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.utilities.scaling.outlier;
/*
This file is part of ELKI:
Environment for Developing KDD-Applications Supported by Index-Structures
Copyright (C) 2015
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 java.util.Arrays;
import de.lmu.ifi.dbs.elki.database.ids.DBIDIter;
import de.lmu.ifi.dbs.elki.database.relation.DoubleRelation;
import de.lmu.ifi.dbs.elki.math.statistics.distribution.Distribution;
import de.lmu.ifi.dbs.elki.math.statistics.distribution.estimator.meta.BestFitEstimator;
import de.lmu.ifi.dbs.elki.result.outlier.InvertedOutlierScoreMeta;
import de.lmu.ifi.dbs.elki.result.outlier.OutlierResult;
import de.lmu.ifi.dbs.elki.utilities.datastructures.arraylike.ArrayLikeUtil;
import de.lmu.ifi.dbs.elki.utilities.datastructures.arraylike.NumberArrayAdapter;
import de.lmu.ifi.dbs.elki.utilities.documentation.Reference;
import de.lmu.ifi.dbs.elki.utilities.exceptions.AbortException;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.AbstractParameterizer;
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.DoubleParameter;
/**
* CDF based outlier score scaling.
*
* Enhanced version of the scaling proposed in:
* <p>
* H.-P. Kriegel, P. Kröger, E. Schubert, A. Zimek<br />
* Interpreting and Unifying Outlier Scores<br />
* Proc. 11th SIAM International Conference on Data Mining (SDM), Mesa, AZ, 2011
* </p>
*
* See also:
* <p>
* Hans-Peter Kriegel, Peer Kröger, Erich Schubert, Arthur Zimek<br />
* Outlier Detection in Arbitrarily Oriented Subspaces<br />
* in: Proc. IEEE International Conference on Data Mining (ICDM 2012)
* </p>
*
* @author Erich Schubert
*/
@Reference(authors = "H.-P. Kriegel, P. Kröger, E. Schubert, A. Zimek", title = "Interpreting and Unifying Outlier Scores", booktitle = "Proc. 11th SIAM International Conference on Data Mining (SDM), Mesa, AZ, 2011", url = "http://siam.omnibooksonline.com/2011datamining/data/papers/018.pdf")
public class COPOutlierScaling implements OutlierScalingFunction {
/**
* Phi parameter.
*/
private double phi = 0.;
/**
* Score distribution.
*/
private Distribution dist;
/**
* Inversion flag.
*/
private boolean inverted = false;
/**
* Constructor.
*
* @param phi Phi parameter
*/
public COPOutlierScaling(double phi) {
super();
this.phi = phi;
}
/**
* Secondary reference.
*/
@Reference(authors = "Hans-Peter Kriegel, Peer Kröger, Erich Schubert, Arthur Zimek", title = "Outlier Detection in Arbitrarily Oriented Subspaces", booktitle = "Proc. IEEE International Conference on Data Mining (ICDM 2012)")
public static final void secondReference() {
// Dummy, reference attachment point only.
}
@Override
public double getScaled(double value) {
if (dist == null) {
throw new AbortException("Programming error: outlier scaling not initialized.");
}
double s = inverted ? (1 - dist.cdf(value)) : dist.cdf(value);
return (phi > 0.) ? (phi * s) / (1 - s + phi) : s;
}
@Override
public double getMin() {
return 0.;
}
@Override
public double getMax() {
return 1.;
}
@Override
public void prepare(OutlierResult or) {
double[] s;
{
DoubleRelation scores = or.getScores();
s = new double[scores.size()];
int i = 0;
for (DBIDIter id = scores.iterDBIDs(); id.valid(); id.advance(), i++) {
s[i] = scores.doubleValue(id);
}
}
Arrays.sort(s);
dist = BestFitEstimator.STATIC.estimate(s, ArrayLikeUtil.DOUBLEARRAYADAPTER);
inverted = (or.getOutlierMeta() instanceof InvertedOutlierScoreMeta);
}
@Override
public <A> void prepare(A array, NumberArrayAdapter<?, A> adapter) {
double[] s = ArrayLikeUtil.toPrimitiveDoubleArray(array, adapter);
Arrays.sort(s);
dist = BestFitEstimator.STATIC.estimate(s, ArrayLikeUtil.DOUBLEARRAYADAPTER);
inverted = false; // Not supported
}
/**
* Parameterization class.
*
* @author Erich Schubert
*
* @apiviz.exclude
*/
public static class Parameterizer extends AbstractParameterizer {
/**
* Phi parameter.
*/
public static final OptionID PHI_ID = new OptionID("copscaling.phi", "Phi parameter, expected rate of outliers. Set to 0 to use raw CDF values.");
/**
* Phi value.
*/
private double phi = 0.;
@Override
protected void makeOptions(Parameterization config) {
super.makeOptions(config);
DoubleParameter phiP = new DoubleParameter(PHI_ID);
if (config.grab(phiP)) {
phi = phiP.doubleValue();
}
}
@Override
protected COPOutlierScaling makeInstance() {
return new COPOutlierScaling(phi);
}
}
}
|
