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.evaluation;
/*
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 java.util.Collection;
import java.util.Iterator;
import java.util.regex.Pattern;
import de.lmu.ifi.dbs.elki.algorithm.clustering.trivial.ByLabelClustering;
import de.lmu.ifi.dbs.elki.data.Cluster;
import de.lmu.ifi.dbs.elki.data.Clustering;
import de.lmu.ifi.dbs.elki.data.type.NoSupportedDataTypeException;
import de.lmu.ifi.dbs.elki.evaluation.clustering.EvaluateClustering;
import de.lmu.ifi.dbs.elki.evaluation.histogram.ComputeOutlierHistogram;
import de.lmu.ifi.dbs.elki.evaluation.outlier.OutlierPrecisionAtKCurve;
import de.lmu.ifi.dbs.elki.evaluation.outlier.OutlierPrecisionRecallCurve;
import de.lmu.ifi.dbs.elki.evaluation.outlier.OutlierROCCurve;
import de.lmu.ifi.dbs.elki.evaluation.outlier.OutlierRankingEvaluation;
import de.lmu.ifi.dbs.elki.logging.Logging;
import de.lmu.ifi.dbs.elki.result.HierarchicalResult;
import de.lmu.ifi.dbs.elki.result.Result;
import de.lmu.ifi.dbs.elki.result.ResultUtil;
import de.lmu.ifi.dbs.elki.result.outlier.OutlierResult;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.AbstractParameterizer;
import de.lmu.ifi.dbs.elki.utilities.scaling.LinearScaling;
/**
* Evaluator that tries to auto-run a number of evaluation methods.
*
* @author Erich Schubert
*
* @apiviz.landmark
*
* @apiviz.uses OutlierResult
* @apiviz.uses Clustering
* @apiviz.composedOf OutlierROCCurve
* @apiviz.composedOf OutlierPrecisionAtKCurve
* @apiviz.composedOf OutlierPrecisionRecallCurve
* @apiviz.composedOf ComputeOutlierHistogram
* @apiviz.composedOf EvaluateClustering
*/
public class AutomaticEvaluation implements Evaluator {
/**
* Class logger
*/
private static final Logging LOG = Logging.getLogger(AutomaticEvaluation.class);
@Override
public void processNewResult(HierarchicalResult baseResult, Result newResult) {
autoEvaluateClusterings(baseResult, newResult);
autoEvaluateOutliers(baseResult, newResult);
}
protected void autoEvaluateOutliers(HierarchicalResult baseResult, Result newResult) {
Collection<OutlierResult> outliers = ResultUtil.filterResults(newResult, OutlierResult.class);
if(LOG.isDebugging()) {
LOG.debug("Number of new outlier results: " + outliers.size());
}
if(outliers.size() > 0) {
ResultUtil.ensureClusteringResult(ResultUtil.findDatabase(baseResult), baseResult);
Collection<Clustering<?>> clusterings = ResultUtil.filterResults(baseResult, Clustering.class);
if(clusterings.size() == 0) {
LOG.warning("Could not find a clustering result, even after running 'ensureClusteringResult'?!?");
return;
}
Clustering<?> basec = clusterings.iterator().next();
// Find minority class label
int min = Integer.MAX_VALUE;
int total = 0;
String label = null;
if(basec.getAllClusters().size() > 1) {
for(Cluster<?> c : basec.getAllClusters()) {
final int csize = c.getIDs().size();
total += csize;
if(csize < min) {
min = csize;
label = c.getName();
}
}
}
if(label == null) {
LOG.warning("Could not evaluate outlier results, as I could not find a minority label.");
return;
}
if(min == 1) {
LOG.warning("The minority class label had a single object. Try using 'ClassLabelFilter' to identify the class label column.");
}
if(min > 0.05 * total) {
LOG.warning("The minority class I discovered (labeled '" + label + "') has " + (min * 100. / total) + "% of objects. Outlier classes should be more rare!");
}
LOG.verbose("Evaluating using minority class: " + label);
Pattern pat = Pattern.compile("^" + Pattern.quote(label) + "$");
// Evaluate rankings.
new OutlierRankingEvaluation(pat).processNewResult(baseResult, newResult);
// Compute ROC curve
new OutlierROCCurve(pat).processNewResult(baseResult, newResult);
// Compute Precision at k
new OutlierPrecisionAtKCurve(pat, min << 1).processNewResult(baseResult, newResult);
// Compute ROC curve
new OutlierPrecisionRecallCurve(pat).processNewResult(baseResult, newResult);
// Compute outlier histogram
new ComputeOutlierHistogram(pat, 50, new LinearScaling(), false).processNewResult(baseResult, newResult);
}
}
protected void autoEvaluateClusterings(HierarchicalResult baseResult, Result newResult) {
Collection<Clustering<?>> clusterings = ResultUtil.filterResults(newResult, Clustering.class);
if(LOG.isDebugging()) {
LOG.warning("Number of new clustering results: " + clusterings.size());
}
for(Iterator<Clustering<?>> c = clusterings.iterator(); c.hasNext();) {
Clustering<?> test = c.next();
if("allinone-clustering".equals(test.getShortName())) {
c.remove();
}
else if("allinnoise-clustering".equals(test.getShortName())) {
c.remove();
}
else if("bylabel-clustering".equals(test.getShortName())) {
c.remove();
}
else if("bymodel-clustering".equals(test.getShortName())) {
c.remove();
}
}
if(clusterings.size() > 0) {
try {
new EvaluateClustering(new ByLabelClustering(), false, true).processNewResult(baseResult, newResult);
}
catch(NoSupportedDataTypeException e) {
// Pass - the data probably did not have labels.
}
}
}
/**
* Parameterization class
*
* @author Erich Schubert
*
* @apiviz.exclude
*/
public static class Parameterizer extends AbstractParameterizer {
@Override
protected AutomaticEvaluation makeInstance() {
return new AutomaticEvaluation();
}
}
}
|
