mllib/clustering/JavaGaussianMixtureSuite.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.mllib.clustering;
0019
0020 import java.util.Arrays;
0021 import java.util.List;
0022
0023 import static org.junit.Assert.assertEquals;
0024
0025 import org.junit.Test;
0026
0027 import org.apache.spark.SharedSparkSession;
0028 import org.apache.spark.api.java.JavaRDD;
0029 import org.apache.spark.mllib.linalg.Vector;
0030 import org.apache.spark.mllib.linalg.Vectors;
0031
0032 public class JavaGaussianMixtureSuite extends SharedSparkSession {
0033
0034   @Test
0035   public void runGaussianMixture() {
0036     List<Vector> points = Arrays.asList(
0037       Vectors.dense(1.0, 2.0, 6.0),
0038       Vectors.dense(1.0, 3.0, 0.0),
0039       Vectors.dense(1.0, 4.0, 6.0)
0040     );
0041
0042     JavaRDD<Vector> data = jsc.parallelize(points, 2);
0043     GaussianMixtureModel model = new GaussianMixture().setK(2).setMaxIterations(1).setSeed(1234)
0044       .run(data);
0045     assertEquals(2, model.gaussians().length);
0046     JavaRDD<Integer> predictions = model.predict(data);
0047     predictions.first();
0048   }
0049 }