blob: 00ed08c40b61c038a6682c1ae15a56b53279c16c (
plain)
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
|
package de.lmu.ifi.dbs.elki.algorithm.clustering.kmeans;
/*
This file is part of ELKI:
Environment for Developing KDD-Applications Supported by Index-Structures
Copyright (C) 2012
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 java.util.Random;
import de.lmu.ifi.dbs.elki.data.NumberVector;
import de.lmu.ifi.dbs.elki.database.relation.Relation;
import de.lmu.ifi.dbs.elki.distance.distancefunction.PrimitiveDistanceFunction;
import de.lmu.ifi.dbs.elki.math.MathUtil;
import de.lmu.ifi.dbs.elki.utilities.DatabaseUtil;
import de.lmu.ifi.dbs.elki.utilities.pairs.Pair;
/**
* Initialize k-means by generating random vectors (within the data sets value
* range).
*
* @author Erich Schubert
*
* @param <V> Vector type
*/
public class RandomlyGeneratedInitialMeans<V extends NumberVector<V, ?>> extends AbstractKMeansInitialization<V> {
/**
* Constructor.
*
* @param seed Random seed.
*/
public RandomlyGeneratedInitialMeans(Long seed) {
super(seed);
}
@Override
public List<V> chooseInitialMeans(Relation<V> relation, int k, PrimitiveDistanceFunction<? super V, ?> distanceFunction) {
final int dim = DatabaseUtil.dimensionality(relation);
Pair<V, V> minmax = DatabaseUtil.computeMinMax(relation);
List<V> means = new ArrayList<V>(k);
final Random random = (this.seed != null) ? new Random(this.seed) : new Random();
for(int i = 0; i < k; i++) {
double[] r = MathUtil.randomDoubleArray(dim, random);
// Rescale
for(int d = 0; d < dim; d++) {
r[d] = minmax.first.doubleValue(d + 1) + (minmax.second.doubleValue(d + 1) - minmax.first.doubleValue(d + 1)) * r[d];
}
means.add(minmax.first.newNumberVector(r));
}
return means;
}
/**
* Parameterization class.
*
* @author Erich Schubert
*
* @apiviz.exclude
*/
public static class Parameterizer<V extends NumberVector<V, ?>> extends AbstractKMeansInitialization.Parameterizer<V> {
@Override
protected RandomlyGeneratedInitialMeans<V> makeInstance() {
return new RandomlyGeneratedInitialMeans<V>(seed);
}
}
}
|
