diff options
Diffstat (limited to 'test/de/lmu/ifi/dbs/elki/algorithm/clustering/correlation')
5 files changed, 0 insertions, 536 deletions
diff --git a/test/de/lmu/ifi/dbs/elki/algorithm/clustering/correlation/TestCASHResults.java b/test/de/lmu/ifi/dbs/elki/algorithm/clustering/correlation/TestCASHResults.java deleted file mode 100644 index 62791b68..00000000 --- a/test/de/lmu/ifi/dbs/elki/algorithm/clustering/correlation/TestCASHResults.java +++ /dev/null @@ -1,96 +0,0 @@ -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) 2012 - 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.DoubleVector; -import de.lmu.ifi.dbs.elki.data.model.Model; -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; - -/** - * 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. - */ - @Test - public void testCASHResults() { - // Input - Database db = makeSimpleDatabase(UNITTEST + "hierarchical-3d2d1d.csv", 600, new ListParameterization(), 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<DoubleVector> cash = ClassGenericsUtil.parameterizeOrAbort(CASH.class, params); - testParameterizationOk(params); - - // run CASH on database - Clustering<Model> result = cash.run(db); - - testFMeasure(db, result, 0.490551); // with hierarchical pairs: 0.64102 - testClusterSizes(result, new int[] { 37, 71, 76, 442 }); - } - - /** - * Run CASH with fixed parameters and compare the result to a golden standard. - */ - @Test - public void testCASHEmbedded() { - // CASH input - Database db = makeSimpleDatabase(UNITTEST + "correlation-embedded-2-4d.ascii", 600, new ListParameterization(), 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<DoubleVector> 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 }); - } -}
\ No newline at end of file diff --git a/test/de/lmu/ifi/dbs/elki/algorithm/clustering/correlation/TestCOPACResults.java b/test/de/lmu/ifi/dbs/elki/algorithm/clustering/correlation/TestCOPACResults.java deleted file mode 100644 index 94c59557..00000000 --- a/test/de/lmu/ifi/dbs/elki/algorithm/clustering/correlation/TestCOPACResults.java +++ /dev/null @@ -1,114 +0,0 @@ -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) 2012 - 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.DBSCAN; -import de.lmu.ifi.dbs.elki.data.Clustering; -import de.lmu.ifi.dbs.elki.data.DoubleVector; -import de.lmu.ifi.dbs.elki.data.model.Model; -import de.lmu.ifi.dbs.elki.database.Database; -import de.lmu.ifi.dbs.elki.distance.distancevalue.DoubleDistance; -import de.lmu.ifi.dbs.elki.index.preprocessed.localpca.KNNQueryFilteredPCAIndex; -import de.lmu.ifi.dbs.elki.math.linearalgebra.pca.PCAFilteredRunner; -import de.lmu.ifi.dbs.elki.math.linearalgebra.pca.PCARunner; -import de.lmu.ifi.dbs.elki.math.linearalgebra.pca.PercentageEigenPairFilter; -import de.lmu.ifi.dbs.elki.math.linearalgebra.pca.WeightedCovarianceMatrixBuilder; -import de.lmu.ifi.dbs.elki.math.linearalgebra.pca.weightfunctions.ErfcWeight; -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 COPAC run, and compare the result with a clustering derived - * from the data set labels. This test ensures that COPAC 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 TestCOPACResults extends AbstractSimpleAlgorithmTest implements JUnit4Test { - /** - * Run COPAC with fixed parameters and compare the result to a golden - * standard. - * - * @throws ParameterException on errors. - */ - @Test - public void testCOPACResults() { - Database db = makeSimpleDatabase(UNITTEST + "correlation-hierarchy.csv", 450); - - // these parameters are not picked too smartly - room for improvement. - ListParameterization params = new ListParameterization(); - params.addParameter(COPAC.PARTITION_ALGORITHM_ID, DBSCAN.class); - params.addParameter(DBSCAN.Parameterizer.EPSILON_ID, 0.02); - params.addParameter(DBSCAN.Parameterizer.MINPTS_ID, 50); - params.addParameter(COPAC.PREPROCESSOR_ID, KNNQueryFilteredPCAIndex.Factory.class); - params.addParameter(KNNQueryFilteredPCAIndex.Factory.K_ID, 15); - - COPAC<DoubleVector, DoubleDistance> copac = ClassGenericsUtil.parameterizeOrAbort(COPAC.class, params); - testParameterizationOk(params); - - // run COPAC on database - Clustering<Model> result = copac.run(db); - - testFMeasure(db, result, 0.842521); - testClusterSizes(result, new int[] { 6, 16, 32, 196, 200 }); - } - - /** - * Run COPAC with fixed parameters and compare the result to a golden - * standard. - * - * @throws ParameterException on errors. - */ - @Test - public void testCOPACOverlap() { - Database db = makeSimpleDatabase(UNITTEST + "correlation-overlap-3-5d.ascii", 650); - - // Setup algorithm - ListParameterization params = new ListParameterization(); - params.addParameter(COPAC.PARTITION_ALGORITHM_ID, DBSCAN.class); - params.addParameter(DBSCAN.Parameterizer.EPSILON_ID, 0.5); - params.addParameter(DBSCAN.Parameterizer.MINPTS_ID, 20); - params.addParameter(COPAC.PREPROCESSOR_ID, KNNQueryFilteredPCAIndex.Factory.class); - params.addParameter(KNNQueryFilteredPCAIndex.Factory.K_ID, 45); - // PCA - params.addParameter(PCARunner.PCA_COVARIANCE_MATRIX, WeightedCovarianceMatrixBuilder.class); - params.addParameter(WeightedCovarianceMatrixBuilder.WEIGHT_ID, ErfcWeight.class); - params.addParameter(PCAFilteredRunner.PCA_EIGENPAIR_FILTER, PercentageEigenPairFilter.class); - params.addParameter(PercentageEigenPairFilter.ALPHA_ID, 0.8); - - COPAC<DoubleVector, DoubleDistance> copac = ClassGenericsUtil.parameterizeOrAbort(COPAC.class, params); - testParameterizationOk(params); - - Clustering<Model> result = copac.run(db); - testFMeasure(db, result, 0.84687864); - testClusterSizes(result, new int[] { 1, 22, 22, 29, 34, 158, 182, 202 }); - } -}
\ No newline at end of file diff --git a/test/de/lmu/ifi/dbs/elki/algorithm/clustering/correlation/TestERiCResults.java b/test/de/lmu/ifi/dbs/elki/algorithm/clustering/correlation/TestERiCResults.java deleted file mode 100644 index 76e8cca2..00000000 --- a/test/de/lmu/ifi/dbs/elki/algorithm/clustering/correlation/TestERiCResults.java +++ /dev/null @@ -1,130 +0,0 @@ -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) 2012 - 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.DBSCAN; -import de.lmu.ifi.dbs.elki.data.Clustering; -import de.lmu.ifi.dbs.elki.data.DoubleVector; -import de.lmu.ifi.dbs.elki.data.model.CorrelationModel; -import de.lmu.ifi.dbs.elki.database.Database; -import de.lmu.ifi.dbs.elki.distance.distancefunction.correlation.ERiCDistanceFunction; -import de.lmu.ifi.dbs.elki.index.preprocessed.localpca.KNNQueryFilteredPCAIndex; -import de.lmu.ifi.dbs.elki.math.linearalgebra.pca.PCAFilteredRunner; -import de.lmu.ifi.dbs.elki.math.linearalgebra.pca.PCARunner; -import de.lmu.ifi.dbs.elki.math.linearalgebra.pca.PercentageEigenPairFilter; -import de.lmu.ifi.dbs.elki.math.linearalgebra.pca.RelativeEigenPairFilter; -import de.lmu.ifi.dbs.elki.math.linearalgebra.pca.WeightedCovarianceMatrixBuilder; -import de.lmu.ifi.dbs.elki.math.linearalgebra.pca.weightfunctions.ErfcWeight; -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 ERiC run, and compare the result with a clustering derived - * from the data set labels. This test ensures that ERiC 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 TestERiCResults extends AbstractSimpleAlgorithmTest implements JUnit4Test { - /** - * Run ERiC with fixed parameters and compare the result to a golden standard. - * - * @throws ParameterException on errors. - */ - @Test - public void testERiCResults() { - Database db = makeSimpleDatabase(UNITTEST + "hierarchical-3d2d1d.csv", 600); - - // ERiC - ListParameterization params = new ListParameterization(); - params.addParameter(COPAC.PARTITION_ALGORITHM_ID, DBSCAN.class); - params.addParameter(DBSCAN.Parameterizer.MINPTS_ID, 30); - params.addParameter(DBSCAN.Parameterizer.EPSILON_ID, 0); - // ERiC Distance function in DBSCAN: - params.addParameter(COPAC.PARTITION_DISTANCE_ID, ERiCDistanceFunction.class); - params.addParameter(ERiCDistanceFunction.DELTA_ID, 0.20); - params.addParameter(ERiCDistanceFunction.TAU_ID, 0.04); - // Preprocessing