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
|
package de.lmu.ifi.dbs.elki.algorithm.clustering.correlation;
/*
This file is part of ELKI:
Environment for Developing KDD-Applications Supported by Index-Structures
Copyright (C) 2011
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.data.Clustering;
import de.lmu.ifi.dbs.elki.data.model.Model;
import de.lmu.ifi.dbs.elki.database.Database;
import de.lmu.ifi.dbs.elki.datasource.FileBasedDatabaseConnection;
import de.lmu.ifi.dbs.elki.datasource.parser.ParameterizationFunctionLabelParser;
import de.lmu.ifi.dbs.elki.utilities.ClassGenericsUtil;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.ParameterException;
import de.lmu.ifi.dbs.elki.utilities.optionhandling.parameterization.ListParameterization;
/**
* Perform a full CASH run, and compare the result with a clustering derived
* from the data set labels. This test ensures that CASH performance doesn't
* unexpectedly drop on this data set (and also ensures that the algorithms
* work, as a side effect).
*
* @author Erich Schubert
* @author Katharina Rausch
*/
public class TestCASHResults extends AbstractSimpleAlgorithmTest implements JUnit4Test {
/**
* Run CASH with fixed parameters and compare the result to a golden standard.
*
* @throws ParameterException on errors.
*/
@Test
public void testCASHResults() {
ListParameterization inp = new ListParameterization();
// CASH input
inp.addParameter(FileBasedDatabaseConnection.PARSER_ID, ParameterizationFunctionLabelParser.class);
// Input
Database db = makeSimpleDatabase(UNITTEST + "hierarchical-3d2d1d.csv", 600, inp, null);
// CASH parameters
ListParameterization params = new ListParameterization();
params.addParameter(CASH.JITTER_ID, 0.7);
params.addParameter(CASH.MINPTS_ID, 50);
params.addParameter(CASH.MAXLEVEL_ID, 25);
params.addFlag(CASH.ADJUST_ID);
// setup algorithm
CASH cash = ClassGenericsUtil.parameterizeOrAbort(CASH.class, params);
testParameterizationOk(params);
// run CASH on database
Clustering<Model> result = cash.run(db);
testFMeasureHierarchical(db, result, 0.64102);
testClusterSizes(result, new int[] { 37, 71, 76, 442 });
// Old heap scored worse?
// testFMeasureHierarchical(db, result, 0.638727);
// testClusterSizes(result, new int[] { 13, 65, 74, 75, 442 });
}
/**
* Run CASH with fixed parameters and compare the result to a golden standard.
*
* @throws ParameterException on errors.
*/
@Test
public void testCASHEmbedded() {
// CASH input
ListParameterization inp = new ListParameterization();
inp.addParameter(FileBasedDatabaseConnection.PARSER_ID, ParameterizationFunctionLabelParser.class);
Database db = makeSimpleDatabase(UNITTEST + "correlation-embedded-2-4d.ascii", 600, inp, null);
// CASH parameters
ListParameterization params = new ListParameterization();
params.addParameter(CASH.JITTER_ID, 0.7);
params.addParameter(CASH.MINPTS_ID, 160);
params.addParameter(CASH.MAXLEVEL_ID, 40);
// setup algorithm
CASH cash = ClassGenericsUtil.parameterizeOrAbort(CASH.class, params);
testParameterizationOk(params);
// run CASH on database
Clustering<Model> result = cash.run(db);
testFMeasure(db, result, 0.443246);
testClusterSizes(result, new int[] { 169, 196, 235 });
}
}
|
