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
|
package de.lmu.ifi.dbs.elki.algorithm.outlier;
/*
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 de.lmu.ifi.dbs.elki.algorithm.AbstractDistanceBasedAlgorithm;
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.DBID;
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.query.knn.KNNResult;
import de.lmu.ifi.dbs.elki.database.relation.MaterializedRelation;
import de.lmu.ifi.dbs.elki.database.relation.Relation;
import de.lmu.ifi.dbs.elki.distance.distancefunction.DistanceFunction;
import de.lmu.ifi.dbs.elki.distance.distancevalue.NumberDistance;
import de.lmu.ifi.dbs.elki.logging.Logging;
import de.lmu.ifi.dbs.elki.logging.progress.FiniteProgress;
import de.lmu.ifi.dbs.elki.math.DoubleMinMax;
import de.lmu.ifi.dbs.elki.result.outlier.BasicOutlierScoreMeta;
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.documentation.Description;
import de.lmu.ifi.dbs.elki.utilities.documentation.Reference;
import de.lmu.ifi.dbs.elki.utilities.documentation.Title;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.OptionID;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.parameterization.Parameterization;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.parameters.IntParameter;
/**
* <p>
* Outlier Detection based on the distance of an object to its k nearest
* neighbor.
* </p>
*
* <p>
* Reference:<br>
* S. Ramaswamy, R. Rastogi, K. Shim: Efficient Algorithms for Mining Outliers
* from Large Data Sets.</br> In: Proc. of the Int. Conf. on Management of Data,
* Dallas, Texas, 2000.
* </p>
*
* @author Lisa Reichert
*
* @apiviz.has KNNQuery
*
* @param <O> the type of DatabaseObjects handled by this Algorithm
* @param <D> the type of Distance used by this Algorithm
*/
@Title("KNN outlier: Efficient Algorithms for Mining Outliers from Large Data Sets")
@Description("Outlier Detection based on the distance of an object to its k nearest neighbor.")
@Reference(authors = "S. Ramaswamy, R. Rastogi, K. Shim", title = "Efficient Algorithms for Mining Outliers from Large Data Sets", booktitle = "Proc. of the Int. Conf. on Management of Data, Dallas, Texas, 2000", url = "http://dx.doi.org/10.1145/342009.335437")
public class KNNOutlier<O, D extends NumberDistance<D, ?>> extends AbstractDistanceBasedAlgorithm<O, D, OutlierResult> implements OutlierAlgorithm {
/**
* The logger for this class.
*/
private static final Logging logger = Logging.getLogger(KNNOutlier.class);
/**
* Parameter to specify the k nearest neighbor
*/
public static final OptionID K_ID = OptionID.getOrCreateOptionID("knno.k", "k nearest neighbor");
/**
* The parameter k
*/
private int k;
/**
* Constructor for a single kNN query.
*
* @param distanceFunction distance function to use
* @param k Value of k
*/
public KNNOutlier(DistanceFunction<? super O, D> distanceFunction, int k) {
super(distanceFunction);
this.k = k;
}
/**
* Runs the algorithm in the timed evaluation part.
*/
public OutlierResult run(Database database, Relation<O> relation) {
final DistanceQuery<O, D> distanceQuery = database.getDistanceQuery(relation, getDistanceFunction());
KNNQuery<O, D> knnQuery = database.getKNNQuery(distanceQuery, k);
if(logger.isVerbose()) {
logger.verbose("Computing the kNN outlier degree (distance to the k nearest neighbor)");
}
FiniteProgress progressKNNDistance = logger.isVerbose() ? new FiniteProgress("kNN distance for objects", relation.size(), logger) : null;
DoubleMinMax minmax = new DoubleMinMax();
WritableDoubleDataStore knno_score = DataStoreUtil.makeDoubleStorage(relation.getDBIDs(), DataStoreFactory.HINT_STATIC);
// compute distance to the k nearest neighbor.
for(DBID id : relation.iterDBIDs()) {
// distance to the kth nearest neighbor
final KNNResult<D> knns = knnQuery.getKNNForDBID(id, k);
double dkn = knns.getKNNDistance().doubleValue();
knno_score.putDouble(id, dkn);
minmax.put(dkn);
if(progressKNNDistance != null) {
progressKNNDistance.incrementProcessed(logger);
}
}
if(progressKNNDistance != null) {
progressKNNDistance.ensureCompleted(logger);
}
Relation<Double> scoreres = new MaterializedRelation<Double>("kNN Outlier Score", "knn-outlier", TypeUtil.DOUBLE, knno_score, relation.getDBIDs());
OutlierScoreMeta meta = new BasicOutlierScoreMeta(minmax.getMin(), minmax.getMax(), 0.0, Double.POSITIVE_INFINITY, 0.0);
return new OutlierResult(meta, scoreres);
}
@Override
public TypeInformation[] getInputTypeRestriction() {
return TypeUtil.array(getDistanceFunction().getInputTypeRestriction());
}
@Override
protected Logging getLogger() {
return logger;
}
/**
* Parameterization class.
*
* @author Erich Schubert
*
* @apiviz.exclude
*/
public static class Parameterizer<O, D extends NumberDistance<D, ?>> extends AbstractDistanceBasedAlgorithm.Parameterizer<O, D> {
protected int k = 0;
@Override
protected void makeOptions(Parameterization config) {
super.makeOptions(config);
final IntParameter kP = new IntParameter(K_ID);
if(config.grab(kP)) {
k = kP.getValue();
}
}
@Override
protected KNNOutlier<O, D> makeInstance() {
return new KNNOutlier<O, D>(distanceFunction, k);
}
}
}
|
