From 934a53c8b677df524315a75011b4c9396eb4b54e Mon Sep 17 00:00:00 2001
From: Mark Hamstra <markhamstra@gmail.com>
Date: Tue, 5 Feb 2013 22:19:58 -0800
Subject: [PATCH] Change docs on 'reduce' since the merging of local reduces no
longer preserves ordering, so the reduce function must also be commutative.
---
core/src/main/scala/spark/RDD.scala | 2 +-
core/src/main/scala/spark/api/java/JavaRDDLike.scala | 2 +-
docs/scala-programming-guide.md | 2 +-
3 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/core/src/main/scala/spark/RDD.scala b/core/src/main/scala/spark/RDD.scala
index d15c6f7396..3ad3b4d233 100644
--- a/core/src/main/scala/spark/RDD.scala
+++ b/core/src/main/scala/spark/RDD.scala
@@ -330,7 +330,7 @@ abstract class RDD[T: ClassManifest](@transient sc: SparkContext) extends Serial
def toArray(): Array[T] = collect()
/**
- * Reduces the elements of this RDD using the specified associative binary operator.
+ * Reduces the elements of this RDD using the specified commutative and associative binary operator.
*/
def reduce(f: (T, T) => T): T = {
val cleanF = sc.clean(f)
diff --git a/core/src/main/scala/spark/api/java/JavaRDDLike.scala b/core/src/main/scala/spark/api/java/JavaRDDLike.scala
index 81d3a94466..6da89f518f 100644
--- a/core/src/main/scala/spark/api/java/JavaRDDLike.scala
+++ b/core/src/main/scala/spark/api/java/JavaRDDLike.scala
@@ -201,7 +201,7 @@ trait JavaRDDLike[T, This <: JavaRDDLike[T, This]] extends Serializable {
}
/**
- * Reduces the elements of this RDD using the specified associative binary operator.
+ * Reduces the elements of this RDD using the specified commutative and associative binary operator.
*/
def reduce(f: JFunction2[T, T, T]): T = rdd.reduce(f)
diff --git a/docs/scala-programming-guide.md b/docs/scala-programming-guide.md
index 7350eca837..95de4f50bb 100644
--- a/docs/scala-programming-guide.md
+++ b/docs/scala-programming-guide.md
@@ -203,7 +203,7 @@ A complete list of transformations is available in the [RDD API doc](api/core/in
<tr><th>Action</th><th>Meaning</th></tr>
<tr>
<td> <b>reduce</b>(<i>func</i>) </td>
- <td> Aggregate the elements of the dataset using a function <i>func</i> (which takes two arguments and returns one). The function should be associative so that it can be computed correctly in parallel. </td>
+ <td> Aggregate the elements of the dataset using a function <i>func</i> (which takes two arguments and returns one). The function should be commutative and associative so that it can be computed correctly in parallel. </td>
</tr>
<tr>
<td> <b>collect</b>() </td>
--
GitLab