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
|
package de.lmu.ifi.dbs.elki.index.projected;
/*
This file is part of ELKI:
Environment for Developing KDD-Applications Supported by Index-Structures
Copyright (C) 2014
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.projection.RandomProjection;
import de.lmu.ifi.dbs.elki.index.IndexFactory;
import de.lmu.ifi.dbs.elki.math.linearalgebra.randomprojections.AchlioptasRandomProjectionFamily;
import de.lmu.ifi.dbs.elki.math.random.RandomFactory;
import de.lmu.ifi.dbs.elki.utilities.documentation.Reference;
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.parameterization.Parameterization;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.parameters.DoubleParameter;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.parameters.IntParameter;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.parameters.ObjectParameter;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.parameters.RandomParameter;
/**
* Projection-Indexed nearest-neighbors (PINN) is an index to retrieve the
* nearest neighbors in high dimensional spaces by using a random projection
* based index.
*
* Reference:
* <p>
* Finding local anomalies in very high dimensional space<br />
* T. de Vries, S. Chawla, M. E. Houle<br />
* In: Proc. IEEE 10th International Conference on Data Mining (ICDM)
* </p>
*
* @author Erich Schubert
*
* @apiviz.composedOf AchlioptasRandomProjectionFamily
*
* @param <O> Object type
*/
@Reference(title = "Finding local anomalies in very high dimensional space", authors = "T. de Vries, S. Chawla, M. E. Houle", booktitle = "Proc. IEEE 10th International Conference on Data Mining (ICDM)", url = "http://dx.doi.org/10.1109/ICDM.2010.151")
public class PINN<O extends NumberVector> extends ProjectedIndex.Factory<O, O> {
/**
* Constructor.
*
* @param inner Inner index
* @param t Target dimensionality
* @param s Sparsity
* @param h Neighborhood size multiplicator
* @param random Random generator factory
*/
public PINN(IndexFactory<O, ?> inner, int t, double s, double h, RandomFactory random) {
super(new RandomProjection<O>(t, new AchlioptasRandomProjectionFamily(s, random)), inner, true, false, h);
}
/**
* Parameterization class.
*
* @author Erich Schubert
*
* @apiviz.exclude
*
* @param <O> Outer object type.
*/
public static class Parameterizer<O extends NumberVector> extends AbstractParameterizer {
/**
* Target dimensionality.
*/
public static final OptionID T_ID = new OptionID("pinn.t", "Target dimensionality.");
/**
* Sparsity option.
*/
public static final OptionID S_ID = new OptionID("pinn.s", "Sparsity of the random projection.");
/**
* Neighborhood size.
*/
public static final OptionID H_ID = new OptionID("pinn.hmult", "Multiplicator for neighborhood size.");
/**
* Random generator.
*/
public static final OptionID RANDOM_ID = new OptionID("pinn.seed", "Random generator seed.");
/**
* Inner index factory.
*/
IndexFactory<O, ?> inner;
/**
* Dimensionality.
*/
int t;
/**
* Sparsity.
*/
double s;
/**
* Multiplicator.
*/
double h;
/**
* Random generator.
*/
RandomFactory random;
@Override
protected void makeOptions(Parameterization config) {
super.makeOptions(config);
ObjectParameter<IndexFactory<O, ?>> innerP = new ObjectParameter<>(ProjectedIndex.Factory.Parameterizer.INDEX_ID, IndexFactory.class);
if(config.grab(innerP)) {
inner = innerP.instantiateClass(config);
}
IntParameter tP = new IntParameter(T_ID);
tP.addConstraint(CommonConstraints.GREATER_EQUAL_ONE_INT);
if(config.grab(tP)) {
t = tP.intValue();
}
DoubleParameter sP = new DoubleParameter(S_ID, 1.);
sP.addConstraint(CommonConstraints.GREATER_EQUAL_ONE_DOUBLE);
if(config.grab(sP)) {
s = sP.doubleValue();
}
DoubleParameter hP = new DoubleParameter(H_ID, 3.);
hP.addConstraint(CommonConstraints.GREATER_EQUAL_ONE_DOUBLE);
if(config.grab(hP)) {
h = hP.doubleValue();
}
RandomParameter randomP = new RandomParameter(RANDOM_ID);
if(config.grab(randomP)) {
random = randomP.getValue();
}
}
@Override
protected PINN<O> makeInstance() {
return new PINN<>(inner, t, s, h, random);
}
}
}
|
