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
178
179
180
181
182
183
184
185
|
package de.lmu.ifi.dbs.elki.datasource.filter.typeconversions;
/*
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.DoubleVector;
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.VectorFieldTypeInformation;
import de.lmu.ifi.dbs.elki.data.uncertain.WeightedDiscreteUncertainObject;
import de.lmu.ifi.dbs.elki.datasource.filter.AbstractConversionFilter;
import de.lmu.ifi.dbs.elki.logging.Logging;
import de.lmu.ifi.dbs.elki.utilities.exceptions.AbortException;
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.constraints.GreaterEqualConstraint;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.constraints.LessConstraint;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.parameterization.Parameterization;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.parameters.IntParameter;
/**
* Filter to transform a single vector into a set of samples and weights to
* interpret as uncertain observation.
*
* @author Erich Schubert
*/
public class WeightedUncertainSplitFilter extends AbstractConversionFilter<NumberVector, WeightedDiscreteUncertainObject> {
/**
* Class logger.
*/
private static final Logging LOG = Logging.getLogger(WeightedUncertainSplitFilter.class);
/**
* Data dimensionality.
*/
protected int dims;
/**
* Modulo value for splitting.
*/
protected int mod;
/**
* Column in which the probability is stored.
*/
protected int probcol;
/**
* Constructor.
*
* @param dims Number of dimensions
* @param probcol Column in which probabilities are stored.
*/
public WeightedUncertainSplitFilter(int dims, int probcol) {
this.dims = dims;
if(probcol < -dims || probcol >= dims) {
throw new AbortException("Invalid column given for prob: " + probcol);
}
else if(probcol < 0) {
probcol += dims;
}
this.probcol = probcol;
this.mod = dims + 1;
}
@Override
protected WeightedDiscreteUncertainObject filterSingleObject(NumberVector vec) {
final int dim = vec.getDimensionality();
if(dim % mod != 0) {
throw new AbortException("Vector length " + dim + " not divisible by the number of dimensions + 1 (for probability): " + mod);
}
final int num = dim / mod;
final DoubleVector[] samples = new DoubleVector[num];
final double[] weights = new double[dims];
final double[] buf = new double[dims];
for(int i = 0, j = 0, k = 0, l = 0; i < mod; i++) {
if(l++ == probcol) {
weights[k] = vec.doubleValue(i);
}
else {
buf[j++] = vec.doubleValue(i);
}
if(l == mod) {
samples[k] = new DoubleVector(buf);
j = 0;
l = 0;
k++;
}
}
return new WeightedDiscreteUncertainObject(samples, weights);
}
@Override
protected SimpleTypeInformation<? super NumberVector> getInputTypeRestriction() {
return TypeUtil.NUMBER_VECTOR_FIELD;
}
@Override
protected SimpleTypeInformation<WeightedDiscreteUncertainObject> convertedType(SimpleTypeInformation<NumberVector> in) {
final int dim = ((VectorFieldTypeInformation<NumberVector>) in).getDimensionality();
if(dim % mod != 0) {
throw new AbortException("Vector length " + dim + " not divisible by the number of dimensions + 1 (for probability): " + mod);
}
return new VectorFieldTypeInformation<WeightedDiscreteUncertainObject>(WeightedDiscreteUncertainObject.FACTORY, dim);
}
@Override
protected Logging getLogger() {
return LOG;
}
/**
* Parameterization class.
*
* @author Erich Schubert
*
* @apiviz.exclude
*/
public static class Parameterizer extends AbstractParameterizer {
/**
* Parameter for specifying the number of dimensions of the sample.
*/
public static final OptionID DIM_ID = new OptionID("uncertain.dimensionality", "Dimensionality of the data set (used for splitting).");
/**
* Parameter to specify where the probability is stored.
*/
public static final OptionID PROBCOL_ID = new OptionID("uncertain.probability.column", "Column in which the probability is stored, starting at 0. -1 is the last column.");
/**
* Field to hold the dimensional constraint.
*/
protected int dims = 0;
/**
* Column in which the probability is stored.
*/
protected int probcol = Integer.MIN_VALUE;
@Override
protected void makeOptions(Parameterization config) {
super.makeOptions(config);
IntParameter dimsP = new IntParameter(DIM_ID) //
.addConstraint(CommonConstraints.GREATER_EQUAL_ONE_INT);
IntParameter probP = new IntParameter(PROBCOL_ID);
if(config.grab(dimsP)) {
dims = dimsP.intValue();
// Add additional constraints:
probP.addConstraint(new LessConstraint(dimsP.intValue()));
probP.addConstraint(new GreaterEqualConstraint(-dimsP.intValue()));
}
if(config.grab(probP)) {
probcol = probP.intValue();
}
}
@Override
protected WeightedUncertainSplitFilter makeInstance() {
return new WeightedUncertainSplitFilter(dims, probcol);
}
}
}
|
