You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@spark.apache.org by sr...@apache.org on 2016/01/12 14:20:15 UTC
spark git commit: [SPARK-12638][API DOC] Parameter explanation not
very accurate for rdd function "aggregate"
Repository: spark
Updated Branches:
refs/heads/master 9c7f34af3 -> 9f0995bb0
[SPARK-12638][API DOC] Parameter explanation not very accurate for rdd function "aggregate"
Currently, RDD function aggregate's parameter doesn't explain well, especially parameter "zeroValue".
It's helpful to let junior scala user know that "zeroValue" attend both "seqOp" and "combOp" phase.
Author: Tommy YU <tu...@163.com>
Closes #10587 from Wenpei/rdd_aggregate_doc.
Project: http://git-wip-us.apache.org/repos/asf/spark/repo
Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/9f0995bb
Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/9f0995bb
Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/9f0995bb
Branch: refs/heads/master
Commit: 9f0995bb0d0bbe5d9b15a1ca9fa18e246ff90d66
Parents: 9c7f34a
Author: Tommy YU <tu...@163.com>
Authored: Tue Jan 12 13:20:04 2016 +0000
Committer: Sean Owen <so...@cloudera.com>
Committed: Tue Jan 12 13:20:04 2016 +0000
----------------------------------------------------------------------
core/src/main/scala/org/apache/spark/rdd/RDD.scala | 14 ++++++++++++++
1 file changed, 14 insertions(+)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/spark/blob/9f0995bb/core/src/main/scala/org/apache/spark/rdd/RDD.scala
----------------------------------------------------------------------
diff --git a/core/src/main/scala/org/apache/spark/rdd/RDD.scala b/core/src/main/scala/org/apache/spark/rdd/RDD.scala
index de7102f..53e01a0 100644
--- a/core/src/main/scala/org/apache/spark/rdd/RDD.scala
+++ b/core/src/main/scala/org/apache/spark/rdd/RDD.scala
@@ -970,6 +970,13 @@ abstract class RDD[T: ClassTag](
* apply the fold to each element sequentially in some defined ordering. For functions
* that are not commutative, the result may differ from that of a fold applied to a
* non-distributed collection.
+ *
+ * @param zeroValue the initial value for the accumulated result of each partition for the `op`
+ * operator, and also the initial value for the combine results from different
+ * partitions for the `op` operator - this will typically be the neutral
+ * element (e.g. `Nil` for list concatenation or `0` for summation)
+ * @param op an operator used to both accumulate results within a partition and combine results
+ * from different partitions
*/
def fold(zeroValue: T)(op: (T, T) => T): T = withScope {
// Clone the zero value since we will also be serializing it as part of tasks
@@ -988,6 +995,13 @@ abstract class RDD[T: ClassTag](
* and one operation for merging two U's, as in scala.TraversableOnce. Both of these functions are
* allowed to modify and return their first argument instead of creating a new U to avoid memory
* allocation.
+ *
+ * @param zeroValue the initial value for the accumulated result of each partition for the
+ * `seqOp` operator, and also the initial value for the combine results from
+ * different partitions for the `combOp` operator - this will typically be the
+ * neutral element (e.g. `Nil` for list concatenation or `0` for summation)
+ * @param seqOp an operator used to accumulate results within a partition
+ * @param combOp an associative operator used to combine results from different partitions
*/
def aggregate[U: ClassTag](zeroValue: U)(seqOp: (U, T) => U, combOp: (U, U) => U): U = withScope {
// Clone the zero value since we will also be serializing it as part of tasks
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org