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
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
|
package de.lmu.ifi.dbs.elki.distance.similarityfunction.cluster;
/*
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.type.SimpleTypeInformation;
import de.lmu.ifi.dbs.elki.database.query.DistanceSimilarityQuery;
import de.lmu.ifi.dbs.elki.database.query.distance.PrimitiveDistanceSimilarityQuery;
import de.lmu.ifi.dbs.elki.database.relation.Relation;
import de.lmu.ifi.dbs.elki.distance.similarityfunction.AbstractPrimitiveSimilarityFunction;
import de.lmu.ifi.dbs.elki.evaluation.clustering.ClusterContingencyTable;
import de.lmu.ifi.dbs.elki.utilities.documentation.Reference;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.AbstractParameterizer;
/**
* Measure the similarity of clusters via the Rand Index.
*
* Reference:
* <p>
* Rand, W. M.<br />
* Objective Criteria for the Evaluation of Clustering Methods<br />
* Journal of the American Statistical Association, Vol. 66 Issue 336
* </p>
*
* @author Erich Schubert
*/
@Reference(authors = "Rand, W. M.", //
title = "Objective Criteria for the Evaluation of Clustering Methods", //
booktitle = "Journal of the American Statistical Association, Vol. 66 Issue 336", //
url = "http://www.jstor.org/stable/10.2307/2284239")
public class ClusteringRandIndexSimilarityFunction extends AbstractPrimitiveSimilarityFunction<Clustering<?>>implements ClusteringDistanceSimilarityFunction {
/**
* Static instance.
*/
public static final ClusteringRandIndexSimilarityFunction STATIC = new ClusteringRandIndexSimilarityFunction();
/**
* Constructor - use the static instance {@link #STATIC}!
*/
public ClusteringRandIndexSimilarityFunction() {
super();
}
@Override
public double similarity(Clustering<?> o1, Clustering<?> o2) {
ClusterContingencyTable ct = new ClusterContingencyTable(false, true);
ct.process(o1, o2);
return ct.getPaircount().randIndex();
}
@Override
public double distance(Clustering<?> o1, Clustering<?> o2) {
ClusterContingencyTable ct = new ClusterContingencyTable(false, true);
ct.process(o1, o2);
return 1. - ct.getPaircount().randIndex();
}
@Override
public boolean isMetric() {
return false;
}
@Override
public <T extends Clustering<?>> DistanceSimilarityQuery<T> instantiate(Relation<T> relation) {
return new PrimitiveDistanceSimilarityQuery<>(relation, this, this);
}
@Override
public SimpleTypeInformation<? super Clustering<?>> getInputTypeRestriction() {
return new SimpleTypeInformation<>(Clustering.class);
}
/**
* Parameterization class.
*
* @author Erich Schubert
*
* @apiviz.exclude
*/
public static class Parameterizer extends AbstractParameterizer {
@Override
protected ClusteringRandIndexSimilarityFunction makeInstance() {
return STATIC;
}
}
}
|