blob: a79a304752e780d77a19d70a199c424ac9f0dce5 (
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
|
package de.lmu.ifi.dbs.elki.datasource.filter.normalization.instancewise;
/*
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.data.type.SimpleTypeInformation;
import de.lmu.ifi.dbs.elki.data.type.TypeUtil;
import de.lmu.ifi.dbs.elki.datasource.filter.normalization.AbstractStreamNormalization;
import de.lmu.ifi.dbs.elki.utilities.Alias;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.AbstractParameterizer;
/**
* Normalize histograms by scaling them to L1 norm 1, then taking the square
* root in each attribute.
*
* Using Euclidean distance (linear kernel) and this transformation is the same
* as using Hellinger distance:
* {@link de.lmu.ifi.dbs.elki.distance.distancefunction.probabilistic.HellingerDistanceFunction}
*
* @author Erich Schubert
*
* @param <V> vector type
*/
@Alias({ "de.lmu.ifi.dbs.elki.datasource.filter.normalization.HellingerHistogramNormalization" })
public class HellingerHistogramNormalization<V extends NumberVector> extends AbstractStreamNormalization<V> {
/**
* Static instance.
*/
public static final HellingerHistogramNormalization<NumberVector> STATIC = new HellingerHistogramNormalization<>();
/**
* Constructor.
*/
public HellingerHistogramNormalization() {
super();
}
@Override
protected V filterSingleObject(V featureVector) {
double[] data = new double[featureVector.getDimensionality()];
double sum = 0.;
for(int d = 0; d < data.length; ++d) {
data[d] = featureVector.doubleValue(d);
data[d] = data[d] > 0 ? data[d] : -data[d];
sum += data[d];
}
// Normalize and sqrt:
if(sum > 0.) {
for(int d = 0; d < data.length; ++d) {
if(data[d] > 0) {
data[d] = Math.sqrt(data[d] / sum);
}
}
}
return factory.newNumberVector(data);
}
@Override
protected SimpleTypeInformation<? super V> getInputTypeRestriction() {
return TypeUtil.NUMBER_VECTOR_VARIABLE_LENGTH;
}
/**
* Parameterization class.
*
* @author Erich Schubert
*
* @apiviz.exclude
*/
public static class Parameterizer extends AbstractParameterizer {
@Override
protected HellingerHistogramNormalization<NumberVector> makeInstance() {
return STATIC;
}
}
}
|