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
|
package de.lmu.ifi.dbs.elki.distance.distancefunction.correlation;
/*
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.NumberVector;
import de.lmu.ifi.dbs.elki.distance.distancefunction.AbstractNumberVectorDistanceFunction;
import de.lmu.ifi.dbs.elki.math.MathUtil;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.AbstractParameterizer;
/**
* Pearson correlation distance function for feature vectors.
*
* The Pearson correlation distance is computed from the Pearson correlation
* coefficient <code>r</code> as: <code>1-r</code>. Hence, possible values of
* this distance are between 0 and 2.
*
* The distance between two vectors will be low (near 0), if their attribute
* values are dimension-wise strictly positively correlated, it will be high
* (near 2), if their attribute values are dimension-wise strictly negatively
* correlated. For Features with uncorrelated attributes, the distance value
* will be intermediate (around 1).
*
* @author Arthur Zimek
* @since 0.3
*/
public class PearsonCorrelationDistanceFunction extends AbstractNumberVectorDistanceFunction {
/**
* Static instance.
*/
public static final PearsonCorrelationDistanceFunction STATIC = new PearsonCorrelationDistanceFunction();
/**
* Constructor - use {@link #STATIC} instead.
*
* @deprecated Use static instance!
*/
@Deprecated
public PearsonCorrelationDistanceFunction() {
super();
}
/**
* Computes the Pearson correlation distance for two given feature vectors.
*
* The Pearson correlation distance is computed from the Pearson correlation
* coefficient <code>r</code> as: <code>1-r</code>. Hence, possible values of
* this distance are between 0 and 2.
*
* @param v1 first feature vector
* @param v2 second feature vector
* @return the Pearson correlation distance for two given feature vectors v1
* and v2
*/
@Override
public double distance(NumberVector v1, NumberVector v2) {
return 1 - MathUtil.pearsonCorrelationCoefficient(v1, v2);
}
@Override
public String toString() {
return "PearsonCorrelationDistance";
}
@Override
public boolean equals(Object obj) {
if(obj == null) {
return false;
}
return this.getClass().equals(obj.getClass());
}
/**
* Parameterization class.
*
* @author Erich Schubert
*
* @apiviz.exclude
*/
public static class Parameterizer extends AbstractParameterizer {
@Override
protected PearsonCorrelationDistanceFunction makeInstance() {
return PearsonCorrelationDistanceFunction.STATIC;
}
}
}
|
