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
|
package de.lmu.ifi.dbs.elki.algorithm.clustering;
/*
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.algorithm.AbstractAlgorithm;
import de.lmu.ifi.dbs.elki.algorithm.clustering.subspace.PROCLUS;
import de.lmu.ifi.dbs.elki.data.Clustering;
import de.lmu.ifi.dbs.elki.data.NumberVector;
import de.lmu.ifi.dbs.elki.database.Database;
import de.lmu.ifi.dbs.elki.database.QueryUtil;
import de.lmu.ifi.dbs.elki.database.query.distance.DistanceQuery;
import de.lmu.ifi.dbs.elki.distance.distancefunction.DistanceFunction;
import de.lmu.ifi.dbs.elki.distance.distancefunction.minkowski.EuclideanDistanceFunction;
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.constraints.CommonConstraints;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.parameterization.Parameterization;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.parameters.IntParameter;
/**
* Abstract superclass for projected clustering algorithms, like {@link PROCLUS}
* and {@link de.lmu.ifi.dbs.elki.algorithm.clustering.correlation.ORCLUS}.
*
* @author Elke Achtert
*
* @param <R> the result we return
* @param <V> the type of FeatureVector handled by this Algorithm
*/
public abstract class AbstractProjectedClustering<R extends Clustering<?>, V extends NumberVector> extends AbstractAlgorithm<R> implements ClusteringAlgorithm<R> {
/**
* Holds the value of {@link Parameterizer#K_ID}.
*/
protected int k;
/**
* Holds the value of {@link Parameterizer#K_I_ID}.
*/
protected int k_i;
/**
* Holds the value of {@link Parameterizer#L_ID}.
*/
protected int l;
/**
* The Euclidean distance function.
*/
private DistanceFunction<? super V> distanceFunction = EuclideanDistanceFunction.STATIC;
/**
* Internal constructor.
*
* @param k K parameter
* @param k_i K_i parameter
* @param l L parameter
*/
public AbstractProjectedClustering(int k, int k_i, int l) {
super();
this.k = k;
this.k_i = k_i;
this.l = l;
}
/**
* Returns the distance function.
*
* @return the distance function
*/
protected DistanceFunction<? super V> getDistanceFunction() {
return distanceFunction;
}
/**
* Returns the distance function.
*
* @return the distance function
*/
protected DistanceQuery<V> getDistanceQuery(Database database) {
return QueryUtil.getDistanceQuery(database, distanceFunction);
}
/**
* Parameterization class.
*
* @author Erich Schubert
*
* @apiviz.exclude
*/
public abstract static class Parameterizer extends AbstractParameterizer {
/**
* Parameter to specify the number of clusters to find, must be an integer
* greater than 0.
* <p>
* Key: {@code -projectedclustering.k}
* </p>
*/
public static final OptionID K_ID = new OptionID("projectedclustering.k", "The number of clusters to find.");
/**
* Parameter to specify the multiplier for the initial number of seeds, must
* be an integer greater than 0.
* <p>
* Default value: {@code 30}
* </p>
* <p>
* Key: {@code -projectedclustering.k_i}
* </p>
*/
public static final OptionID K_I_ID = new OptionID("projectedclustering.k_i", "The multiplier for the initial number of seeds.");
/**
* Parameter to specify the dimensionality of the clusters to find, must be
* an integer greater than 0.
* <p>
* Key: {@code -projectedclustering.l}
* </p>
*/
public static final OptionID L_ID = new OptionID("projectedclustering.l", "The dimensionality of the clusters to find.");
protected int k;
protected int k_i;
protected int l;
/**
* Get the parameter k, see {@link #K_ID}
*
* @param config Parameterization
*/
protected void configK(Parameterization config) {
IntParameter kP = new IntParameter(K_ID);
kP.addConstraint(CommonConstraints.GREATER_EQUAL_ONE_INT);
if(config.grab(kP)) {
k = kP.getValue();
}
}
/**
* Get the parameter k_i, see {@link #K_I_ID}
*
* @param config Parameterization
*/
protected void configKI(Parameterization config) {
IntParameter k_iP = new IntParameter(K_I_ID, 30);
k_iP.addConstraint(CommonConstraints.GREATER_EQUAL_ONE_INT);
if(config.grab(k_iP)) {
k_i = k_iP.getValue();
}
}
/**
* Get the parameter l, see {@link #L_ID}
*
* @param config Parameterization
*/
protected void configL(Parameterization config) {
IntParameter lP = new IntParameter(L_ID);
lP.addConstraint(CommonConstraints.GREATER_EQUAL_ONE_INT);
if(config.grab(lP)) {
l = lP.getValue();
}
}
}
}
|
