Commons Math example source code file (KMeansPlusPlusClustererTest.java)

This example Commons Math source code file (KMeansPlusPlusClustererTest.java) is included in the DevDaily.com "Java Source Code Warehouse" project. The intent of this project is to help you "Learn Java by Example" ^TM.

Java - Commons Math tags/keywords

cluster, euclideanintegerpoint, euclideanintegerpoint, kmeansplusplusclusterer, kmeansplusplusclusterer, kmeansplusplusclusterertest, list, random, random, test, test, util

The Commons Math KMeansPlusPlusClustererTest.java source code

/*
 * 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.commons.math.stat.clustering;

import static org.junit.Assert.assertEquals;
import static org.junit.Assert.assertTrue;

import java.util.Arrays;
import java.util.List;
import java.util.Random;

import org.junit.Test;

public class KMeansPlusPlusClustererTest {

    @Test
    public void dimension2() {
        KMeansPlusPlusClusterer<EuclideanIntegerPoint> transformer =
            new KMeansPlusPlusClusterer<EuclideanIntegerPoint>(new Random(1746432956321l));
        EuclideanIntegerPoint[] points = new EuclideanIntegerPoint[] {

                // first expected cluster
                new EuclideanIntegerPoint(new int[] { -15,  3 }),
                new EuclideanIntegerPoint(new int[] { -15,  4 }),
                new EuclideanIntegerPoint(new int[] { -15,  5 }),
                new EuclideanIntegerPoint(new int[] { -14,  3 }),
                new EuclideanIntegerPoint(new int[] { -14,  5 }),
                new EuclideanIntegerPoint(new int[] { -13,  3 }),
                new EuclideanIntegerPoint(new int[] { -13,  4 }),
                new EuclideanIntegerPoint(new int[] { -13,  5 }),

                // second expected cluster
                new EuclideanIntegerPoint(new int[] { -1,  0 }),
                new EuclideanIntegerPoint(new int[] { -1, -1 }),
                new EuclideanIntegerPoint(new int[] {  0, -1 }),
                new EuclideanIntegerPoint(new int[] {  1, -1 }),
                new EuclideanIntegerPoint(new int[] {  1, -2 }),

                // third expected cluster
                new EuclideanIntegerPoint(new int[] { 13,  3 }),
                new EuclideanIntegerPoint(new int[] { 13,  4 }),
                new EuclideanIntegerPoint(new int[] { 14,  4 }),
                new EuclideanIntegerPoint(new int[] { 14,  7 }),
                new EuclideanIntegerPoint(new int[] { 16,  5 }),
                new EuclideanIntegerPoint(new int[] { 16,  6 }),
                new EuclideanIntegerPoint(new int[] { 17,  4 }),
                new EuclideanIntegerPoint(new int[] { 17,  7 })

        };
        List<Cluster clusters =
            transformer.cluster(Arrays.asList(points), 3, 10);

        assertEquals(3, clusters.size());
        boolean cluster1Found = false;
        boolean cluster2Found = false;
        boolean cluster3Found = false;
        for (Cluster<EuclideanIntegerPoint> cluster : clusters) {
            int[] center = cluster.getCenter().getPoint();
            if (center[0] < 0) {
                cluster1Found = true;
                assertEquals(8, cluster.getPoints().size());
                assertEquals(-14, center[0]);
                assertEquals( 4, center[1]);
            } else if (center[1] < 0) {
                cluster2Found = true;
                assertEquals(5, cluster.getPoints().size());
                assertEquals( 0, center[0]);
                assertEquals(-1, center[1]);
            } else {
                cluster3Found = true;
                assertEquals(8, cluster.getPoints().size());
                assertEquals(15, center[0]);
                assertEquals(5, center[1]);
            }
        }
        assertTrue(cluster1Found);
        assertTrue(cluster2Found);
        assertTrue(cluster3Found);

    }

    /**
     * JIRA: MATH-305
     *
     * Two points, one cluster, one iteration
     */
    @Test
    public void testPerformClusterAnalysisDegenerate() {
        KMeansPlusPlusClusterer<EuclideanIntegerPoint> transformer = new KMeansPlusPlusClusterer(
                new Random(1746432956321l));
        EuclideanIntegerPoint[] points = new EuclideanIntegerPoint[] {
                new EuclideanIntegerPoint(new int[] { 1959, 325100 }),
                new EuclideanIntegerPoint(new int[] { 1960, 373200 }), };
        List<Cluster clusters = transformer.cluster(Arrays.asList(points), 1, 1);
        assertEquals(1, clusters.size());
        assertEquals(2, (clusters.get(0).getPoints().size()));
        EuclideanIntegerPoint pt1 = new EuclideanIntegerPoint(new int[] { 1959, 325100 });
        EuclideanIntegerPoint pt2 = new EuclideanIntegerPoint(new int[] { 1960, 373200 });
        assertTrue(clusters.get(0).getPoints().contains(pt1));
        assertTrue(clusters.get(0).getPoints().contains(pt2));

    }

}