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
|
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) 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.database.ids.DBIDIter;
import de.lmu.ifi.dbs.elki.database.relation.DoubleRelation;
import de.lmu.ifi.dbs.elki.math.DoubleMinMax;
import de.lmu.ifi.dbs.elki.math.MeanVariance;
import de.lmu.ifi.dbs.elki.result.outlier.OutlierResult;
import de.lmu.ifi.dbs.elki.utilities.datastructures.arraylike.NumberArrayAdapter;
import de.lmu.ifi.dbs.elki.utilities.documentation.Reference;
/**
* Normalization used by HeDES
*
* @author Erich Schubert
*/
@Reference(authors = "H. V. Nguyen, H. H. Ang, V. Gopalkrishnan", title = "Mining Outliers with Ensemble of Heterogeneous Detectors on Random Subspaces", booktitle = "Proc. 15th International Conference on Database Systems for Advanced Applications (DASFAA 2010)", url = "http://dx.doi.org/10.1007/978-3-642-12026-8_29")
public class HeDESNormalizationOutlierScaling implements OutlierScalingFunction {
/**
* Mean
*/
double mean;
/**
* Standard deviation
*/
double stddev;
/**
* Minimum after scaling
*/
double scaledmin;
/**
* Maximum after scaling
*/
double scaledmax;
@Override
public void prepare(OutlierResult or) {
MeanVariance mv = new MeanVariance();
DoubleMinMax minmax = new DoubleMinMax();
DoubleRelation scores = or.getScores();
for (DBIDIter id = scores.iterDBIDs(); id.valid(); id.advance()) {
double val = scores.doubleValue(id);
if (!Double.isNaN(val) && !Double.isInfinite(val)) {
mv.put(val);
minmax.put(val);
}
}
mean = mv.getMean();
stddev = mv.getSampleStddev();
scaledmax = getScaled(minmax.getMax());
scaledmin = getScaled(minmax.getMin());
}
@Override
public <A> void prepare(A array, NumberArrayAdapter<?, A> adapter) {
MeanVariance mv = new MeanVariance();
DoubleMinMax minmax = new DoubleMinMax();
final int size = adapter.size(array);
for (int i = 0; i < size; i++) {
double val = adapter.getDouble(array, i);
if (!Double.isNaN(val) && !Double.isInfinite(val)) {
mv.put(val);
minmax.put(val);
}
}
mean = mv.getMean();
stddev = mv.getSampleStddev();
scaledmax = getScaled(minmax.getMax());
scaledmin = getScaled(minmax.getMin());
}
@Override
public double getMax() {
return scaledmax;
}
@Override
public double getMin() {
return scaledmin;
}
@Override
public double getScaled(double value) {
assert (stddev > 0 || (value == mean)) : "prepare() was not run prior to using the scaling function.";
if (stddev > 0.) {
return (value - mean) / stddev;
} else {
return 0.;
}
}
}
|
