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
81
82
83
84
85
86
87
88
89
|
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 java.util.ArrayList;
import java.util.List;
import de.lmu.ifi.dbs.elki.algorithm.clustering.kmeans.initialization.KMeansInitialization;
import de.lmu.ifi.dbs.elki.data.NumberVector;
import de.lmu.ifi.dbs.elki.data.model.EMModel;
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.math.MathUtil;
import de.lmu.ifi.dbs.elki.math.linearalgebra.Vector;
/**
* Factory for EM with multivariate gaussian models using diagonal matrixes.
*
* These models have individual variances, but no covariance, so this
* corresponds to the {@code 'VVI'} model in Mclust (R).
*
* @author Erich Schubert
* @since 0.7.0
*
* @apiviz.has DiagonalGaussianModel
*
* @param <V> vector type
*/
public class DiagonalGaussianModelFactory<V extends NumberVector> extends AbstractEMModelFactory<V, EMModel> {
/**
* Constructor.
*
* @param initializer Class for choosing the inital seeds.
*/
public DiagonalGaussianModelFactory(KMeansInitialization<V> initializer) {
super(initializer);
}
@Override
public List<DiagonalGaussianModel> buildInitialModels(Database database, Relation<V> relation, int k, NumberVectorDistanceFunction<? super V> df) {
final List<Vector> initialMeans = initializer.chooseInitialMeans(database, relation, k, df, Vector.FACTORY);
assert (initialMeans.size() == k);
final int dimensionality = initialMeans.get(0).getDimensionality();
final double norm = MathUtil.powi(MathUtil.TWOPI, dimensionality);
List<DiagonalGaussianModel> models = new ArrayList<>(k);
for(Vector nv : initialMeans) {
models.add(new DiagonalGaussianModel(1. / k, nv, norm));
}
return models;
}
/**
* Parameterization class
*
* @author Erich Schubert
*
* @apiviz.exclude
*
* @param <V> Vector type
*/
public static class Parameterizer<V extends NumberVector> extends AbstractEMModelFactory.Parameterizer<V> {
@Override
protected DiagonalGaussianModelFactory<V> makeInstance() {
return new DiagonalGaussianModelFactory<>(initializer);
}
}
}
|
