Repository: spark Updated Branches: refs/heads/master 7d10631c1 -> ea3605e82
[MINOR][ML] Refactor clustering summary. ## What changes were proposed in this pull request? Abstract ```ClusteringSummary``` from ```KMeansSummary```, ```GaussianMixtureSummary``` and ```BisectingSummary```, and eliminate duplicated pieces of code. ## How was this patch tested? Existing tests. Author: Yanbo Liang <yblia...@gmail.com> Closes #15555 from yanboliang/clustering-summary. Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/ea3605e8 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/ea3605e8 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/ea3605e8 Branch: refs/heads/master Commit: ea3605e82545031a00235ee0f449e1e2418674e8 Parents: 7d10631 Author: Yanbo Liang <yblia...@gmail.com> Authored: Wed Oct 26 11:48:54 2016 -0700 Committer: Joseph K. Bradley <jos...@databricks.com> Committed: Wed Oct 26 11:48:54 2016 -0700 ---------------------------------------------------------------------- .../spark/ml/clustering/BisectingKMeans.scala | 36 +++---------- .../spark/ml/clustering/ClusteringSummary.scala | 54 ++++++++++++++++++++ .../spark/ml/clustering/GaussianMixture.scala | 37 ++++---------- .../org/apache/spark/ml/clustering/KMeans.scala | 36 +++---------- 4 files changed, 80 insertions(+), 83 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/ea3605e8/mllib/src/main/scala/org/apache/spark/ml/clustering/BisectingKMeans.scala ---------------------------------------------------------------------- diff --git a/mllib/src/main/scala/org/apache/spark/ml/clustering/BisectingKMeans.scala b/mllib/src/main/scala/org/apache/spark/ml/clustering/BisectingKMeans.scala index ef2d918..2718dd9 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/clustering/BisectingKMeans.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/clustering/BisectingKMeans.scala @@ -288,35 +288,15 @@ object BisectingKMeans extends DefaultParamsReadable[BisectingKMeans] { * :: Experimental :: * Summary of BisectingKMeans. * - * @param predictions [[DataFrame]] produced by [[BisectingKMeansModel.transform()]] - * @param predictionCol Name for column of predicted clusters in `predictions` - * @param featuresCol Name for column of features in `predictions` - * @param k Number of clusters + * @param predictions [[DataFrame]] produced by [[BisectingKMeansModel.transform()]]. + * @param predictionCol Name for column of predicted clusters in `predictions`. + * @param featuresCol Name for column of features in `predictions`. + * @param k Number of clusters. */ @Since("2.1.0") @Experimental class BisectingKMeansSummary private[clustering] ( - @Since("2.1.0") @transient val predictions: DataFrame, - @Since("2.1.0") val predictionCol: String, - @Since("2.1.0") val featuresCol: String, - @Since("2.1.0") val k: Int) extends Serializable { - - /** - * Cluster centers of the transformed data. - */ - @Since("2.1.0") - @transient lazy val cluster: DataFrame = predictions.select(predictionCol) - - /** - * Size of (number of data points in) each cluster. - */ - @Since("2.1.0") - lazy val clusterSizes: Array[Long] = { - val sizes = Array.fill[Long](k)(0) - cluster.groupBy(predictionCol).count().select(predictionCol, "count").collect().foreach { - case Row(cluster: Int, count: Long) => sizes(cluster) = count - } - sizes - } - -} + predictions: DataFrame, + predictionCol: String, + featuresCol: String, + k: Int) extends ClusteringSummary(predictions, predictionCol, featuresCol, k) http://git-wip-us.apache.org/repos/asf/spark/blob/ea3605e8/mllib/src/main/scala/org/apache/spark/ml/clustering/ClusteringSummary.scala ---------------------------------------------------------------------- diff --git a/mllib/src/main/scala/org/apache/spark/ml/clustering/ClusteringSummary.scala b/mllib/src/main/scala/org/apache/spark/ml/clustering/ClusteringSummary.scala new file mode 100644 index 0000000..8b5f525 --- /dev/null +++ b/mllib/src/main/scala/org/apache/spark/ml/clustering/ClusteringSummary.scala @@ -0,0 +1,54 @@ +/* + * 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.ml.clustering + +import org.apache.spark.annotation.Experimental +import org.apache.spark.sql.{DataFrame, Row} + +/** + * :: Experimental :: + * Summary of clustering algorithms. + * + * @param predictions [[DataFrame]] produced by model.transform(). + * @param predictionCol Name for column of predicted clusters in `predictions`. + * @param featuresCol Name for column of features in `predictions`. + * @param k Number of clusters. + */ +@Experimental +class ClusteringSummary private[clustering] ( + @transient val predictions: DataFrame, + val predictionCol: String, + val featuresCol: String, + val k: Int) extends Serializable { + + /** + * Cluster centers of the transformed data. + */ + @transient lazy val cluster: DataFrame = predictions.select(predictionCol) + + /** + * Size of (number of data points in) each cluster. + */ + lazy val clusterSizes: Array[Long] = { + val sizes = Array.fill[Long](k)(0) + cluster.groupBy(predictionCol).count().select(predictionCol, "count").collect().foreach { + case Row(cluster: Int, count: Long) => sizes(cluster) = count + } + sizes + } +} http://git-wip-us.apache.org/repos/asf/spark/blob/ea3605e8/mllib/src/main/scala/org/apache/spark/ml/clustering/GaussianMixture.scala ---------------------------------------------------------------------- diff --git a/mllib/src/main/scala/org/apache/spark/ml/clustering/GaussianMixture.scala b/mllib/src/main/scala/org/apache/spark/ml/clustering/GaussianMixture.scala index 69f060a..e3cb92f 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/clustering/GaussianMixture.