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;
/*
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.AbstractAlgorithm;
import de.lmu.ifi.dbs.elki.algorithm.clustering.EM;
import de.lmu.ifi.dbs.elki.data.Clustering;
import de.lmu.ifi.dbs.elki.data.NumberVector;
import de.lmu.ifi.dbs.elki.data.model.EMModel;
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.relation.MaterializedRelation;
import de.lmu.ifi.dbs.elki.database.relation.Relation;
import de.lmu.ifi.dbs.elki.logging.Logging;
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.ClassGenericsUtil;
import de.lmu.ifi.dbs.elki.utilities.documentation.Description;
import de.lmu.ifi.dbs.elki.utilities.documentation.Title;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.AbstractParameterizer;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.parameterization.Parameterization;
/**
* outlier detection algorithm using EM Clustering. If an object does not belong
* to any cluster it is supposed to be an outlier. If the probability for an
* object to belong to the most probable cluster is still relatively low this
* object is an outlier.
*
* @author Lisa Reichert
*
* @apiviz.has EM
*
* @param <V> Vector type
*/
// TODO: re-use an existing EM when present?
@Title("EM Outlier: Outlier Detection based on the generic EM clustering")
@Description("The outlier score assigned is based on the highest cluster probability obtained from EM clustering.")
public class EMOutlier<V extends NumberVector<V, ?>> extends AbstractAlgorithm<OutlierResult> implements OutlierAlgorithm {
/**
* The logger for this class.
*/
private static final Logging logger = Logging.getLogger(EMOutlier.class);
/**
* Inner algorithm.
*/
private EM<V> emClustering;
/**
* Constructor with an existing em clustering algorithm.
*
* @param emClustering EM clustering algorithm to use.
*/
public EMOutlier(EM<V> emClustering) {
super();
this.emClustering = emClustering;
}
/**
* 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<V> relation) {
Clustering<EMModel<V>> emresult = emClustering.run(database, relation);
double globmax = 0.0;
WritableDoubleDataStore emo_score = DataStoreUtil.makeDoubleStorage(relation.getDBIDs(), DataStoreFactory.HINT_TEMP | DataStoreFactory.HINT_HOT);
for(DBIDIter iditer = relation.iterDBIDs(); iditer.valid(); iditer.advance()) {
double maxProb = Double.POSITIVE_INFINITY;
double[] probs = emClustering.getProbClusterIGivenX(iditer);
for(double prob : probs) {
maxProb = Math.min(1 - prob, maxProb);
}
emo_score.putDouble(iditer, maxProb);
globmax = Math.max(maxProb, globmax);
}
Relation<Double> scoreres = new MaterializedRelation<Double>("EM outlier scores", "em-outlier", TypeUtil.DOUBLE, emo_score, relation.getDBIDs());
OutlierScoreMeta meta = new ProbabilisticOutlierScore(0.0, globmax);
// combine results.
OutlierResult result = new OutlierResult(meta, scoreres);
// TODO: add a keep-EM flag?
result.addChildResult(emresult);
return result;
}
@Override
public TypeInformation[] getInputTypeRestriction() {
return TypeUtil.array(TypeUtil.NUMBER_VECTOR_FIELD);
}
@Override
protected Logging getLogger() {
return logger;
}
/**
* Parameterization class.
*
* @author Erich Schubert
*
* @apiviz.exclude
*/
public static class Parameterizer<V extends NumberVector<V, ?>> extends AbstractParameterizer {
protected EM<V> em = null;
@Override
protected void makeOptions(Parameterization config) {
super.makeOptions(config);
Class<EM<V>> cls = ClassGenericsUtil.uglyCastIntoSubclass(EM.class);
em = config.tryInstantiate(cls);
}
@Override
protected EMOutlier<V> makeInstance() {
return new EMOutlier<V>(em);
}
}
}
|