Github user mengxr commented on a diff in the pull request:
https://github.com/apache/spark/pull/6054#discussion_r35280635
--- Diff:
mllib/src/main/scala/org/apache/spark/mllib/clustering/PowerIterationClustering.scala
---
@@ -213,6 +234,29 @@ object PowerIterationClustering extends Logging {
case class Assignment(id: Long, cluster: Int)
/**
+ * Normalizes the affinity graph (A) and returns the normalized affinity
matrix (W).
+ */
+ private[clustering]
+ def normalize(graph: Graph[Double, Double]): Graph[Double, Double] = {
+ val vD = graph.aggregateMessages[Double](
+ sendMsg = ctx => {
+ val i = ctx.srcId
+ val j = ctx.dstId
+ val s = ctx.attr
+ if (s < 0.0) {
+ throw new SparkException("Similarity must be nonnegative but
found s($i, $j) = $s.")
+ }
+ ctx.sendToSrc(s)
--- End diff --
We allow explicit zero similarities from input. But zero edges could be
filtered out at this stage.
---
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]
