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
|
package de.lmu.ifi.dbs.elki.algorithm.clustering.kmeans;
/*
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.ArrayList;
import java.util.List;
import de.lmu.ifi.dbs.elki.algorithm.clustering.kmeans.initialization.KMeansInitialization;
import de.lmu.ifi.dbs.elki.data.Cluster;
import de.lmu.ifi.dbs.elki.data.Clustering;
import de.lmu.ifi.dbs.elki.data.NumberVector;
import de.lmu.ifi.dbs.elki.data.model.KMeansModel;
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.WritableIntegerDataStore;
import de.lmu.ifi.dbs.elki.database.ids.DBIDUtil;
import de.lmu.ifi.dbs.elki.database.ids.DBIDs;
import de.lmu.ifi.dbs.elki.database.ids.ModifiableDBIDs;
import de.lmu.ifi.dbs.elki.database.relation.Relation;
import de.lmu.ifi.dbs.elki.distance.distancefunction.NumberVectorDistanceFunction;
import de.lmu.ifi.dbs.elki.logging.Logging;
import de.lmu.ifi.dbs.elki.logging.progress.IndefiniteProgress;
import de.lmu.ifi.dbs.elki.logging.statistics.DoubleStatistic;
import de.lmu.ifi.dbs.elki.logging.statistics.LongStatistic;
import de.lmu.ifi.dbs.elki.logging.statistics.StringStatistic;
import de.lmu.ifi.dbs.elki.math.linearalgebra.Vector;
/**
* A hybrid k-means algorithm, alternating between MacQueen-style incremental
* processing and Lloyd-Style batch steps.
*
* @author Erich Schubert
* @since 0.5.0
*
* @apiviz.has KMeansModel
*
* @param <V> vector datatype
*/
public class KMeansHybridLloydMacQueen<V extends NumberVector> extends AbstractKMeans<V, KMeansModel> {
/**
* The logger for this class.
*/
private static final Logging LOG = Logging.getLogger(KMeansHybridLloydMacQueen.class);
/**
* Key for statistics logging.
*/
private static final String KEY = KMeansHybridLloydMacQueen.class.getName();
/**
* Constructor.
*
* @param distanceFunction distance function
* @param k k parameter
* @param maxiter Maxiter parameter
* @param initializer Initialization method
*/
public KMeansHybridLloydMacQueen(NumberVectorDistanceFunction<? super V> distanceFunction, int k, int maxiter, KMeansInitialization<? super V> initializer) {
super(distanceFunction, k, maxiter, initializer);
}
@Override
public Clustering<KMeansModel> run(Database database, Relation<V> relation) {
if(relation.size() <= 0) {
return new Clustering<>("k-Means Clustering", "kmeans-clustering");
}
// Choose initial means
if(LOG.isStatistics()) {
LOG.statistics(new StringStatistic(KEY + ".initialization", initializer.toString()));
}
List<Vector> means = initializer.chooseInitialMeans(database, relation, k, getDistanceFunction(), Vector.FACTORY);
// Setup cluster assignment store
List<ModifiableDBIDs> clusters = new ArrayList<>();
for(int i = 0; i < k; i++) {
clusters.add(DBIDUtil.newHashSet((int) (relation.size() * 2. / k)));
}
WritableIntegerDataStore assignment = DataStoreUtil.makeIntegerStorage(relation.getDBIDs(), DataStoreFactory.HINT_TEMP | DataStoreFactory.HINT_HOT, -1);
double[] varsum = new double[k];
IndefiniteProgress prog = LOG.isVerbose() ? new IndefiniteProgress("K-Means iteration", LOG) : null;
DoubleStatistic varstat = LOG.isStatistics() ? new DoubleStatistic(this.getClass().getName() + ".variance-sum") : null;
int iteration = 0;
for(; maxiter <= 0 || iteration < maxiter; iteration += 2) {
{ // MacQueen
LOG.incrementProcessed(prog);
boolean changed = macQueenIterate(relation, means, clusters, assignment, varsum);
logVarstat(varstat, varsum);
if(!changed) {
break;
}
}
{ // Lloyd
LOG.incrementProcessed(prog);
boolean changed = assignToNearestCluster(relation, means, clusters, assignment, varsum);
logVarstat(varstat, varsum);
// Stop if no cluster assignment changed.
if(!changed) {
break;
}
// Recompute means.
means = means(clusters, means, relation);
}
}
LOG.setCompleted(prog);
if(LOG.isStatistics()) {
LOG.statistics(new LongStatistic(KEY + ".iterations", iteration));
}
// Wrap result
Clustering<KMeansModel> result = new Clustering<>("k-Means Clustering", "kmeans-clustering");
for(int i = 0; i < clusters.size(); i++) {
DBIDs ids = clusters.get(i);
if(ids.size() == 0) {
continue;
}
KMeansModel model = new KMeansModel(means.get(i), varsum[i]);
result.addToplevelCluster(new Cluster<>(ids, model));
}
return result;
}
@Override
protected Logging getLogger() {
return LOG;
}
/**
* Parameterization class.
*
* @author Erich Schubert
*
* @apiviz.exclude
*/
public static class Parameterizer<V extends NumberVector> extends AbstractKMeans.Parameterizer<V> {
@Override
protected Logging getLogger() {
return LOG;
}
@Override
protected KMeansHybridLloydMacQueen<V> makeInstance() {
return new KMeansHybridLloydMacQueen<>(distanceFunction, k, maxiter, initializer);
}
}
}
|