via Local PCA: - params.addParameter(COPAC.PREPROCESSOR_ID, KNNQueryFilteredPCAIndex.Factory.class); - params.addParameter(KNNQueryFilteredPCAIndex.Factory.K_ID, 50); - // PCA - params.addParameter(PCARunner.PCA_COVARIANCE_MATRIX, WeightedCovarianceMatrixBuilder.class); - params.addParameter(WeightedCovarianceMatrixBuilder.WEIGHT_ID, ErfcWeight.class); - params.addParameter(PCAFilteredRunner.PCA_EIGENPAIR_FILTER, RelativeEigenPairFilter.class); - params.addParameter(RelativeEigenPairFilter.EIGENPAIR_FILTER_RALPHA, 1.60); - - ERiC<DoubleVector> eric = ClassGenericsUtil.parameterizeOrAbort(ERiC.class, params); - testParameterizationOk(params); - - // run ERiC on database - Clustering<CorrelationModel<DoubleVector>> result = eric.run(db); - - testFMeasure(db, result, 0.714207); // Hierarchical pairs scored: 0.9204825 - testClusterSizes(result, new int[] { 109, 184, 307 }); - } - - /** - * Run ERiC with fixed parameters and compare the result to a golden standard. - * - * @throws ParameterException on errors. - */ - @Test - public void testERiCOverlap() { - Database db = makeSimpleDatabase(UNITTEST + "correlation-overlap-3-5d.ascii", 650); - - // Setup algorithm - ListParameterization params = new ListParameterization(); - // ERiC - params.addParameter(COPAC.PARTITION_ALGORITHM_ID, DBSCAN.class); - params.addParameter(DBSCAN.Parameterizer.MINPTS_ID, 15); - params.addParameter(DBSCAN.Parameterizer.EPSILON_ID, 0); - // ERiC Distance function in DBSCAN: - params.addParameter(COPAC.PARTITION_DISTANCE_ID, ERiCDistanceFunction.class); - params.addParameter(ERiCDistanceFunction.DELTA_ID, 1.0); - params.addParameter(ERiCDistanceFunction.TAU_ID, 1.0); - // Preprocessing via Local PCA: - params.addParameter(COPAC.PREPROCESSOR_ID, KNNQueryFilteredPCAIndex.Factory.class); - params.addParameter(KNNQueryFilteredPCAIndex.Factory.K_ID, 45); - // PCA - params.addParameter(PCARunner.PCA_COVARIANCE_MATRIX, WeightedCovarianceMatrixBuilder.class); - params.addParameter(WeightedCovarianceMatrixBuilder.WEIGHT_ID, ErfcWeight.class); - params.addParameter(PCAFilteredRunner.PCA_EIGENPAIR_FILTER, PercentageEigenPairFilter.class); - params.addParameter(PercentageEigenPairFilter.ALPHA_ID, 0.6); - - ERiC<DoubleVector> eric = ClassGenericsUtil.parameterizeOrAbort(ERiC.class, params); - testParameterizationOk(params); - - // run ERiC on database - Clustering<CorrelationModel<DoubleVector>> result = eric.run(db); - testFMeasure(db, result, 0.831136946); - testClusterSizes(result, new int[] { 29, 189, 207, 225 }); - } -}
\ No newline at end of file diff --git a/test/de/lmu/ifi/dbs/elki/algorithm/clustering/correlation/TestFourCResults.java b/test/de/lmu/ifi/dbs/elki/algorithm/clustering/correlation/TestFourCResults.java deleted file mode 100644 index 8604a5f0..00000000 --- a/test/de/lmu/ifi/dbs/elki/algorithm/clustering/correlation/TestFourCResults.java +++ /dev/null @@ -1,98 +0,0 @@ -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) 2012 - 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.AbstractProjectedDBSCAN; -import de.lmu.ifi.dbs.elki.data.Clustering; -import de.lmu.ifi.dbs.elki.data.DoubleVector; -import de.lmu.ifi.dbs.elki.data.model.Model; -import de.lmu.ifi.dbs.elki.database.Database; -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 4C run, and compare the result with a clustering derived from - * the data set labels. This test ensures that 4C 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 TestFourCResults extends AbstractSimpleAlgorithmTest implements JUnit4Test { - /** - * Run 4F with fixed parameters and compare the result to a golden standard. - * - * @throws ParameterException on errors. - */ - @Test - public void testFourCResults() { - Database db = makeSimpleDatabase(UNITTEST + "hierarchical-3d2d1d.csv", 600); - - // Setup 4C - ListParameterization params = new ListParameterization(); - params.addParameter(AbstractProjectedDBSCAN.EPSILON_ID, 0.30); - params.addParameter(AbstractProjectedDBSCAN.MINPTS_ID, 20); - params.addParameter(AbstractProjectedDBSCAN.LAMBDA_ID, 