPartitions():
+ raise ValueError("the number of partitions dose not match"
+ " with each other")
+
pairRDD = self._jrdd.zip(other._jrdd)
deserializer = PairDeserializer(self._jrdd_deserializer,
other._jrdd_deserializer)
return RDD(pairRDD, self.ctx, deserializer)
+ # TODO
+ # def zipPartitions(self, other, f, preservesPartitioning=False):
+ # """
+ # Zip this RDD's partitions with one (or more) RDD(s) and return a
+ # new RDD by applying a function to the zipped partitions.
+ # """
+
+ def zipWithIndex(self):
+ """
+ Zips this RDD with its element indices.
+
+ The ordering is first based on the partition index and then the
+ ordering of items within each partition. So the first item in
+ the first partition gets index 0, and the last item in the last
+ partition receives the largest index.
+
+ This method needs to trigger a spark job when this RDD contains
+ more than one partitions.
+
+ >>> sc.parallelize(range(4), 2).zipWithIndex().collect()
+ [(0, 0), (1, 1), (2, 2), (3, 3)]
+ """
+ starts = [0]
+ if self.getNumPartitions() > 1:
+ nums = self.glom().map(lambda it: sum(1 for i in it)).collect()
--- End diff --
glom() actually puts all the elements in a list, so it can get out of
memory errors and such. Instead, use mapPartitions to count the values, similar
to RDD.count().
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
