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
|
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 de.lmu.ifi.dbs.elki.data.Clustering;
import de.lmu.ifi.dbs.elki.data.NumberVector;
import de.lmu.ifi.dbs.elki.data.model.MeanModel;
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.documentation.Reference;
/**
* Akaike Information Criterion (AIC).
*
* Reference:
* <p>
* H. Akaike<br />
* On entropy maximization principle<br />
* Application of statistics, 1977, North-Holland
* </p>
*
* The use for k-means was popularized by:
* <p>
* D. Pelleg, A. Moore:<br />
* X-means: Extending K-means with Efficient Estimation on the Number of
* Clusters<br />
* In: Proceedings of the 17th International Conference on Machine Learning
* (ICML 2000)
* </p>
*
* @author Tibor Goldschwendt
* @author Erich Schubert
*/
@Reference(authors = "H. Akaike", //
title = "On entropy maximization principle", //
booktitle = "Application of statistics, 1977, North-Holland")
public class AkaikeInformationCriterion extends AbstractKMeansQualityMeasure<NumberVector> {
@Override
public <V extends NumberVector> double quality(Clustering<? extends MeanModel> clustering, NumberVectorDistanceFunction<? super V> distanceFunction, Relation<V> relation) {
return logLikelihood(relation, clustering, distanceFunction) - numberOfFreeParameters(relation, clustering);
}
@Override
public boolean ascending() {
return true;
}
@Override
public boolean isBetter(double currentCost, double bestCost) {
// Careful: bestCost may be NaN!
return !(currentCost <= bestCost);
}
}
|
