Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/4622#discussion_r29738697
--- Diff:
mllib/src/main/scala/org/apache/spark/mllib/clustering/AffinityPropagation.scala
---
@@ -0,0 +1,475 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.mllib.clustering
+
+import scala.collection.mutable
+
+import org.apache.spark.{Logging, SparkException}
+import org.apache.spark.annotation.Experimental
+import org.apache.spark.api.java.JavaRDD
+import org.apache.spark.graphx._
+import org.apache.spark.graphx.impl.GraphImpl
+import org.apache.spark.rdd.RDD
+
+/**
+ * :: Experimental ::
+ *
+ * Model produced by [[AffinityPropagation]].
+ *
+ * @param id cluster id.
+ * @param exemplar cluster exemplar.
+ * @param members cluster members.
+ */
+@Experimental
+case class AffinityPropagationCluster(val id: Long, val exemplar: Long,
val members: Array[Long])
+
+/**
+ * :: Experimental ::
+ *
+ * Model produced by [[AffinityPropagation]].
+ *
+ * @param clusters the clusters of AffinityPropagation clustering results.
+ */
+@Experimental
+class AffinityPropagationModel(
+ val clusters: RDD[AffinityPropagationCluster]) extends Serializable {
+
+ /**
+ * Set the number of clusters
+ */
+ lazy val getK: Long = clusters.count()
+
+ /**
+ * Find the cluster the given vertex belongs
+ * @param vertexID vertex id.
+ * @return a [[Array]] that contains vertex ids in the same cluster of
given vertexID. If
+ * the given vertex doesn't belong to any cluster, return null.
+ */
+ def findCluster(vertexID: Long): Array[Long] = {
--- End diff --
I have the same concern @mengxr has. Can that particular cluster contains
lots of vertexes that run out of memory? This can return `RDD[Long]`, but with
data structure of `(vertex id, cluster id)`, it seems it requires two passes.
---
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]
