diff options
author | Andrej Shadura <andrewsh@debian.org> | 2019-03-09 22:30:41 +0000 |
---|---|---|
committer | Andrej Shadura <andrewsh@debian.org> | 2019-03-09 22:30:41 +0000 |
commit | 38212b3127e90751fb39cda34250bc11be62b76c (patch) | |
tree | dc1397346030e9695bd763dddc93b3be527cd643 /elki/src/test/java/de/lmu/ifi/dbs/elki/algorithm/clustering/kmeans/TestKMeansBisecting.java | |
parent | 337087b668d3a54f3afee3a9adb597a32e9f7e94 (diff) |
Import Upstream version 0.7.0
Diffstat (limited to 'elki/src/test/java/de/lmu/ifi/dbs/elki/algorithm/clustering/kmeans/TestKMeansBisecting.java')
-rw-r--r-- | elki/src/test/java/de/lmu/ifi/dbs/elki/algorithm/clustering/kmeans/TestKMeansBisecting.java | 91 |
1 files changed, 91 insertions, 0 deletions
diff --git a/elki/src/test/java/de/lmu/ifi/dbs/elki/algorithm/clustering/kmeans/TestKMeansBisecting.java b/elki/src/test/java/de/lmu/ifi/dbs/elki/algorithm/clustering/kmeans/TestKMeansBisecting.java new file mode 100644 index 00000000..06d55028 --- /dev/null +++ b/elki/src/test/java/de/lmu/ifi/dbs/elki/algorithm/clustering/kmeans/TestKMeansBisecting.java @@ -0,0 +1,91 @@ +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 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.kmeans.quality.WithinClusterVarianceQualityMeasure; +import de.lmu.ifi.dbs.elki.data.Clustering; +import de.lmu.ifi.dbs.elki.data.DoubleVector; +import de.lmu.ifi.dbs.elki.data.model.MeanModel; +import de.lmu.ifi.dbs.elki.database.Database; +import de.lmu.ifi.dbs.elki.utilities.ClassGenericsUtil; +import de.lmu.ifi.dbs.elki.utilities.optionhandling.parameterization.ListParameterization; + +/** + * Tests the KMeansBisecting + * + * @author Stephan Baier + */ +public class TestKMeansBisecting extends AbstractSimpleAlgorithmTest implements JUnit4Test { + /** + * Run KMeansBisecting with fixed parameters and compare cluster size to + * expected value. + */ + @Test + public void testKMeansBisectingClusterSize() { + Database db = makeSimpleDatabase(UNITTEST + "bisecting-test.csv", 300); + + // Setup algorithm + ListParameterization params = new ListParameterization(); + params.addParameter(KMeans.K_ID, 3); + params.addParameter(KMeans.SEED_ID, 0); + params.addParameter(BestOfMultipleKMeans.Parameterizer.TRIALS_ID, 5); + params.addParameter(BestOfMultipleKMeans.Parameterizer.KMEANS_ID, KMeansLloyd.class); + params.addParameter(BestOfMultipleKMeans.Parameterizer.QUALITYMEASURE_ID, WithinClusterVarianceQualityMeasure.class); + + KMeansBisecting<DoubleVector, MeanModel> kmeans = ClassGenericsUtil.parameterizeOrAbort(KMeansBisecting.class, params); + testParameterizationOk(params); + + // run KMedians on database + Clustering<MeanModel> result = kmeans.run(db); + testClusterSizes(result, new int[] { 103, 97, 100 }); + } + + /** + * Run KMeansBisecting with fixed parameters (k = 2) and compare f-measure to + * golden standard. + */ + @Test + public void testKMeansBisectingFMeasure() { + Database db = makeSimpleDatabase(UNITTEST + "bisecting-test.csv", 300); + + // Setup algorithm + ListParameterization params = new ListParameterization(); + params.addParameter(KMeans.K_ID, 2); + params.addParameter(KMeans.SEED_ID, 0); + params.addParameter(BestOfMultipleKMeans.Parameterizer.TRIALS_ID, 5); + params.addParameter(BestOfMultipleKMeans.Parameterizer.KMEANS_ID, KMeansLloyd.class); + params.addParameter(BestOfMultipleKMeans.Parameterizer.QUALITYMEASURE_ID, WithinClusterVarianceQualityMeasure.class); + + KMeansBisecting<DoubleVector, MeanModel> kmeans = ClassGenericsUtil.parameterizeOrAbort(KMeansBisecting.class, params); + testParameterizationOk(params); + + // run KMedians on database + Clustering<MeanModel> result = kmeans.run(db); + testFMeasure(db, result, 0.7408); + } +} |