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
|
package de.lmu.ifi.dbs.elki.datasource.filter;
/*
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 java.util.BitSet;
import java.util.Random;
import de.lmu.ifi.dbs.elki.data.FeatureVector;
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.VectorFieldTypeInformation;
import de.lmu.ifi.dbs.elki.utilities.Util;
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.GreaterEqualConstraint;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.parameterization.Parameterization;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.parameters.IntParameter;
/**
* <p>
* A RandomProjectionParser selects a subset of attributes randomly for
* projection of a ParsingResult.
* </p>
*
* The cardinality of the subset of attributes is specified as a parameter.
*
*
* @author Arthur Zimek
* @author Erich Schubert
*
* @param <V> the type of FeatureVector contained in both the original data of
* the base parser and the projected data of this ProjectionParser
*/
public abstract class AbstractRandomFeatureSelectionFilter<V extends FeatureVector<?, ?>> extends AbstractConversionFilter<V, V> {
/**
* The selected attributes
*/
protected BitSet selectedAttributes = null;
/**
* Parameter for the desired cardinality of the subset of attributes selected
* for projection.
*
* <p>
* Key: <code>-randomprojection.numberselected</code>
* </p>
* <p>
* Default: <code>1</code>
* </p>
* <p>
* Constraint: ≥1
* </p>
*/
public static final OptionID NUMBER_SELECTED_ATTRIBUTES_ID = OptionID.getOrCreateOptionID("randomprojection.numberselected", "number of selected attributes");
/**
* Holds the desired cardinality of the subset of attributes selected for
* projection.
*/
protected int k;
/**
* Holds a random object.
*/
protected final Random random = new Random();
/**
* Constructor.
*
* @param dim dimensionality
*/
public AbstractRandomFeatureSelectionFilter(int dim) {
super();
this.k = dim;
}
@Override
protected boolean prepareStart(SimpleTypeInformation<V> in) {
int d = ((VectorFieldTypeInformation<V>) in).dimensionality();
selectedAttributes = Util.randomBitSet(k, d, random);
// We don't need the full loop, so return false.
return false;
}
/**
* Parameterization class.
*
* @author Erich Schubert
*
* @apiviz.exclude
*/
public static abstract class Parameterizer<V extends NumberVector<V, ?>> extends AbstractParameterizer {
protected int k = 0;
@Override
protected void makeOptions(Parameterization config) {
super.makeOptions(config);
IntParameter kP = new IntParameter(NUMBER_SELECTED_ATTRIBUTES_ID, new GreaterEqualConstraint(1), 1);
if(config.grab(kP)) {
k = kP.getValue();
}
}
}
}
|
