aboutsummaryrefslogtreecommitdiff
path: root/graphx
diff options
context:
space:
mode:
authorAnkur Dave <ankurdave@gmail.com>2014-01-10 15:58:30 -0800
committerAnkur Dave <ankurdave@gmail.com>2014-01-10 15:58:30 -0800
commit04c20e7f4f98b18187f2320ddd7dedce69017de7 (patch)
treee71f226dcfcdd678ebca36144b1b9b9644f4d6c9 /graphx
parent1788729273261c8d9f6ec77b7fd15cab813338f8 (diff)
downloadspark-04c20e7f4f98b18187f2320ddd7dedce69017de7.tar.gz
spark-04c20e7f4f98b18187f2320ddd7dedce69017de7.tar.bz2
spark-04c20e7f4f98b18187f2320ddd7dedce69017de7.zip
Minor cleanup to docs
Diffstat (limited to 'graphx')
-rw-r--r--graphx/src/main/scala/org/apache/spark/graphx/Edge.scala2
-rw-r--r--graphx/src/main/scala/org/apache/spark/graphx/EdgeDirection.scala3
-rw-r--r--graphx/src/main/scala/org/apache/spark/graphx/GraphKryoRegistrator.scala4
-rw-r--r--graphx/src/main/scala/org/apache/spark/graphx/Pregel.scala32
-rw-r--r--graphx/src/main/scala/org/apache/spark/graphx/VertexRDD.scala2
5 files changed, 21 insertions, 22 deletions
diff --git a/graphx/src/main/scala/org/apache/spark/graphx/Edge.scala b/graphx/src/main/scala/org/apache/spark/graphx/Edge.scala
index 29b46674f1..c6b62ebaca 100644
--- a/graphx/src/main/scala/org/apache/spark/graphx/Edge.scala
+++ b/graphx/src/main/scala/org/apache/spark/graphx/Edge.scala
@@ -3,7 +3,7 @@ package org.apache.spark.graphx
/**
* A single directed edge consisting of a source id, target id,
- * and the data associated with the Edgee.
+ * and the data associated with the edge.
*
* @tparam ED type of the edge attribute
*/
diff --git a/graphx/src/main/scala/org/apache/spark/graphx/EdgeDirection.scala b/graphx/src/main/scala/org/apache/spark/graphx/EdgeDirection.scala
index 785f941650..99910ab87b 100644
--- a/graphx/src/main/scala/org/apache/spark/graphx/EdgeDirection.scala
+++ b/graphx/src/main/scala/org/apache/spark/graphx/EdgeDirection.scala
@@ -2,8 +2,7 @@ package org.apache.spark.graphx
/**
- * The direction of directed edge relative to a vertex used to select
- * the set of adjacent neighbors when running a neighborhood query.
+ * The direction of a directed edge relative to a vertex.
*/
sealed abstract class EdgeDirection {
/**
diff --git a/graphx/src/main/scala/org/apache/spark/graphx/GraphKryoRegistrator.scala b/graphx/src/main/scala/org/apache/spark/graphx/GraphKryoRegistrator.scala
index f8aab951f0..681074ba10 100644
--- a/graphx/src/main/scala/org/apache/spark/graphx/GraphKryoRegistrator.scala
+++ b/graphx/src/main/scala/org/apache/spark/graphx/GraphKryoRegistrator.scala
@@ -7,7 +7,9 @@ import org.apache.spark.serializer.KryoRegistrator
import org.apache.spark.util.collection.BitSet
import org.apache.spark.util.BoundedPriorityQueue
-
+/**
+ * Registers GraphX classes with Kryo for improved performance.
+ */
class GraphKryoRegistrator extends KryoRegistrator {
def registerClasses(kryo: Kryo) {
diff --git a/graphx/src/main/scala/org/apache/spark/graphx/Pregel.scala b/graphx/src/main/scala/org/apache/spark/graphx/Pregel.scala
index 0af230ed29..2e6453484c 100644
--- a/graphx/src/main/scala/org/apache/spark/graphx/Pregel.scala
+++ b/graphx/src/main/scala/org/apache/spark/graphx/Pregel.scala
@@ -4,26 +4,24 @@ import scala.reflect.ClassTag
/**
- * This object implements a Pregel-like bulk-synchronous
- * message-passing API. However, unlike the original Pregel API the
- * GraphX pregel API factors the sendMessage computation over edges,
- * enables the message sending computation to read both vertex
- * attributes, and finally constrains messages to the graph structure.
