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
|
package de.lmu.ifi.dbs.elki.index.lsh.hashfamilies;
/*
This file is part of ELKI:
Environment for Developing KDD-Applications Supported by Index-Structures
Copyright (C) 2013
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.ArrayList;
import java.util.Random;
import de.lmu.ifi.dbs.elki.data.NumberVector;
import de.lmu.ifi.dbs.elki.data.type.TypeInformation;
import de.lmu.ifi.dbs.elki.data.type.TypeUtil;
import de.lmu.ifi.dbs.elki.database.relation.Relation;
import de.lmu.ifi.dbs.elki.database.relation.RelationUtil;
import de.lmu.ifi.dbs.elki.index.lsh.hashfunctions.LocalitySensitiveHashFunction;
import de.lmu.ifi.dbs.elki.index.lsh.hashfunctions.MultipleProjectionsLocalitySensitiveHashFunction;
import de.lmu.ifi.dbs.elki.math.linearalgebra.randomprojections.RandomProjectionFamily;
import de.lmu.ifi.dbs.elki.utilities.RandomFactory;
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.RandomParameter;
/**
* Abstract base class for projection based hash functions.
*
* @author Erich Schubert
*/
public abstract class AbstractHashFunctionFamily implements LocalitySensitiveHashFunctionFamily<NumberVector<?>> {
/**
* Random generator to use.
*/
protected RandomFactory random;
/**
* Projection family to use.
*/
protected RandomProjectionFamily proj;
/**
* Width of each bin.
*/
protected double width;
/**
* The number of projections to use for each hash function.
*/
protected int k;
/**
* Constructor.
*
* @param random Random generator
* @param proj Projection family
* @param width Bin width
* @param k Number of projections for each hash function.
*/
public AbstractHashFunctionFamily(RandomFactory random, RandomProjectionFamily proj, double width, int k) {
super();
this.random = random;
this.proj = proj;
this.width = width;
this.k = k;
}
@Override
public ArrayList<? extends LocalitySensitiveHashFunction<? super NumberVector<?>>> generateHashFunctions(Relation<? extends NumberVector<?>> relation, int l) {
int dim = RelationUtil.dimensionality(relation);
ArrayList<LocalitySensitiveHashFunction<? super NumberVector<?>>> ps = new ArrayList<>(l);
final Random rnd = random.getSingleThreadedRandom();
for(int i = 0; i < l; i++) {
RandomProjectionFamily.Projection mat = proj.generateProjection(dim, k);
ps.add(new MultipleProjectionsLocalitySensitiveHashFunction(mat, width, rnd));
}
return ps;
}
@Override
public TypeInformation getInputTypeRestriction() {
return TypeUtil.NUMBER_VECTOR_FIELD;
}
/**
* Parameterization class.
*
* @author Erich Schubert
*
* @apiviz.exclude
*/
public abstract static class Parameterizer extends AbstractParameterizer {
/**
* Parameter for fixing the random seed.
*/
public static final OptionID RANDOM_ID = new OptionID("lsh.projection.random", "Random seed for generating the projections.");
/**
* Parameter for choosing the bin width.
*/
public static final OptionID WIDTH_ID = new OptionID("lsh.projection.width", "Bin width for random projections.");
/**
* Number of projections to use in each hash function.
*/
public static final OptionID NUMPROJ_ID = new OptionID("lsh.projection.projections", "Number of projections to use for each hash function.");
/**
* Random generator to use.
*/
RandomFactory random;
/**
* Width of each bin.
*/
double width;
/**
* The number of projections to use for each hash function.
*/
int k;
@Override
protected void makeOptions(Parameterization config) {
super.makeOptions(config);
RandomParameter randP = new RandomParameter(RANDOM_ID, RandomFactory.DEFAULT);
if(config.grab(randP)) {
random = randP.getValue();
}
DoubleParameter widthP = new DoubleParameter(WIDTH_ID);
widthP.addConstraint(CommonConstraints.GREATER_THAN_ZERO_DOUBLE);
if(config.grab(widthP)) {
width = widthP.doubleValue();
}
IntParameter lP = new IntParameter(NUMPROJ_ID);
lP.addConstraint(CommonConstraints.GREATER_EQUAL_ONE_INT);
if(config.grab(lP)) {
k = lP.intValue();
}
}
}
}
|
