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
|
package de.lmu.ifi.dbs.elki.distance.similarityfunction;
/*
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.database.ids.DBIDIter;
import de.lmu.ifi.dbs.elki.database.ids.DBIDRef;
import de.lmu.ifi.dbs.elki.database.ids.DBIDUtil;
import de.lmu.ifi.dbs.elki.database.ids.DBIDs;
import de.lmu.ifi.dbs.elki.database.relation.Relation;
import de.lmu.ifi.dbs.elki.index.preprocessed.snn.SharedNearestNeighborIndex;
import de.lmu.ifi.dbs.elki.index.preprocessed.snn.SharedNearestNeighborPreprocessor;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.parameterization.Parameterization;
/**
* SharedNearestNeighborSimilarityFunction with a pattern defined to accept
* Strings that define a non-negative Integer.
*
* @author Arthur Zimek
*
* @apiviz.has
* de.lmu.ifi.dbs.elki.index.preprocessed.snn.SharedNearestNeighborIndex
* .Factory
* @apiviz.has Instance oneway - - «create»
*
* @param <O> object type
*/
public class FractionalSharedNearestNeighborSimilarityFunction<O> extends AbstractIndexBasedSimilarityFunction<O, SharedNearestNeighborIndex<O>> implements NormalizedSimilarityFunction<O> {
/**
* Constructor.
*
* @param indexFactory Index factory.
*/
public FractionalSharedNearestNeighborSimilarityFunction(SharedNearestNeighborIndex.Factory<O, SharedNearestNeighborIndex<O>> indexFactory) {
super(indexFactory);
}
@SuppressWarnings("unchecked")
@Override
public <T extends O> Instance<T> instantiate(Relation<T> database) {
SharedNearestNeighborIndex<O> indexi = indexFactory.instantiate((Relation<O>) database);
return (Instance<T>) new Instance<>((Relation<O>) database, indexi, this);
}
/**
* Actual instance for a dataset.
*
* @author Erich Schubert
*
* @apiviz.uses SharedNearestNeighborIndex
*
* @param <T> Object type
*/
public static class Instance<T> extends AbstractIndexBasedSimilarityFunction.Instance<T, SharedNearestNeighborIndex<T>> {
/**
* Similarity function.
*/
private FractionalSharedNearestNeighborSimilarityFunction<? super T> similarityFunction;
/**
* Constructor.
*
* @param database Database
* @param preprocessor Preprocessor
*/
public Instance(Relation<T> database, SharedNearestNeighborIndex<T> preprocessor, FractionalSharedNearestNeighborSimilarityFunction<? super T> similarityFunction) {
super(database, preprocessor);
this.similarityFunction = similarityFunction;
}
/**
* Compute the intersection size.
*
* @param neighbors1 SORTED neighbor ids of first
* @param neighbors2 SORTED neighbor ids of second
* @return Intersection size
*/
static protected int countSharedNeighbors(DBIDs neighbors1, DBIDs neighbors2) {
int intersection = 0;
DBIDIter iter1 = neighbors1.iter();
DBIDIter iter2 = neighbors2.iter();
while (iter1.valid() && iter2.valid()) {
final int comp = DBIDUtil.compare(iter1, iter2);
if (comp == 0) {
intersection++;
iter1.advance();
iter2.advance();
} else if (comp < 0) {
iter1.advance();
} else // iter2 < iter1
{
iter2.advance();
}
}
return intersection;
}
@Override
public double similarity(DBIDRef id1, DBIDRef id2) {
DBIDs neighbors1 = index.getNearestNeighborSet(id1);
DBIDs neighbors2 = index.getNearestNeighborSet(id2);
int intersection = countSharedNeighbors(neighbors1, neighbors2);
return (double) intersection / index.getNumberOfNeighbors();
}
@Override
public SimilarityFunction<? super T> getSimilarityFunction() {
return similarityFunction;
}
}
/**
* Parameterization class.
*
* @author Erich Schubert
*
* @apiviz.exclude
*
* @param <O> object type
*/
public static class Parameterizer<O> extends AbstractIndexBasedSimilarityFunction.Parameterizer<SharedNearestNeighborIndex.Factory<O, SharedNearestNeighborIndex<O>>> {
@Override
protected void makeOptions(Parameterization config) {
super.makeOptions(config);
configIndexFactory(config, SharedNearestNeighborIndex.Factory.class, SharedNearestNeighborPreprocessor.Factory.class);
}
@Override
protected FractionalSharedNearestNeighborSimilarityFunction<O> makeInstance() {
return new FractionalSharedNearestNeighborSimilarityFunction<>(factory);
}
}
}
|
