blob: 8b445b97b93e133ec2a4a3a47ac2028168e761ff (
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
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
|
package de.lmu.ifi.dbs.elki.math.linearalgebra.pca;
/*
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 java.util.ArrayList;
import java.util.List;
import de.lmu.ifi.dbs.elki.logging.Logging;
import de.lmu.ifi.dbs.elki.math.linearalgebra.EigenPair;
import de.lmu.ifi.dbs.elki.math.linearalgebra.SortedEigenPairs;
import de.lmu.ifi.dbs.elki.utilities.documentation.Description;
import de.lmu.ifi.dbs.elki.utilities.documentation.Title;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.AbstractParameterizer;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.OptionID;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.constraints.CommonConstraints;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.parameterization.Parameterization;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.parameters.DoubleParameter;
/**
* The PercentageEigenPairFilter sorts the eigenpairs in descending order of
* their eigenvalues and marks the first eigenpairs, whose sum of eigenvalues is
* higher than the given percentage of the sum of all eigenvalues as strong
* eigenpairs.
*
* @author Elke Achtert
* @since 0.2
*/
@Title("Percentage based Eigenpair filter")
@Description("Sorts the eigenpairs in decending order of their eigenvalues and returns the first eigenpairs, whose sum of eigenvalues is higher than the given percentage of the sum of all eigenvalues.")
public class PercentageEigenPairFilter implements EigenPairFilter {
/**
* The logger for this class.
*/
private static final Logging LOG = Logging.getLogger(PercentageEigenPairFilter.class);
/**
* The default value for alpha.
*/
public static final double DEFAULT_ALPHA = 0.85;
/**
* The threshold for strong eigenvectors: the strong eigenvectors explain a
* portion of at least alpha of the total variance.
*/
private double alpha;
/**
* Constructor.
*
* @param alpha
*/
public PercentageEigenPairFilter(double alpha) {
super();
this.alpha = alpha;
}
@Override
public FilteredEigenPairs filter(SortedEigenPairs eigenPairs) {
StringBuilder msg = new StringBuilder();
if(LOG.isDebugging()) {
msg.append("alpha = ").append(alpha);
msg.append("\nsortedEigenPairs = ").append(eigenPairs);
}
// init strong and weak eigenpairs
List<EigenPair> strongEigenPairs = new ArrayList<>();
List<EigenPair> weakEigenPairs = new ArrayList<>();
// determine sum of eigenvalues
double totalSum = 0;
for(int i = 0; i < eigenPairs.size(); i++) {
EigenPair eigenPair = eigenPairs.getEigenPair(i);
totalSum += eigenPair.getEigenvalue();
}
if(LOG.isDebugging()) {
msg.append("\ntotalSum = ").append(totalSum);
}
// determine strong and weak eigenpairs
double currSum = 0;
boolean found = false;
for(int i = 0; i < eigenPairs.size(); i++) {
EigenPair eigenPair = eigenPairs.getEigenPair(i);
currSum += eigenPair.getEigenvalue();
if(currSum / totalSum >= alpha) {
if(!found) {
found = true;
strongEigenPairs.add(eigenPair);
}
else {
weakEigenPairs.add(eigenPair);
}
}
else {
strongEigenPairs.add(eigenPair);
}
}
if(LOG.isDebugging()) {
msg.append("\nstrong EigenPairs = ").append(strongEigenPairs);
msg.append("\nweak EigenPairs = ").append(weakEigenPairs);
LOG.debugFine(msg.toString());
}
return new FilteredEigenPairs(weakEigenPairs, strongEigenPairs);
}
/**
* Parameterization class.
*
* @author Erich Schubert
*
* @apiviz.exclude
*/
public static class Parameterizer extends AbstractParameterizer {
/**
* The threshold for 'strong' eigenvectors: the 'strong' eigenvectors explain
* a portion of at least alpha of the total variance.
* <p>
* Default value: {@link #DEFAULT_ALPHA}
* </p>
* <p>
* Key: {@code -pca.filter.alpha}
* </p>
*/
public static final OptionID ALPHA_ID = new OptionID("pca.filter.alpha", "The share (0.0 to 1.0) of variance that needs to be explained by the 'strong' eigenvectors." + "The filter class will choose the number of strong eigenvectors by this share.");
/**
* The threshold for strong eigenvectors: the strong eigenvectors explain a
* portion of at least alpha of the total variance.
*/
private double alpha;
@Override
protected void makeOptions(Parameterization config) {
super.makeOptions(config);
DoubleParameter alphaP = new DoubleParameter(ALPHA_ID, DEFAULT_ALPHA);
alphaP.addConstraint(CommonConstraints.GREATER_THAN_ZERO_DOUBLE);
alphaP.addConstraint(CommonConstraints.LESS_THAN_ONE_DOUBLE);
if(config.grab(alphaP)) {
alpha = alphaP.doubleValue();
}
}
@Override
protected PercentageEigenPairFilter makeInstance() {
return new PercentageEigenPairFilter(alpha);
}
}
}
|
