1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
|
package de.lmu.ifi.dbs.elki.algorithm.clustering.kmeans.quality;
/*
This file is part of ELKI:
Environment for Developing KDD-Applications Supported by Index-Structures
Copyright (C) 2015
Ludwig-Maximilians-Universität München
Lehr- und Forschungseinheit für Datenbanksysteme
ELKI Development Team
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU Affero General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU Affero General Public License for more details.
You should have received a copy of the GNU Affero General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
import static org.junit.Assert.assertEquals;
import org.junit.Test;
import de.lmu.ifi.dbs.elki.JUnit4Test;
import de.lmu.ifi.dbs.elki.algorithm.AbstractSimpleAlgorithmTest;
import de.lmu.ifi.dbs.elki.algorithm.clustering.kmeans.AbstractKMeans;
import de.lmu.ifi.dbs.elki.algorithm.clustering.kmeans.KMeans;
import de.lmu.ifi.dbs.elki.algorithm.clustering.kmeans.KMeansLloyd;
import de.lmu.ifi.dbs.elki.algorithm.clustering.kmeans.initialization.FirstKInitialMeans;
import de.lmu.ifi.dbs.elki.data.Clustering;
import de.lmu.ifi.dbs.elki.data.DoubleVector;
import de.lmu.ifi.dbs.elki.data.model.MeanModel;
import de.lmu.ifi.dbs.elki.data.type.TypeUtil;
import de.lmu.ifi.dbs.elki.database.Database;
import de.lmu.ifi.dbs.elki.database.relation.Relation;
import de.lmu.ifi.dbs.elki.distance.distancefunction.NumberVectorDistanceFunction;
import de.lmu.ifi.dbs.elki.utilities.ClassGenericsUtil;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.parameterization.ListParameterization;
/**
* Test cluster quality measure computations.
*
* @author Stephan Baier
* @since 0.6.0
*/
public class WithinClusterVarianceQualityMeasureTest extends AbstractSimpleAlgorithmTest implements JUnit4Test {
/**
* Test cluster variance.
*/
@Test
public void testVariance() {
Database db = makeSimpleDatabase(UNITTEST + "quality-measure-test.csv", 7);
Relation<DoubleVector> rel = db.getRelation(TypeUtil.DOUBLE_VECTOR_FIELD);
// Setup algorithm
ListParameterization params = new ListParameterization();
params = new ListParameterization();
params.addParameter(KMeans.K_ID, 2);
params.addParameter(KMeans.INIT_ID, FirstKInitialMeans.class);
AbstractKMeans<DoubleVector, ?> kmeans = ClassGenericsUtil.parameterizeOrAbort(KMeansLloyd.class, params);
testParameterizationOk(params);
// run KMeans on database
@SuppressWarnings("unchecked")
Clustering<MeanModel> result2 = (Clustering<MeanModel>) kmeans.run(db);
// Test Cluster Variance
KMeansQualityMeasure<? super DoubleVector> variance = new WithinClusterVarianceQualityMeasure();
final NumberVectorDistanceFunction<? super DoubleVector> dist = kmeans.getDistanceFunction();
final double quality = variance.quality(result2, dist, rel);
assertEquals("Within cluster variance incorrect", 3.16666666666, quality, 1e-10);
}
}
|
