blob: 100c2dfcf0dd34b8f682f6201a5c0fa3185ef9b8 (
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
|
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;
/**
* Interface for computing the quality of a K-Means clustering.
*
* Important note: some measures are ascending, others are descending!
*
* @author Erich Schubert
* @since 0.2
*
* @param <O> Input Object restriction type
*/
public interface KMeansQualityMeasure<O extends NumberVector> {
/**
* Calculates and returns the quality measure.
*
* @param clustering Clustering to analyze
* @param distanceFunction Distance function to use (usually Euclidean or
* squared Euclidean!)
* @param relation Relation for accessing objects
* @param <V> Actual vector type (could be a subtype of O!)
*
* @return quality measure
*/
<V extends O> double quality(Clustering<? extends MeanModel> clustering, NumberVectorDistanceFunction<? super V> distanceFunction, Relation<V> relation);
/**
* Use ascending or descending ordering.
*
* @return {@code true} when larger scores are better.
*/
boolean ascending();
/**
* Compare two scores.
*
* @param currentCost New (candiate) cost/score
* @param bestCost Existing best cost/score (may be {@code NaN})
* @return {@code true} when the new score is better, or the old score is
* {@code NaN}.
*/
boolean isBetter(double currentCost, double bestCost);
}
|