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
|
package de.lmu.ifi.dbs.elki.algorithm.outlier.spatial;
/*
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.outlier.spatial.neighborhood.NeighborSetPredicate;
import de.lmu.ifi.dbs.elki.data.NumberVector;
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.datastore.DataStoreFactory;
import de.lmu.ifi.dbs.elki.database.datastore.DataStoreUtil;
import de.lmu.ifi.dbs.elki.database.datastore.WritableDataStore;
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.ids.DBIDIter;
import de.lmu.ifi.dbs.elki.database.ids.DBIDs;
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.math.DoubleMinMax;
import de.lmu.ifi.dbs.elki.math.linearalgebra.Centroid;
import de.lmu.ifi.dbs.elki.math.linearalgebra.CovarianceMatrix;
import de.lmu.ifi.dbs.elki.math.linearalgebra.Matrix;
import de.lmu.ifi.dbs.elki.math.linearalgebra.Vector;
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.DatabaseUtil;
import de.lmu.ifi.dbs.elki.utilities.documentation.Reference;
/**
* Mean Approach is used to discover spatial outliers with multiple attributes.
*
* <p>
* Reference:<br>
* Chang-Tien Lu and Dechang Chen and Yufeng Kou:<br>
* Detecting Spatial Outliers with Multiple Attributes<br>
* in 15th IEEE International Conference on Tools with Artificial Intelligence,
* 2003
* </p>
*
* <p>
* Implementation note: attribute standardization is not used; this is
* equivalent to using the
* {@link de.lmu.ifi.dbs.elki.datasource.filter.normalization.AttributeWiseVarianceNormalization
* AttributeWiseVarianceNormalization} filter.
* </p>
*
* @author Ahmed Hettab
*
* @param <N> Spatial Vector
* @param <O> Attribute Vector
*/
@Reference(authors = "Chang-Tien Lu and Dechang Chen and Yufeng Kou", title = "Detecting Spatial Outliers with Multiple Attributes", booktitle = "Proc. 15th IEEE International Conference on Tools with Artificial Intelligence, 2003", url = "http://dx.doi.org/10.1109/TAI.2003.1250179")
public class CTLuMeanMultipleAttributes<N, O extends NumberVector<?, ?>> extends AbstractNeighborhoodOutlier<N> {
/**
* logger
*/
public static final Logging logger = Logging.getLogger(CTLuMeanMultipleAttributes.class);
/**
* Constructor
*
* @param npredf Neighborhood predicate
*/
public CTLuMeanMultipleAttributes(NeighborSetPredicate.Factory<N> npredf) {
super(npredf);
}
@Override
protected Logging getLogger() {
return logger;
}
public OutlierResult run(Relation<N> spatial, Relation<O> attributes) {
if(logger.isDebugging()) {
logger.debug("Dimensionality: " + DatabaseUtil.dimensionality(attributes));
}
final NeighborSetPredicate npred = getNeighborSetPredicateFactory().instantiate(spatial);
CovarianceMatrix covmaker = new CovarianceMatrix(DatabaseUtil.dimensionality(attributes));
WritableDataStore<Vector> deltas = DataStoreUtil.makeStorage(attributes.getDBIDs(), DataStoreFactory.HINT_TEMP, Vector.class);
for(DBIDIter iditer = attributes.iterDBIDs(); iditer.valid(); iditer.advance()) {
DBID id = iditer.getDBID();
final O obj = attributes.get(id);
final DBIDs neighbors = npred.getNeighborDBIDs(id);
// TODO: remove object itself from neighbors?
// Mean vector "g"
Vector mean = Centroid.make(attributes, neighbors);
// Delta vector "h"
Vector delta = obj.getColumnVector().minus(mean);
deltas.put(id, delta);
covmaker.put(delta);
}
// Finalize covariance matrix:
Vector mean = covmaker.getMeanVector();
Matrix cmati = covmaker.destroyToSampleMatrix().inverse();
DoubleMinMax minmax = new DoubleMinMax();
WritableDoubleDataStore scores = DataStoreUtil.makeDoubleStorage(attributes.getDBIDs(), DataStoreFactory.HINT_STATIC);
for(DBIDIter iditer = attributes.iterDBIDs(); iditer.valid(); iditer.advance()) {
DBID id = iditer.getDBID();
Vector temp = deltas.get(id).minus(mean);
final double score = temp.transposeTimesTimes(cmati, temp);
minmax.put(score);
scores.putDouble(id, score);
}
Relation<Double> scoreResult = new MaterializedRelation<Double>("mean multiple attributes spatial outlier", "mean-multipleattributes-outlier", TypeUtil.DOUBLE, scores, attributes.getDBIDs());
OutlierScoreMeta scoreMeta = new BasicOutlierScoreMeta(minmax.getMin(), minmax.getMax(), 0.0, Double.POSITIVE_INFINITY, 0);
OutlierResult or = new OutlierResult(scoreMeta, scoreResult);
or.addChildResult(npred);
return or;
}
@Override
public TypeInformation[] getInputTypeRestriction() {
return TypeUtil.array(getNeighborSetPredicateFactory().getInputTypeRestriction(), TypeUtil.NUMBER_VECTOR_FIELD);
}
/**
* Parameterization class.
*
* @author Ahmed Hettab
*
* @apiviz.exclude
*
* @param <N> Neighborhood type
* @param <O> Attribute object type
*/
public static class Parameterizer<N, O extends NumberVector<?, ?>> extends AbstractNeighborhoodOutlier.Parameterizer<N> {
@Override
protected CTLuMeanMultipleAttributes<N, O> makeInstance() {
return new CTLuMeanMultipleAttributes<N, O>(npredf);
}
}
}
|
