Github user mengxr commented on a diff in the pull request:
https://github.com/apache/spark/pull/2634#discussion_r18488331
--- Diff:
mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeansPlusPlus.scala ---
@@ -0,0 +1,200 @@
+/*
+ * 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 org.apache.spark.mllib.base.{PointOps, FP, Infinity, One, Zero}
+import org.apache.spark.util.random.XORShiftRandom
+import org.apache.spark.{Logging, SparkContext}
+
+import scala.collection.mutable.ArrayBuffer
+import scala.reflect.ClassTag
+
+/**
+ *
+ * The KMeans++ initialization algorithm
+ *
+ * @param pointOps distance function
+ * @tparam P point type
+ * @tparam C center type
+ */
+private[mllib] class KMeansPlusPlus[P <: FP : ClassTag, C <: FP :
ClassTag](
+ pointOps: PointOps[P, C]) extends Serializable with Logging {
+
+ /**
+ * We will maintain for each point the distance to its closest cluster
center.
+ * Since only one center is added on each iteration, recomputing the
closest cluster center
+ * only requires computing the distance to the new cluster center if
+ * that distance is less than the closest cluster center.
+ */
+ case class FatPoint(location: P, index: Int, weight: Double, distance:
Double)
+
+ /**
+ * K-means++ on the weighted point set `points`. This first does the
K-means++
+ * initialization procedure and then rounds of Lloyd's algorithm.
+ */
+
+ def cluster(
+ sc: SparkContext,
--- End diff --
4-space indentation
---
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]
