examples/ml/JavaGaussianMixtureExample.java

0001 /*
0002  * Licensed to the Apache Software Foundation (ASF) under one or more
0003  * contributor license agreements.  See the NOTICE file distributed with
0004  * this work for additional information regarding copyright ownership.
0005  * The ASF licenses this file to You under the Apache License, Version 2.0
0006  * (the "License"); you may not use this file except in compliance with
0007  * the License.  You may obtain a copy of the License at
0008  *
0009  *    http://www.apache.org/licenses/LICENSE-2.0
0010  *
0011  * Unless required by applicable law or agreed to in writing, software
0012  * distributed under the License is distributed on an "AS IS" BASIS,
0013  * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
0014  * See the License for the specific language governing permissions and
0015  * limitations under the License.
0016  */
0017
0018 package org.apache.spark.examples.ml;
0019
0020 // $example on$
0021 import org.apache.spark.ml.clustering.GaussianMixture;
0022 import org.apache.spark.ml.clustering.GaussianMixtureModel;
0023 import org.apache.spark.sql.Dataset;
0024 import org.apache.spark.sql.Row;
0025 // $example off$
0026 import org.apache.spark.sql.SparkSession;
0027
0028
0029 /**
0030  * An example demonstrating Gaussian Mixture Model.
0031  * Run with
0032  * <pre>
0033  * bin/run-example ml.JavaGaussianMixtureExample
0034  * </pre>
0035  */
0036 public class JavaGaussianMixtureExample {
0037
0038   public static void main(String[] args) {
0039
0040     // Creates a SparkSession
0041     SparkSession spark = SparkSession
0042             .builder()
0043             .appName("JavaGaussianMixtureExample")
0044             .getOrCreate();
0045
0046     // $example on$
0047     // Loads data
0048     Dataset<Row> dataset = spark.read().format("libsvm").load("data/mllib/sample_kmeans_data.txt");
0049
0050     // Trains a GaussianMixture model
0051     GaussianMixture gmm = new GaussianMixture()
0052       .setK(2);
0053     GaussianMixtureModel model = gmm.fit(dataset);
0054
0055     // Output the parameters of the mixture model
0056     for (int i = 0; i < model.getK(); i++) {
0057       System.out.printf("Gaussian %d:\nweight=%f\nmu=%s\nsigma=\n%s\n\n",
0058               i, model.weights()[i], model.gaussians()[i].mean(), model.gaussians()[i].cov());
0059     }
0060     // $example off$
0061
0062     spark.stop();
0063   }
0064 }