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
|
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.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.ids.DBIDs;
import de.lmu.ifi.dbs.elki.database.query.distance.DistanceQuery;
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.PrimitiveDistanceFunction;
import de.lmu.ifi.dbs.elki.distance.distancevalue.NumberDistance;
import de.lmu.ifi.dbs.elki.logging.Logging;
import de.lmu.ifi.dbs.elki.math.DoubleMinMax;
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.QuotientOutlierScoreMeta;
import de.lmu.ifi.dbs.elki.utilities.documentation.Reference;
import de.lmu.ifi.dbs.elki.utilities.documentation.Title;
/**
* The Spatial Outlier Factor (SOF) is a spatial
* {@link de.lmu.ifi.dbs.elki.algorithm.outlier.LOF LOF} variation.
*
* Since the "reachability distance" of LOF cannot be used canonically in the
* bichromatic case, this part of LOF is dropped and the exact distance is used
* instead.
*
* <p>
* Huang, T., Qin, X.<br>
* Detecting outliers in spatial database.<br>
* In: Proc. 3rd International Conference on Image and Graphics,
* Hong Kong, China.
* </p>
*
* A LOF variation simplified with reachDist(o,p) == dist(o,p).
*
* @author Ahmed Hettab
*
* @param <N> Neighborhood object type
* @param <O> Attribute object type
* @param <D> Distance type
*/
@Title("Spatial Outlier Factor")
@Reference(authors = "Huang, T., Qin, X.", title = "Detecting outliers in spatial database", booktitle = "Proc. 3rd International Conference on Image and Graphics", url = "http://dx.doi.org/10.1109/ICIG.2004.53")
public class SOF<N, O, D extends NumberDistance<D, ?>> extends AbstractDistanceBasedSpatialOutlier<N, O, D> {
/**
* The logger for this class.
*/
private static final Logging logger = Logging.getLogger(SOF.class);
/**
* Constructor.
*
* @param npred Neighborhood predicate
* @param nonSpatialDistanceFunction Distance function on non-spatial
* attributes
*/
public SOF(NeighborSetPredicate.Factory<N> npred, PrimitiveDistanceFunction<O, D> nonSpatialDistanceFunction) {
super(npred, nonSpatialDistanceFunction);
}
@Override
protected Logging getLogger() {
return logger;
}
/**
* The main run method
*
* @param database Database to use (actually unused)
* @param spatial Relation for neighborhood
* @param relation Attributes to evaluate
* @return Outlier result
*/
public OutlierResult run(Database database, Relation<N> spatial, Relation<O> relation) {
final NeighborSetPredicate npred = getNeighborSetPredicateFactory().instantiate(spatial);
DistanceQuery<O, D> distFunc = getNonSpatialDistanceFunction().instantiate(relation);
WritableDoubleDataStore lrds = DataStoreUtil.makeDoubleStorage(relation.getDBIDs(), DataStoreFactory.HINT_TEMP | DataStoreFactory.HINT_HOT);
WritableDoubleDataStore lofs = DataStoreUtil.makeDoubleStorage(relation.getDBIDs(), DataStoreFactory.HINT_STATIC);
DoubleMinMax lofminmax = new DoubleMinMax();
// Compute densities
for(DBID id : relation.iterDBIDs()) {
DBIDs neighbors = npred.getNeighborDBIDs(id);
double avg = 0;
for(DBID n : neighbors) {
avg += distFunc.distance(id, n).doubleValue();
}
double lrd = 1 / (avg / neighbors.size());
if (Double.isNaN(lrd)) {
lrd = 0;
}
lrds.putDouble(id, lrd);
}
// Compute density quotients
for(DBID id : relation.iterDBIDs()) {
DBIDs neighbors = npred.getNeighborDBIDs(id);
double avg = 0;
for(DBID n : neighbors) {
avg += lrds.doubleValue(n);
}
final double lrd = (avg / neighbors.size()) / lrds.doubleValue(id);
if (!Double.isNaN(lrd)) {
lofs.putDouble(id, lrd);
lofminmax.put(lrd);
} else {
lofs.putDouble(id, 0.0);
}
}
// Build result representation.
Relation<Double> scoreResult = new MaterializedRelation<Double>("Spatial Outlier Factor", "sof-outlier", TypeUtil.DOUBLE, lofs, relation.getDBIDs());
OutlierScoreMeta scoreMeta = new QuotientOutlierScoreMeta(lofminmax.getMin(), lofminmax.getMax(), 0.0, Double.POSITIVE_INFINITY, 1.0);
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
* @param <D> Distance type
*/
public static class Parameterizer<N, O, D extends NumberDistance<D, ?>> extends AbstractDistanceBasedSpatialOutlier.Parameterizer<N, O, D> {
@Override
protected SOF<N, O, D> makeInstance() {
return new SOF<N, O, D>(npredf, distanceFunction);
}
}
}
|
