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
|
package de.lmu.ifi.dbs.elki.algorithm.clustering.hierarchical;
/*
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 org.junit.Test;
import de.lmu.ifi.dbs.elki.JUnit4Test;
import de.lmu.ifi.dbs.elki.algorithm.AbstractSimpleAlgorithmTest;
import de.lmu.ifi.dbs.elki.algorithm.clustering.hierarchical.extraction.ExtractFlatClusteringFromHierarchy;
import de.lmu.ifi.dbs.elki.data.Clustering;
import de.lmu.ifi.dbs.elki.database.Database;
import de.lmu.ifi.dbs.elki.result.Result;
import de.lmu.ifi.dbs.elki.utilities.ClassGenericsUtil;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.parameterization.ListParameterization;
import de.lmu.ifi.dbs.elki.workflow.AlgorithmStep;
/**
* Perform agglomerative hierarchical clustering, using the naive algorithm.
*
* @author Erich Schubert
* @since 0.6.0
*/
public class AGNESTest extends AbstractSimpleAlgorithmTest implements JUnit4Test {
// TODO: add more data sets.
/**
* Run agglomerative hierarchical clustering with fixed parameters and compare
* the result to a golden standard.
*/
@Test
public void testSingleLink() {
Database db = makeSimpleDatabase(UNITTEST + "single-link-effect.ascii", 638);
// Setup algorithm
ListParameterization params = new ListParameterization();
params.addParameter(ExtractFlatClusteringFromHierarchy.Parameterizer.MINCLUSTERS_ID, 3);
params.addParameter(AlgorithmStep.Parameterizer.ALGORITHM_ID, AGNES.class);
params.addParameter(AGNES.Parameterizer.LINKAGE_ID, SingleLinkageMethod.class);
ExtractFlatClusteringFromHierarchy c = ClassGenericsUtil.parameterizeOrAbort(ExtractFlatClusteringFromHierarchy.class, params);
testParameterizationOk(params);
// run clustering algorithm on database
Result result = c.run(db);
Clustering<?> clustering = findSingleClustering(result);
testFMeasure(db, clustering, 0.6829722);
testClusterSizes(clustering, new int[] { 9, 200, 429 });
}
/**
* Run agglomerative hierarchical clustering with fixed parameters and compare
* the result to a golden standard.
*/
@Test
public void testWard() {
Database db = makeSimpleDatabase(UNITTEST + "single-link-effect.ascii", 638);
// Setup algorithm
ListParameterization params = new ListParameterization();
params.addParameter(ExtractFlatClusteringFromHierarchy.Parameterizer.MINCLUSTERS_ID, 3);
params.addParameter(AlgorithmStep.Parameterizer.ALGORITHM_ID, AGNES.class);
ExtractFlatClusteringFromHierarchy c = ClassGenericsUtil.parameterizeOrAbort(ExtractFlatClusteringFromHierarchy.class, params);
testParameterizationOk(params);
// run clustering algorithm on database
Result result = c.run(db);
Clustering<?> clustering = findSingleClustering(result);
testFMeasure(db, clustering, 0.93866265);
testClusterSizes(clustering, new int[] { 200, 211, 227 });
}
/**
* Run agglomerative hierarchical clustering with fixed parameters and compare
* the result to a golden standard.
*/
@Test
public void testGroupAverage() {
Database db = makeSimpleDatabase(UNITTEST + "single-link-effect.ascii", 638);
// Setup algorithm
ListParameterization params = new ListParameterization();
params.addParameter(ExtractFlatClusteringFromHierarchy.Parameterizer.MINCLUSTERS_ID, 3);
params.addParameter(AlgorithmStep.Parameterizer.ALGORITHM_ID, AGNES.class);
params.addParameter(AGNES.Parameterizer.LINKAGE_ID, GroupAverageLinkageMethod.class);
ExtractFlatClusteringFromHierarchy c = ClassGenericsUtil.parameterizeOrAbort(ExtractFlatClusteringFromHierarchy.class, params);
testParameterizationOk(params);
// run clustering algorithm on database
Result result = c.run(db);
Clustering<?> clustering = findSingleClustering(result);
testFMeasure(db, clustering, 0.93866265);
testClusterSizes(clustering, new int[] { 200, 211, 227 });
}
/**
* Run agglomerative hierarchical clustering with fixed parameters and compare
* the result to a golden standard.
*/
@Test
public void testCompleteLink() {
Database db = makeSimpleDatabase(UNITTEST + "single-link-effect.ascii", 638);
// Setup algorithm
ListParameterization params = new ListParameterization();
params.addParameter(ExtractFlatClusteringFromHierarchy.Parameterizer.MINCLUSTERS_ID, 3);
params.addParameter(AlgorithmStep.Parameterizer.ALGORITHM_ID, AGNES.class);
params.addParameter(AGNES.Parameterizer.LINKAGE_ID, CompleteLinkageMethod.class);
ExtractFlatClusteringFromHierarchy c = ClassGenericsUtil.parameterizeOrAbort(ExtractFlatClusteringFromHierarchy.class, params);
testParameterizationOk(params);
// run clustering algorithm on database
Result result = c.run(db);
Clustering<?> clustering = findSingleClustering(result);
testFMeasure(db, clustering, 0.938167802);
testClusterSizes(clustering, new int[] { 200, 217, 221 });
}
}
|
