diff options
Diffstat (limited to 'examples/src/main/scala')
-rw-r--r-- | examples/src/main/scala/org/apache/spark/examples/ml/BisectingKMeansExample.scala | 65 |
1 files changed, 65 insertions, 0 deletions
diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/BisectingKMeansExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/BisectingKMeansExample.scala new file mode 100644 index 0000000000..5f8f2c99cb --- /dev/null +++ b/examples/src/main/scala/org/apache/spark/examples/ml/BisectingKMeansExample.scala @@ -0,0 +1,65 @@ +/* + * 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.examples.ml + +// scalastyle:off println + +// $example on$ +import org.apache.spark.ml.clustering.BisectingKMeans +// $example off$ +import org.apache.spark.sql.SparkSession + +/** + * An example demonstrating bisecting k-means clustering. + * Run with + * {{{ + * bin/run-example ml.BisectingKMeansExample + * }}} + */ +object BisectingKMeansExample { + + def main(args: Array[String]): Unit = { + // Creates a SparkSession + val spark = SparkSession + .builder + .appName("BisectingKMeansExample") + .getOrCreate() + + // $example on$ + // Loads data. + val dataset = spark.read.format("libsvm").load("data/mllib/sample_kmeans_data.txt") + + // Trains a bisecting k-means model. + val bkm = new BisectingKMeans().setK(2).setSeed(1) + val model = bkm.fit(dataset) + + // Evaluate clustering. + val cost = model.computeCost(dataset) + println(s"Within Set Sum of Squared Errors = $cost") + + // Shows the result. + println("Cluster Centers: ") + val centers = model.clusterCenters + centers.foreach(println) + // $example off$ + + spark.stop() + } +} +// scalastyle:on println + |