ml/clustering/JavaKMeansSuite.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.ml.clustering;
0019
0020 import java.io.IOException;
0021 import java.util.Arrays;
0022 import java.util.List;
0023
0024 import org.junit.Test;
0025 import static org.junit.Assert.assertEquals;
0026 import static org.junit.Assert.assertTrue;
0027
0028 import org.apache.spark.SharedSparkSession;
0029 import org.apache.spark.ml.linalg.Vector;
0030 import org.apache.spark.sql.Dataset;
0031 import org.apache.spark.sql.Row;
0032
0033 public class JavaKMeansSuite extends SharedSparkSession {
0034
0035   private transient int k = 5;
0036   private transient Dataset<Row> dataset;
0037
0038   @Override
0039   public void setUp() throws IOException {
0040     super.setUp();
0041     dataset = KMeansSuite.generateKMeansData(spark, 50, 3, k);
0042   }
0043
0044   @Test
0045   public void fitAndTransform() {
0046     KMeans kmeans = new KMeans().setK(k).setSeed(1);
0047     KMeansModel model = kmeans.fit(dataset);
0048
0049     Vector[] centers = model.clusterCenters();
0050     assertEquals(k, centers.length);
0051
0052     Dataset<Row> transformed = model.transform(dataset);
0053     List<String> columns = Arrays.asList(transformed.columns());
0054     List<String> expectedColumns = Arrays.asList("features", "prediction");
0055     for (String column : expectedColumns) {
0056       assertTrue(columns.contains(column));
0057     }
0058   }
0059 }