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
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
|
package de.lmu.ifi.dbs.elki.algorithm.outlier;
/*
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 java.util.ArrayList;
import java.util.Vector;
import de.lmu.ifi.dbs.elki.data.NumberVector;
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.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.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.result.outlier.InvertedOutlierScoreMeta;
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.Description;
import de.lmu.ifi.dbs.elki.utilities.documentation.Reference;
import de.lmu.ifi.dbs.elki.utilities.documentation.Title;
import de.lmu.ifi.dbs.elki.utilities.pairs.IntIntPair;
/**
* BruteForce provides a naive brute force algorithm in which all k-subsets of
* dimensions are examined and calculates the sparsity coefficient to find
* outliers.
*
* The evolutionary approach is implemented as
* {@link de.lmu.ifi.dbs.elki.algorithm.outlier.AggarwalYuEvolutionary}.
*
* <p>
* Reference: <br />
* Outlier detection for high dimensional data<br />
* C.C. Aggarwal, P. S. Yu<br />
* International Conference on Management of Data Proceedings of the 2001 ACM
* SIGMOD international conference on Management of data 2001, Santa Barbara,
* California, United States
* </p>
*
* @author Ahmed Hettab
* @author Erich Schubert
*/
// TODO: progress logging!
@Title("BruteForce: Outlier detection for high dimensional data")
@Description("Examines all possible sets of k dimensional projections")
@Reference(authors = "C.C. Aggarwal, P. S. Yu", title = "Outlier detection for high dimensional data", booktitle = "Proc. ACM SIGMOD Int. Conf. on Management of Data (SIGMOD 2001), Santa Barbara, CA, 2001", url = "http://dx.doi.org/10.1145/375663.375668")
public class AggarwalYuNaive<V extends NumberVector<?, ?>> extends AbstractAggarwalYuOutlier<V> {
/**
* The logger for this class.
*/
private static final Logging logger = Logging.getLogger(AggarwalYuNaive.class);
/**
* Constructor.
*
* @param k K
* @param phi Phi
*/
public AggarwalYuNaive(int k, int phi) {
super(k, phi);
}
/**
* Run the algorithm on the given relation.
*
* @param relation Relation
* @return Outlier detection result
*/
public OutlierResult run(Relation<V> relation) {
final int dimensionality = DatabaseUtil.dimensionality(relation);
final int size = relation.size();
ArrayList<ArrayList<DBIDs>> ranges = buildRanges(relation);
ArrayList<Vector<IntIntPair>> Rk;
// Build a list of all subspaces
{
// R1 initial one-dimensional subspaces.
Rk = new ArrayList<Vector<IntIntPair>>();
// Set of all dim*phi ranges
ArrayList<IntIntPair> q = new ArrayList<IntIntPair>();
for(int i = 1; i <= dimensionality; i++) {
for(int j = 1; j <= phi; j++) {
IntIntPair s = new IntIntPair(i, j);
q.add(s);
// Add to first Rk
Vector<IntIntPair> v = new Vector<IntIntPair>();
v.add(s);
Rk.add(v);
}
}
// build Ri
for(int i = 2; i <= k; i++) {
ArrayList<Vector<IntIntPair>> Rnew = new ArrayList<Vector<IntIntPair>>();
for(int j = 0; j < Rk.size(); j++) {
Vector<IntIntPair> c = Rk.get(j);
for(IntIntPair pair : q) {
boolean invalid = false;
for(int t = 0; t < c.size(); t++) {
if(c.get(t).first == pair.first) {
invalid = true;
break;
}
}
if(!invalid) {
Vector<IntIntPair> neu = new Vector<IntIntPair>(c);
neu.add(pair);
Rnew.add(neu);
}
}
}
Rk = Rnew;
}
}
WritableDoubleDataStore sparsity = DataStoreUtil.makeDoubleStorage(relation.getDBIDs(), DataStoreFactory.HINT_HOT | DataStoreFactory.HINT_STATIC);
// calculate the sparsity coefficient
for(Vector<IntIntPair> sub : Rk) {
DBIDs ids = computeSubspace(sub, ranges);
final double sparsityC = sparsity(ids.size(), size, k);
if(sparsityC < 0) {
for(DBID id : ids) {
double prev = sparsity.doubleValue(id);
if(Double.isNaN(prev) || sparsityC < prev) {
sparsity.putDouble(id, sparsityC);
}
}
}
}
DoubleMinMax minmax = new DoubleMinMax();
for(DBID id : relation.iterDBIDs()) {
double val = sparsity.doubleValue(id);
if(Double.isNaN(val)) {
sparsity.putDouble(id, 0.0);
val = 0.0;
}
minmax.put(val);
}
Relation<Double> scoreResult = new MaterializedRelation<Double>("AggarwalYuNaive", "aggarwal-yu-outlier", TypeUtil.DOUBLE, sparsity, relation.getDBIDs());
OutlierScoreMeta meta = new InvertedOutlierScoreMeta(minmax.getMin(), minmax.getMax(), Double.NEGATIVE_INFINITY, 0.0);
return new OutlierResult(meta, scoreResult);
}
@Override
protected Logging getLogger() {
return logger;
}
/**
* Parameterization class.
*
* @author Erich Schubert
*
* @apiviz.exclude
*/
public static class Parameterizer<V extends NumberVector<?, ?>> extends AbstractAggarwalYuOutlier.Parameterizer {
@Override
protected AggarwalYuNaive<V> makeInstance() {
return new AggarwalYuNaive<V>(k, phi);
}
}
}
|