- * These changes allow for substantially more efficient distributed
- * execution while also exposing greater flexibility for graph based
- * computation.
+ * Implements a Pregel-like bulk-synchronous message-passing API.
*
- * @example We can use the Pregel abstraction to implement PageRank
+ * Unlike the original Pregel API, the GraphX Pregel API factors the sendMessage computation over
+ * edges, enables the message sending computation to read both vertex attributes, and constrains
+ * messages to the graph structure. These changes allow for substantially more efficient
+ * distributed execution while also exposing greater flexibility for graph-based computation.
+ *
+ * @example We can use the Pregel abstraction to implement PageRank:
* {{{
* val pagerankGraph: Graph[Double, Double] = graph
* // Associate the degree with each vertex
- * .outerJoinVertices(graph.outDegrees){
+ * .outerJoinVertices(graph.outDegrees) {
* (vid, vdata, deg) => deg.getOrElse(0)
* }
* // Set the weight on the edges based on the degree
- * .mapTriplets( e => 1.0 / e.srcAttr )
+ * .mapTriplets(e => 1.0 / e.srcAttr)
* // Set the vertex attributes to the initial pagerank values
- * .mapVertices( (id, attr) => 1.0 )
+ * .mapVertices((id, attr) => 1.0)
*
* def vertexProgram(id: VertexID, attr: Double, msgSum: Double): Double =
* resetProb + (1.0 - resetProb) * msgSum
@@ -31,7 +29,7 @@ import scala.reflect.ClassTag
* Some(edge.srcAttr * edge.attr)
* def messageCombiner(a: Double, b: Double): Double = a + b
* val initialMessage = 0.0
- * // Execute pregel for a fixed number of iterations.
+ * // Execute Pregel for a fixed number of iterations.
* Pregel(pagerankGraph, initialMessage, numIter)(
* vertexProgram, sendMessage, messageCombiner)
* }}}
@@ -54,7 +52,7 @@ object Pregel {
* then the vertex-program is not invoked.
*
* This function iterates until there are no remaining messages, or
- * for maxIterations iterations.
+ * for `maxIterations` iterations.
*
* @tparam VD the vertex data type
* @tparam ED the edge data type
@@ -63,9 +61,9 @@ object Pregel {
* @param graph the input graph.
*
* @param initialMsg the message each vertex will receive at the on
- * the first iteration.
+ * the first iteration
*
- * @param maxIterations the maximum number of iterations to run for.
+ * @param maxIterations the maximum number of iterations to run for
*
* @param vprog the user-defined vertex program which runs on each
* vertex and receives the inbound message and computes a new vertex
@@ -76,7 +74,7 @@ object Pregel {
*
* @param sendMsg a user supplied function that is applied to out
* edges of vertices that received messages in the current
- * iteration.
+ * iteration
*
* @param mergeMsg a user supplied function that takes two incoming
* messages of type A and merges them into a single message of type
diff --git a/graphx/src/main/scala/org/apache/spark/graphx/VertexRDD.scala b/graphx/src/main/scala/org/apache/spark/graphx/VertexRDD.scala
index 3ef9d6e9cf..3ef4fec405 100644
--- a/graphx/src/main/scala/org/apache/spark/graphx/VertexRDD.scala
+++ b/graphx/src/main/scala/org/apache/spark/graphx/VertexRDD.scala
@@ -28,7 +28,7 @@ import org.apache.spark.graphx.impl.MsgRDDFunctions
import org.apache.spark.graphx.impl.VertexPartition
/**
- * A `VertexRDD[VD]` extends the `RDD[(VertexID, VD)]` by ensuring that there is only one entry for
+ * `VertexRDD[VD]` extends the `RDD[(VertexID, VD)]` by ensuring that there is only one entry for
* each vertex and by pre-indexing the entries for fast, efficient joins. Two VertexRDDs with the
* same index can be joined efficiently.
*