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
|
package de.lmu.ifi.dbs.elki.distance.distancefunction;
/*
This file is part of ELKI:
Environment for Developing KDD-Applications Supported by Index-Structures
Copyright (C) 2012
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 de.lmu.ifi.dbs.elki.data.SparseNumberVector;
import de.lmu.ifi.dbs.elki.data.type.SimpleTypeInformation;
import de.lmu.ifi.dbs.elki.data.type.TypeUtil;
import de.lmu.ifi.dbs.elki.distance.distancevalue.DoubleDistance;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.AbstractParameterizer;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.constraints.GreaterConstraint;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.parameterization.Parameterization;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.parameters.DoubleParameter;
/**
* Provides a LP-Norm for FeatureVectors.
*
* @author Erich Schubert
*/
// TODO: implement SpatialDistanceFunction
public class SparseLPNormDistanceFunction extends AbstractPrimitiveDistanceFunction<SparseNumberVector<?, ?>, DoubleDistance> implements DoubleNorm<SparseNumberVector<?, ?>> {
/**
* Keeps the currently set p.
*/
private double p;
/**
* Provides a LP-Norm for FeatureVectors.
*/
public SparseLPNormDistanceFunction(double p) {
super();
}
@Override
public double doubleDistance(SparseNumberVector<?, ?> v1, SparseNumberVector<?, ?> v2) {
// Get the bit masks
BitSet b1 = v1.getNotNullMask();
BitSet b2 = v2.getNotNullMask();
double sqrDist = 0;
int i1 = b1.nextSetBit(0);
int i2 = b2.nextSetBit(0);
while(i1 >= 0 && i2 >= 0) {
if(i1 == i2) {
// Set in both
double manhattanI = Math.abs(v1.doubleValue(i1) - v2.doubleValue(i2));
sqrDist += Math.pow(manhattanI, p);
i1 = b1.nextSetBit(i1 + 1);
i2 = b2.nextSetBit(i2 + 1);
}
else if(i1 < i2 && i1 >= 0) {
// In first only
double manhattanI = Math.abs(v1.doubleValue(i1));
sqrDist += Math.pow(manhattanI, p);
i1 = b1.nextSetBit(i1 + 1);
}
else {
// In second only
double manhattanI = Math.abs(v2.doubleValue(i2));
sqrDist += Math.pow(manhattanI, p);
i2 = b1.nextSetBit(i2 + 1);
}
}
return Math.pow(sqrDist, 1.0 / p);
}
@Override
public double doubleNorm(SparseNumberVector<?, ?> v1) {
double sqrDist = 0;
// Get the bit masks
BitSet b1 = v1.getNotNullMask();
// Set in first only
for(int i = b1.nextSetBit(0); i >= 0; i = b1.nextSetBit(i + 1)) {
double manhattanI = Math.abs(v1.doubleValue(i));
sqrDist += Math.pow(manhattanI, p);
}
return Math.pow(sqrDist, 1.0 / p);
}
@Override
public DoubleDistance norm(SparseNumberVector<?, ?> obj) {
return new DoubleDistance(doubleNorm(obj));
}
@Override
public DoubleDistance distance(SparseNumberVector<?, ?> v1, SparseNumberVector<?, ?> v2) {
return new DoubleDistance(doubleDistance(v1, v2));
}
@Override
public DoubleDistance getDistanceFactory() {
return DoubleDistance.FACTORY;
}
@Override
public SimpleTypeInformation<? super SparseNumberVector<?, ?>> getInputTypeRestriction() {
return TypeUtil.SPARSE_VECTOR_VARIABLE_LENGTH;
}
@Override
public boolean isMetric() {
return (p >= 1);
}
/**
* Parameterizer
*
* @author Erich Schubert
*
* @apiviz.exclude
*/
public static class Parameterizer extends AbstractParameterizer {
/**
* Value for p
*/
double p = 2.0;
@Override
protected void makeOptions(Parameterization config) {
super.makeOptions(config);
DoubleParameter pP = new DoubleParameter(LPNormDistanceFunction.P_ID, new GreaterConstraint(0));
if(config.grab(pP)) {
p = pP.getValue();
}
}
@Override
protected SparseLPNormDistanceFunction makeInstance() {
if(p == 2.0) {
return SparseEuclideanDistanceFunction.STATIC;
}
if(p == 1.0) {
return SparseManhattanDistanceFunction.STATIC;
}
if(p == Double.POSITIVE_INFINITY) {
return SparseMaximumDistanceFunction.STATIC;
}
return new SparseLPNormDistanceFunction(p);
}
}
}
|