5); - - FourC<DoubleVector> fourc = ClassGenericsUtil.parameterizeOrAbort(FourC.class, params); - testParameterizationOk(params); - - // run 4C on database - Clustering<Model> result = fourc.run(db); - - testFMeasure(db, result, 0.498048); // Hierarchical pairs scored: 0.79467 - testClusterSizes(result, new int[] { 5, 595 }); - } - - /** - * Run ERiC with fixed parameters and compare the result to a golden standard. - * - * @throws ParameterException on errors. - */ - @Test - public void testFourCOverlap() { - Database db = makeSimpleDatabase(UNITTEST + "correlation-overlap-3-5d.ascii", 650); - - // Setup algorithm - ListParameterization params = new ListParameterization(); - // 4C - params.addParameter(AbstractProjectedDBSCAN.EPSILON_ID, 1.2); - params.addParameter(AbstractProjectedDBSCAN.MINPTS_ID, 5); - params.addParameter(AbstractProjectedDBSCAN.LAMBDA_ID, 3); - - FourC<DoubleVector> fourc = ClassGenericsUtil.parameterizeOrAbort(FourC.class, params); - testParameterizationOk(params); - - // run 4C on database - Clustering<Model> result = fourc.run(db); - testFMeasure(db, result, 0.48305405); - testClusterSizes(result, new int[] { 65, 70, 515 }); - } -}
\ No newline at end of file diff --git a/test/de/lmu/ifi/dbs/elki/algorithm/clustering/correlation/TestORCLUSResults.java b/test/de/lmu/ifi/dbs/elki/algorithm/clustering/correlation/TestORCLUSResults.java deleted file mode 100644 index 5cdb09c9..00000000 --- a/test/de/lmu/ifi/dbs/elki/algorithm/clustering/correlation/TestORCLUSResults.java +++ /dev/null @@ -1,98 +0,0 @@ -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) 2012 - 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.DoubleVector; -import de.lmu.ifi.dbs.elki.data.model.Model; -import de.lmu.ifi.dbs.elki.database.Database; -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; - -/** - * Performs a full ORCLUS run, and compares the result with a clustering derived - * from the data set labels. This test ensures that ORCLUS performance doesn't - * unexpectedly drop on this data set (and also ensures that the algorithms - * work, as a side effect). - * - * @author Elke Achtert - * @author Katharina Rausch - */ -public class TestORCLUSResults extends AbstractSimpleAlgorithmTest implements JUnit4Test { - /** - * Run ORCLUS with fixed parameters and compare the result to a golden - * standard. - * - * @throws ParameterException on errors. - */ - @Test - public void testORCLUSResults() { - Database db = makeSimpleDatabase(UNITTEST + "correlation-hierarchy.csv", 450); - - ListParameterization params = new ListParameterization(); - params.addParameter(ORCLUS.Parameterizer.K_ID, 3); - params.addParameter(ORCLUS.Parameterizer.L_ID, 1); - params.addParameter(ORCLUS.Parameterizer.SEED_ID, 2); - - // setup algorithm - ORCLUS<DoubleVector> orclus = ClassGenericsUtil.parameterizeOrAbort(ORCLUS.class, params); - testParameterizationOk(params); - - // run ORCLUS on database - Clustering<Model> result = orclus.run(db); - - testFMeasure(db, result, 0.6361108); // Hierarchical pairs scored: 0.789113 - testClusterSizes(result, new int[] { 19, 33, 398 }); - } - - /** - * Run ORCLUS with fixed parameters and compare the result to a golden - * standard. - * - * @throws ParameterException on errors. - */ - @Test - public void testORCLUSSkewedDisjoint() { - Database db = makeSimpleDatabase(UNITTEST + "correlation-skewed-disjoint-3-5d.ascii", 601); - - // Setup algorithm - ListParameterization params = new ListParameterization(); - params.addParameter(ORCLUS.Parameterizer.K_ID, 3); - params.addParameter(ORCLUS.Parameterizer.L_ID, 4); - params.addParameter(ORCLUS.Parameterizer.SEED_ID, 9); - - ORCLUS<DoubleVector> orclus = ClassGenericsUtil.parameterizeOrAbort(ORCLUS.class, params); - testParameterizationOk(params); - - // run ORCLUS on database - Clustering<Model> result = orclus.run(db); - testFMeasure(db, result, 0.8687866); - testClusterSizes(result, new int[] { 170, 200, 231 }); - } -}
\ No newline at end of file |