Github user yu-iskw commented on a diff in the pull request: https://github.com/apache/spark/pull/2906#discussion_r19396796 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/clustering/HierarchicalClustering.scala --- @@ -0,0 +1,549 @@ +/* + * 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, 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 + +/** + * the configuration for a hierarchical clustering algorithm + * + * @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 HierarchicalClusteringConf( + private var numClusters: Int, + private var subIterations: Int, + private var numRetries: Int, + private var epsilon: Double, + private var randomSeed: Int, + private[mllib] var randomRange: Double) extends Serializable { + + def this() = this(20, 5, 20, 10E-6, 1, 0.1) + + def setNumClusters(numClusters: Int): this.type = { --- End diff -- I changed `HierarchicalClusteringConf` class to a trait for `HierarchicalClustering`. And the class parameters were moved to `HierarchicalClustering` such as `numClusters`. I think if the accessor methods for the algorithm is included `HierarchicalClustering`, it gets larger. So I delegated the methods to the trait class. https://github.com/yu-iskw/spark/commit/2879b00c39880a4ffc29cefaaffde26df655e63f
--- 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 infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org