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
|
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) 2014
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.DoubleDataStore;
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.result.outlier.OutlierResult;
import de.lmu.ifi.dbs.elki.result.outlier.OutlierScoreMeta;
import de.lmu.ifi.dbs.elki.result.outlier.ProbabilisticOutlierScore;
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.DoubleParameter;
/**
* Simple distance based outlier detection algorithms.
*
* Reference:
* <p>
* E.M. Knorr, R. T. Ng:<br />
* Algorithms for Mining Distance-Based Outliers in Large Datasets,<br />
* In: Procs Int. Conf. on Very Large Databases (VLDB'98), New York, USA, 1998.
* </p>
*
* @author Lisa Reichert
*
* @param <O> the type of DatabaseObjects handled by this Algorithm
*/
@Reference(authors = "E.M. Knorr, R. T. Ng", //
title = "Algorithms for Mining Distance-Based Outliers in Large Datasets", //
booktitle = "Procs Int. Conf. on Very Large Databases (VLDB'98), New York, USA, 1998")
public abstract class AbstractDBOutlier<O> extends AbstractDistanceBasedAlgorithm<O, OutlierResult> implements OutlierAlgorithm {
/**
* Radius parameter d.
*/
private double d;
/**
* Constructor with actual parameters.
*
* @param distanceFunction distance function to use
* @param d radius d value
*/
public AbstractDBOutlier(DistanceFunction<? super O> distanceFunction, double d) {
super(distanceFunction);
this.d = d;
}
/**
* Runs the algorithm in the timed evaluation part.
*
* @param database Database to process
* @param relation Relation to process
* @return Outlier result
*/
public OutlierResult run(Database database, Relation<O> relation) {
// Run the actual score process
DoubleDataStore dbodscore = computeOutlierScores(database, relation, d);
// Build result representation.
DoubleRelation scoreResult = new MaterializedDoubleRelation("Density-Based Outlier Detection", "db-outlier", dbodscore, relation.getDBIDs());
OutlierScoreMeta scoreMeta = new ProbabilisticOutlierScore();
return new OutlierResult(scoreMeta, scoreResult);
}
/**
* computes an outlier score for each object of the database.
*
* @param database Database
* @param relation Relation
* @param d distance
* @return computed scores
*/
protected abstract DoubleDataStore computeOutlierScores(Database database, Relation<O> relation, double d);
@Override
public TypeInformation[] getInputTypeRestriction() {
return TypeUtil.array(getDistanceFunction().getInputTypeRestriction());
}
/**
* Parameterization class.
*
* @author Erich Schubert
*
* @apiviz.exclude
*/
public abstract static class Parameterizer<O> extends AbstractDistanceBasedAlgorithm.Parameterizer<O> {
/**
* Parameter to specify the size of the D-neighborhood
*/
public static final OptionID D_ID = new OptionID("dbod.d", "size of the D-neighborhood");
/**
* Query radius
*/
protected double d;
@Override
protected void makeOptions(Parameterization config) {
super.makeOptions(config);
configD(config, distanceFunction);
}
/**
* Grab the 'd' configuration option.
*
* @param config Parameterization
*/
protected void configD(Parameterization config, DistanceFunction<?> distanceFunction) {
final DoubleParameter param = new DoubleParameter(D_ID) //
.addConstraint(CommonConstraints.GREATER_THAN_ZERO_DOUBLE);
if(config.grab(param)) {
d = param.getValue();
}
}
}
}
|