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/clustering/GaussianMixture.scala @@ -356,42 +356,25 @@ object GaussianMixture extends DefaultParamsReadable[GaussianMixture] { * :: Experimental :: * Summary of GaussianMixture. * - * @param predictions [[DataFrame]] produced by [[GaussianMixtureModel.transform()]] - * @param predictionCol Name for column of predicted clusters in `predictions` - * @param probabilityCol Name for column of predicted probability of each cluster in `predictions` - * @param featuresCol Name for column of features in `predictions` - * @param k Number of clusters + * @param predictions [[DataFrame]] produced by [[GaussianMixtureModel.transform()]]. + * @param predictionCol Name for column of predicted clusters in `predictions`. + * @param probabilityCol Name for column of predicted probability of each cluster + * in `predictions`. + * @param featuresCol Name for column of features in `predictions`. + * @param k Number of clusters. */ @Since("2.0.0") @Experimental class GaussianMixtureSummary private[clustering] ( - @Since("2.0.0") @transient val predictions: DataFrame, - @Since("2.0.0") val predictionCol: String, + predictions: DataFrame, + predictionCol: String, @Since("2.0.0") val probabilityCol: String, - @Since("2.0.0") val featuresCol: String, - @Since("2.0.0") val k: Int) extends Serializable { - - /** - * Cluster centers of the transformed data. - */ - @Since("2.0.0") - @transient lazy val cluster: DataFrame = predictions.select(predictionCol) + featuresCol: String, + k: Int) extends ClusteringSummary(predictions, predictionCol, featuresCol, k) { /** * Probability of each cluster. */ @Since("2.0.0") @transient lazy val probability: DataFrame = predictions.select(probabilityCol) - - /** - * Size of (number of data points in) each cluster. - */ - @Since("2.0.0") - lazy val clusterSizes: Array[Long] = { - val sizes = Array.fill[Long](k)(0) - cluster.groupBy(predictionCol).count().select(predictionCol, "count").collect().foreach { - case Row(cluster: Int, count: Long) => sizes(cluster) = count - } - sizes - } } http://git-wip-us.apache.org/repos/asf/spark/blob/ea3605e8/mllib/src/main/scala/org/apache/spark/ml/clustering/KMeans.scala ---------------------------------------------------------------------- diff --git a/mllib/src/main/scala/org/apache/spark/ml/clustering/KMeans.scala b/mllib/src/main/scala/org/apache/spark/ml/clustering/KMeans.scala index 0d2405b..05ed322 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/clustering/KMeans.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/clustering/KMeans.scala @@ -346,35 +346,15 @@ object KMeans extends DefaultParamsReadable[KMeans] { * :: Experimental :: * Summary of KMeans. * - * @param predictions [[DataFrame]] produced by [[KMeansModel.transform()]] - * @param predictionCol Name for column of predicted clusters in `predictions` - * @param featuresCol Name for column of features in `predictions` - * @param k Number of clusters + * @param predictions [[DataFrame]] produced by [[KMeansModel.transform()]]. + * @param predictionCol Name for column of predicted clusters in `predictions`. + * @param featuresCol Name for column of features in `predictions`. + * @param k Number of clusters. */ @Since("2.0.0") @Experimental class KMeansSummary private[clustering] ( - @Since("2.0.0") @transient val predictions: DataFrame, - @Since("2.0.0") val predictionCol: String, - @Since("2.0.0") val featuresCol: String, - @Since("2.0.0") val k: Int) extends Serializable { - - /** - * Cluster centers of the transformed data. - */ - @Since("2.0.0") - @transient lazy val cluster: DataFrame = predictions.select(predictionCol) - - /** - * Size of (number of data points in) each cluster. - */ - @Since("2.0.0") - lazy val clusterSizes: Array[Long] = { - val sizes = Array.fill[Long](k)(0) - cluster.groupBy(predictionCol).count().select(predictionCol, "count").collect().foreach { - case Row(cluster: Int, count: Long) => sizes(cluster) = count - } - sizes - } - -} + predictions: DataFrame, + predictionCol: String, + featuresCol: String, + k: Int) extends ClusteringSummary(predictions, predictionCol, featuresCol, k) --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org