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
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
|
package de.lmu.ifi.dbs.elki.algorithm.outlier.distance;
/*
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.algorithm.AbstractDistanceBasedAlgorithm;
import de.lmu.ifi.dbs.elki.algorithm.outlier.OutlierAlgorithm;
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.Database;
import de.lmu.ifi.dbs.elki.database.datastore.DataStoreFactory;
import de.lmu.ifi.dbs.elki.database.datastore.DataStoreUtil;
import de.lmu.ifi.dbs.elki.database.datastore.WritableDoubleDataStore;
import de.lmu.ifi.dbs.elki.database.ids.DBIDIter;
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.query.distance.DistanceQuery;
import de.lmu.ifi.dbs.elki.database.query.knn.KNNQuery;
import de.lmu.ifi.dbs.elki.database.relation.DoubleRelation;
import de.lmu.ifi.dbs.elki.database.relation.MaterializedDoubleRelation;
import de.lmu.ifi.dbs.elki.database.relation.Relation;
import de.lmu.ifi.dbs.elki.distance.distancefunction.DistanceFunction;
import de.lmu.ifi.dbs.elki.logging.Logging;
import de.lmu.ifi.dbs.elki.result.outlier.InvertedOutlierScoreMeta;
import de.lmu.ifi.dbs.elki.result.outlier.OutlierResult;
import de.lmu.ifi.dbs.elki.result.outlier.OutlierScoreMeta;
import de.lmu.ifi.dbs.elki.utilities.Alias;
import de.lmu.ifi.dbs.elki.utilities.documentation.Reference;
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.IntParameter;
/**
* Outlier detection based on the in-degree of the kNN graph.
*
* This is a curried version: instead of using a threshold T to obtain a binary
* decision, we use the computed value as outlier score; normalized by k to make
* the numbers more comparable across different parameterizations.
*
* Reference:
* <p>
* V. Hautamäki and I. Kärkkäinen and P. Fränti<br />
* Outlier detection using k-nearest neighbour graph<br />
* Proc. 17th Int. Conf. Pattern Recognition, ICPR 2004
* </p>
*
* @author Erich Schubert
* @since 0.6.0
*
* @param <O> Object type
*/
@Reference(authors = "V. Hautamäki and I. Kärkkäinen and P. Fränti", //
title = "Outlier detection using k-nearest neighbour graph", //
booktitle = "Proc. 17th Int. Conf. Pattern Recognition, ICPR 2004", //
url = "http://dx.doi.org/10.1109/ICPR.2004.1334558")
@Alias({ "de.lmu.ifi.dbs.elki.algorithm.outlier.ODIN" })
public class ODIN<O> extends AbstractDistanceBasedAlgorithm<O, OutlierResult> implements OutlierAlgorithm {
/**
* Class logger.
*/
private static final Logging LOG = Logging.getLogger(ODIN.class);
/**
* Number of neighbors for kNN graph.
*/
int k;
/**
* Constructor.
*
* @param distanceFunction Distance function
* @param k k parameter
*/
public ODIN(DistanceFunction<? super O> distanceFunction, int k) {
super(distanceFunction);
this.k = k + 1; // + query point
}
/**
* Run the ODIN algorithm
*
* @param database Database to run on.
* @param relation Relation to process.
* @return ODIN outlier result.
*/
public OutlierResult run(Database database, Relation<O> relation) {
// Get the query functions:
DistanceQuery<O> dq = database.getDistanceQuery(relation, getDistanceFunction());
KNNQuery<O> knnq = database.getKNNQuery(dq, k);
// Get the objects to process, and a data storage for counting and output:
DBIDs ids = relation.getDBIDs();
WritableDoubleDataStore scores = DataStoreUtil.makeDoubleStorage(ids, DataStoreFactory.HINT_DB, 0.);
double inc = 1. / (k - 1);
double min = Double.POSITIVE_INFINITY, max = 0.0;
// Process all objects
for(DBIDIter iter = ids.iter(); iter.valid(); iter.advance()) {
// Find the nearest neighbors (using an index, if available!)
DBIDs neighbors = knnq.getKNNForDBID(iter, k);
// For each neighbor, except ourselves, increase the in-degree:
for(DBIDIter nei = neighbors.iter(); nei.valid(); nei.advance()) {
if(DBIDUtil.equal(iter, nei)) {
continue;
}
final double value = scores.doubleValue(nei) + inc;
if(value < min) {
min = value;
}
if(value > max) {
max = value;
}
scores.put(nei, value);
}
}
// Wrap the result and add metadata.
OutlierScoreMeta meta = new InvertedOutlierScoreMeta(min, max, 0., inc * (ids.size() - 1), 1);
DoubleRelation rel = new MaterializedDoubleRelation("ODIN In-Degree", "odin", scores, ids);
return new OutlierResult(meta, rel);
}
@Override
public TypeInformation[] getInputTypeRestriction() {
return TypeUtil.array(getDistanceFunction().getInputTypeRestriction());
}
@Override
protected Logging getLogger() {
return LOG;
}
/**
* Parameterization class.
*
* @author Erich Schubert
*
* @apiviz.exclude
*
* @param <O> Object type
*/
public static class Parameterizer<O> extends AbstractDistanceBasedAlgorithm.Parameterizer<O> {
/**
* Parameter for the number of nearest neighbors:
*
* <pre>
* -odin.k <int>
* </pre>
*/
public static final OptionID K_ID = new OptionID("odin.k", "Number of neighbors to use for kNN graph.");
/**
* Number of nearest neighbors to use.
*/
int k;
@Override
protected void makeOptions(Parameterization config) {
super.makeOptions(config);
IntParameter param = new IntParameter(K_ID) //
.addConstraint(CommonConstraints.GREATER_EQUAL_ONE_INT);
if(config.grab(param)) {
k = param.intValue();
}
}
@Override
protected ODIN<O> makeInstance() {
return new ODIN<>(distanceFunction, k);
}
}
}
|
