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.distance.similarityfunction;
/*
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.Iterator;
import de.lmu.ifi.dbs.elki.database.ids.DBID;
import de.lmu.ifi.dbs.elki.database.ids.SetDBIDs;
import de.lmu.ifi.dbs.elki.database.relation.Relation;
import de.lmu.ifi.dbs.elki.distance.distancevalue.Distance;
import de.lmu.ifi.dbs.elki.distance.distancevalue.IntegerDistance;
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.uses Instance oneway - - «create»
*
* @param <O> object type
* @param <D> distance type
*/
// todo arthur comment class
public class SharedNearestNeighborSimilarityFunction<O, D extends Distance<D>> extends AbstractIndexBasedSimilarityFunction<O, SharedNearestNeighborIndex<O>, SetDBIDs, IntegerDistance> {
/**
* Constructor.
*
* @param indexFactory Index factory.
*/
public SharedNearestNeighborSimilarityFunction(SharedNearestNeighborIndex.Factory<O, SharedNearestNeighborIndex<O>> indexFactory) {
super(indexFactory);
}
@Override
public IntegerDistance getDistanceFactory() {
return IntegerDistance.FACTORY;
}
static protected int countSharedNeighbors(SetDBIDs neighbors1, SetDBIDs neighbors2) {
int intersection = 0;
Iterator<DBID> iter1 = neighbors1.iterator();
Iterator<DBID> iter2 = neighbors2.iterator();
DBID neighbors1ID = null;
DBID neighbors2ID = null;
if(iter1.hasNext()) {
neighbors1ID = iter1.next();
}
if(iter2.hasNext()) {
neighbors2ID = iter2.next();
}
while((iter1.hasNext() || iter2.hasNext()) && neighbors1ID != null && neighbors2ID != null) {
if(neighbors1ID.equals(neighbors2ID)) {
intersection++;
if(iter1.hasNext()) {
neighbors1ID = iter1.next();
}
else {
neighbors1ID = null;
}
if(iter2.hasNext()) {
neighbors2ID = iter2.next();
}
else {
neighbors2ID = null;
}
}
else if(neighbors2ID.compareTo(neighbors1ID) > 0) {
if(iter1.hasNext()) {
neighbors1ID = iter1.next();
}
else {
neighbors1ID = null;
}
}
else // neighbors1ID > neighbors2ID
{
if(iter2.hasNext()) {
neighbors2ID = iter2.next();
}
else {
neighbors2ID = null;
}
}
}
return intersection;
}
@SuppressWarnings("unchecked")
@Override
public <T extends O> Instance<T, D> instantiate(Relation<T> database) {
SharedNearestNeighborIndex<O> indexi = indexFactory.instantiate((Relation<O>) database);
return (Instance<T, D>) new Instance<O, D>((Relation<O>) database, indexi);
}
/**
* TODO: document
*
* @author Erich Schubert
*
* @apiviz.uses SharedNearestNeighborIndex
*
* @param <D>
*/
public static class Instance<O, D extends Distance<D>> extends AbstractIndexBasedSimilarityFunction.Instance<O, SharedNearestNeighborIndex<O>, SetDBIDs, IntegerDistance> {
public Instance(Relation<O> database, SharedNearestNeighborIndex<O> preprocessor) {
super(database, preprocessor);
}
@Override
public IntegerDistance similarity(DBID id1, DBID id2) {
SetDBIDs neighbors1 = index.getNearestNeighborSet(id1);
SetDBIDs neighbors2 = index.getNearestNeighborSet(id2);
return new IntegerDistance(countSharedNeighbors(neighbors1, neighbors2));
}
@Override
public IntegerDistance getDistanceFactory() {
return IntegerDistance.FACTORY;
}
}
/**
* Parameterization class.
*
* @author Erich Schubert
*
* @apiviz.exclude
*/
public static class Parameterizer<O, D extends Distance<D>> 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 SharedNearestNeighborSimilarityFunction<O, D> makeInstance() {
return new SharedNearestNeighborSimilarityFunction<O, D>(factory);
}
}
}
|
