blob: 457cc6ebcf9d8229a36ce19ca025e56632becc89 (
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
|
package de.lmu.ifi.dbs.elki.datasource.filter.normalization;
/*
This file is part of ELKI:
Environment for Developing KDD-Applications Supported by Index-Structures
Copyright (C) 2011
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.data.type.SimpleTypeInformation;
import de.lmu.ifi.dbs.elki.data.type.TypeUtil;
import de.lmu.ifi.dbs.elki.distance.distancefunction.DoubleNorm;
import de.lmu.ifi.dbs.elki.distance.distancefunction.EuclideanDistanceFunction;
import de.lmu.ifi.dbs.elki.math.linearalgebra.LinearEquationSystem;
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.parameterization.Parameterization;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.parameters.ObjectParameter;
/**
* Class to perform a normalization on vectors to norm 1.
*
* @author Heidi Kolb
* @author Erich Schubert
*
* @param <V> vector type
*/
public class LengthNormalization<V extends NumberVector<?>> extends AbstractStreamNormalization<V> {
/**
* Norm to use.
*/
DoubleNorm<? super V> norm;
/**
* Constructor.
*
* @param norm Norm to use
*/
public LengthNormalization(DoubleNorm<? super V> norm) {
super();
this.norm = norm;
}
@Override
protected V filterSingleObject(V featureVector) {
final double d = norm.doubleNorm(featureVector);
return factory.newNumberVector(featureVector.getColumnVector().timesEquals(1 / d).getArrayRef());
}
@Override
public V restore(V featureVector) {
throw new UnsupportedOperationException();
}
@Override
public LinearEquationSystem transform(LinearEquationSystem linearEquationSystem) {
// TODO.
throw new UnsupportedOperationException();
}
@Override
protected SimpleTypeInformation<? super V> getInputTypeRestriction() {
return TypeUtil.NUMBER_VECTOR_FIELD;
}
/**
* Parameterization class.
*
* @author Erich Schubert
*
* @apiviz.exclude
*/
public static class Parameterizer<V extends NumberVector<?>> extends AbstractParameterizer {
/**
* Option ID for normalization norm.
*/
public static final OptionID NORM_ID = new OptionID("normalization.norm", "Norm (length function) to use for computing the vector length.");
/**
* Norm to use.
*/
DoubleNorm<? super V> norm;
@Override
protected void makeOptions(Parameterization config) {
super.makeOptions(config);
ObjectParameter<DoubleNorm<? super V>> normP = new ObjectParameter<DoubleNorm<? super V>>(NORM_ID, DoubleNorm.class, EuclideanDistanceFunction.class);
if(config.grab(normP)) {
norm = normP.instantiateClass(config);
}
}
@Override
protected LengthNormalization<V> makeInstance() {
return new LengthNormalization<V>(norm);
}
}
}
|