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
170
171
172
173
174
175
176
177
|
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.data.type.VectorTypeInformation;
import de.lmu.ifi.dbs.elki.datasource.filter.normalization.AbstractStreamNormalization;
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.LessGlobalConstraint;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.parameterization.Parameterization;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.parameters.DoubleParameter;
/**
* Normalize vectors such that the smallest attribute is 0, the largest is 1.
*
* @author Erich Schubert
*
* @param <V> vector type
*/
public class InstanceMinMaxNormalization<V extends NumberVector> extends AbstractStreamNormalization<V> {
/**
* Minimum and maximum values.
*/
private double min, max;
/**
* Multiplicity of the vector.
*/
private int multiplicity;
/**
* Constructor.
*
* @param min Desired minimum value
* @param max Desired maximum value
*/
public InstanceMinMaxNormalization(double min, double max) {
super();
this.min = min;
this.max = max;
}
/**
* Constructor, normalizing to {@code [0;1]}
*/
public InstanceMinMaxNormalization() {
this(0., 1.);
}
@Override
protected V filterSingleObject(V featureVector) {
double[] raw = featureVector.getColumnVector().getArrayRef();
// Multivariate codepath:
if(multiplicity > 1) {
assert (raw.length % multiplicity == 0) : "Vector length is not divisible by multiplicity?";
double[] mi = new double[multiplicity], ma = new double[multiplicity];
for(int i = 0; i < multiplicity; i++) {
mi[i] = Double.POSITIVE_INFINITY;
ma[i] = Double.NEGATIVE_INFINITY;
}
for(int i = 0, j = 0; i < raw.length; ++i, j = ++j % multiplicity) {
final double v = raw[i];
if(v != v) { // NaN guard
continue;
}
mi[j] = (mi[j] < v) ? mi[j] : v;
ma[j] = (ma[j] > v) ? ma[j] : v;
}
for(int j = 0; j < multiplicity; j++) {
if(mi[j] < ma[j]) {
final double s = (max - min) / (ma[j] - mi[j]);
for(int i = 0; i < raw.length; i += multiplicity) {
raw[i] = (raw[i] - mi[j]) * s + min;
}
}
}
return factory.newNumberVector(raw);
}
// Default codepath
double mi = Double.POSITIVE_INFINITY, ma = Double.NEGATIVE_INFINITY;
for(int i = 0; i < raw.length; ++i) {
final double v = raw[i];
if(v != v) { // NaN guard
continue;
}
mi = (mi < v) ? mi : v;
ma = (ma > v) ? ma : v;
}
if(mi < ma) {
final double s = (max - min) / (ma - mi);
for(int i = 0; i < raw.length; ++i) {
raw[i] = (raw[i] - mi) * s + min;
}
}
return factory.newNumberVector(raw);
}
@Override
protected void initializeOutputType(SimpleTypeInformation<V> type) {
super.initializeOutputType(type);
multiplicity = ((VectorTypeInformation<?>) type).getMultiplicity();
}
@Override
protected SimpleTypeInformation<? super V> getInputTypeRestriction() {
return TypeUtil.NUMBER_VECTOR_VARIABLE_LENGTH;
}
/**
* Parameterization class.
*
* @author Erich Schubert
*
* @apiviz.exclude
*/
public static class Parameterizer<V extends NumberVector> extends AbstractParameterizer {
/**
* Option ID for minimum value.
*/
public static final OptionID MIN_ID = new OptionID("normalization.min", "Minimum value to assign to objects.");
/**
* Option ID for maximum value.
*/
public static final OptionID MAX_ID = new OptionID("normalization.max", "Maximum value to assign to objects.");
/**
* Minimum and maximum values.
*/
private double min, max;
@Override
protected void makeOptions(Parameterization config) {
super.makeOptions(config);
DoubleParameter minP = new DoubleParameter(MIN_ID, 0.) //
.setOptional(true);
if(config.grab(minP)) {
min = minP.doubleValue();
}
DoubleParameter maxP = new DoubleParameter(MAX_ID, 1.) //
.setOptional(true);
if(config.grab(maxP)) {
max = maxP.doubleValue();
}
config.checkConstraint(new LessGlobalConstraint<>(minP, maxP));
}
@Override
protected InstanceMinMaxNormalization<V> makeInstance() {
return new InstanceMinMaxNormalization<>(min, max);
}
}
}
|