-
Notifications
You must be signed in to change notification settings - Fork 28.3k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Move ClusteringSummary to a separate file.
- Loading branch information
1 parent
f13f240
commit 946ee73
Showing
3 changed files
with
55 additions
and
35 deletions.
There are no files selected for viewing
54 changes: 54 additions & 0 deletions
54
mllib/src/main/scala/org/apache/spark/ml/clustering/ClusteringSummary.scala
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -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 | ||
} | ||
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters