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
|
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.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 WeakEigenPairFilter sorts the eigenpairs in descending order of their
* eigenvalues and returns the first eigenpairs who are above the average mark
* as "strong", the others as "weak".
*
* @author Erich Schubert
* @since 0.2
*/
@Title("Weak Eigenpair Filter")
@Description("Sorts the eigenpairs in decending order of their eigenvalues and returns those eigenpairs, whose eigenvalue is above the average ('expected') eigenvalue.")
public class WeakEigenPairFilter implements EigenPairFilter {
/**
* The default value for walpha.
*/
public static final double DEFAULT_WALPHA = 0.95;
/**
* The noise tolerance level for weak eigenvectors
*/
private double walpha;
/**
* Constructor.
*
* @param walpha
*/
public WeakEigenPairFilter(double walpha) {
super();
this.walpha = walpha;
}
/**
* Filter eigenpairs
*/
@Override
public FilteredEigenPairs filter(SortedEigenPairs 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();
}
double expectEigenvalue = totalSum / eigenPairs.size() * walpha;
// determine strong and weak eigenpairs
for(int i = 0; i < eigenPairs.size(); i++) {
EigenPair eigenPair = eigenPairs.getEigenPair(i);
if(eigenPair.getEigenvalue() > expectEigenvalue) {
strongEigenPairs.add(eigenPair);
}
else {
weakEigenPairs.add(eigenPair);
}
}
// the code using this method doesn't expect an empty strong set,
// if we didn't find any strong ones, we make all vectors strong
if(strongEigenPairs.size() == 0) {
return new FilteredEigenPairs(new ArrayList<EigenPair>(), weakEigenPairs);
}
return new FilteredEigenPairs(weakEigenPairs, strongEigenPairs);
}
/**
* Parameterization class.
*
* @author Erich Schubert
*
* @apiviz.exclude
*/
public static class Parameterizer extends AbstractParameterizer {
/**
* OptionID for the weak alpha value of {@link WeakEigenPairFilter},
* {@link de.lmu.ifi.dbs.elki.math.linearalgebra.pca.ProgressiveEigenPairFilter}
* and
* {@link de.lmu.ifi.dbs.elki.math.linearalgebra.pca.SignificantEigenPairFilter}
*/
public static final OptionID EIGENPAIR_FILTER_WALPHA = new OptionID("pca.filter.weakalpha", "The minimum strength of the statistically expected variance (1/n) share an eigenvector " + "needs to have to be considered 'strong'.");
/**
* The threshold for strong eigenvectors: the strong eigenvectors explain a
* portion of at least alpha of the total variance.
*/
private double walpha;
@Override
protected void makeOptions(Parameterization config) {
super.makeOptions(config);
DoubleParameter walphaP = new DoubleParameter(EIGENPAIR_FILTER_WALPHA, DEFAULT_WALPHA);
walphaP.addConstraint(CommonConstraints.GREATER_EQUAL_ZERO_DOUBLE);
if(config.grab(walphaP)) {
walpha = walphaP.getValue();
}
}
@Override
protected WeakEigenPairFilter makeInstance() {
return new WeakEigenPairFilter(walpha);
}
}
}
|
