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
|
package de.lmu.ifi.dbs.elki.algorithm.clustering.em;
/*
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 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.KMeans;
import de.lmu.ifi.dbs.elki.data.Clustering;
import de.lmu.ifi.dbs.elki.data.DoubleVector;
import de.lmu.ifi.dbs.elki.database.Database;
import de.lmu.ifi.dbs.elki.utilities.ClassGenericsUtil;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.ParameterException;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.parameterization.ListParameterization;
/**
* Performs a full EM run, and compares the result with a clustering derived
* from the data set labels. This test ensures that EM's performance doesn't
* unexpectedly drop on this data set (and also ensures that the algorithms
* work, as a side effect).
*
* @author Katharina Rausch
* @author Erich Schubert
*/
public class TestEMResults extends AbstractSimpleAlgorithmTest implements JUnit4Test {
/**
* Run EM with fixed parameters and compare the result to a golden standard.
*
* @throws ParameterException
*/
@Test
public void testEMResults() {
Database db = makeSimpleDatabase(UNITTEST + "hierarchical-2d.ascii", 710);
// Setup algorithm
ListParameterization params = new ListParameterization();
params.addParameter(KMeans.SEED_ID, 0);
params.addParameter(EM.Parameterizer.K_ID, 6);
EM<DoubleVector, ?> em = ClassGenericsUtil.parameterizeOrAbort(EM.class, params);
testParameterizationOk(params);
// run EM on database
Clustering<?> result = em.run(db);
testFMeasure(db, result, 0.781737);
testClusterSizes(result, new int[] { 2, 5, 17, 175, 200, 311 });
}
}
|
