Github user freeman-lab commented on a diff in the pull request:
https://github.com/apache/spark/pull/2906#discussion_r22632654
--- Diff:
mllib/src/main/scala/org/apache/spark/mllib/clustering/HierarchicalClustering.scala
---
@@ -0,0 +1,627 @@
+/*
+ * 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 breeze.linalg.{DenseVector => BDV, SparseVector => BSV, Vector =>
BV, norm => breezeNorm}
+import org.apache.spark.Logging
+import org.apache.spark.SparkContext._
+import org.apache.spark.mllib.linalg.{Vector, Vectors}
+import org.apache.spark.rdd.RDD
+import org.apache.spark.util.random.XORShiftRandom
+
+/**
+ * This trait is used for the configuration of the hierarchical clustering
+ */
+sealed
+trait HierarchicalClusteringConf extends Serializable {
+ this: HierarchicalClustering =>
+
+ def setNumClusters(numClusters: Int): this.type = {
+ this.numClusters = numClusters
+ this
+ }
+
+ def getNumClusters(): Int = this.numClusters
+
+ def setNumRetries(numRetries: Int): this.type = {
+ this.numRetries = numRetries
+ this
+ }
+
+ def getNumRetries(): Int = this.numRetries
+
+ def setSubIterations(subIterations: Int): this.type = {
+ this.subIterations = subIterations
+ this
+ }
+
+ def getSubIterations(): Int = this.subIterations
+
+ def setEpsilon(epsilon: Double): this.type = {
+ this.epsilon = epsilon
+ this
+ }
+
+ def getEpsilon(): Double = this.epsilon
+
+ def setRandomSeed(seed: Int): this.type = {
+ this.randomSeed = seed
+ this
+ }
+
+ def getRandomSeed(): Int = this.randomSeed
+
+ def setRandomRange(range: Double): this.type = {
+ this.randomRange = range
+ this
+ }
+}
+
+
+/**
+ * This is a divisive hierarchical clustering algorithm based on bi-sect
k-means algorithm.
+ *
+ * The main idea of this algorithm is derived from:
+ * "A comparison of document clustering techniques",
+ * M. Steinbach, G. Karypis and V. Kumar. Workshop on Text Mining, KDD,
2000.
+ * http://cs.fit.edu/~pkc/classes/ml-internet/papers/steinbach00tr.pdf
+ *
+ * @param numClusters the number of clusters you want
+ * @param subIterations the number of iterations at digging
+ * @param epsilon the threshold to stop the sub-iterations
+ * @param randomSeed uses in sampling data for initializing centers in
each sub iterations
+ * @param randomRange the range coefficient to generate random points in
each clustering step
+ */
+class HierarchicalClustering(
+ private[mllib] var numClusters: Int,
+ private[mllib] var subIterations: Int,
+ private[mllib] var numRetries: Int,
+ private[mllib] var epsilon: Double,
+ private[mllib] var randomSeed: Int,
+ private[mllib] var randomRange: Double)
+ extends Serializable with Logging with HierarchicalClusteringConf {
--- End diff --
Indent by 2 spaces.
---
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]
