Package de.lmu.ifi.dbs.elki.utilities.optionhandling.parameterization

Examples of de.lmu.ifi.dbs.elki.utilities.optionhandling.parameterization.ListParameterization

51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
   *
   * @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);

View Full Code Here
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
  @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.EPSILON_ID, 0.5);
    params.addParameter(DBSCAN.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);
View Full Code Here
54
55
56
57
58
59
60
61
62
63
64
65
66
   */
  @Test
  public void testSUBCLUResults() {
    Database db = makeSimpleDatabase(UNITTEST + "subspace-simple.csv", 600);

    ListParameterization params = new ListParameterization();
    params.addParameter(SUBCLU.EPSILON_ID, 0.001);
    params.addParameter(SUBCLU.MINPTS_ID, 100);

    // setup algorithm
    SUBCLU<DoubleVector> subclu = ClassGenericsUtil.parameterizeOrAbort(SUBCLU.class, params);
    testParameterizationOk(params);

View Full Code Here
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
   * @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);

View Full Code Here
81
82
83
84
85
86
87
88
89
90
91
92
93
  @Test
  public void testSUBCLUSubspaceOverlapping() {
    Database db = makeSimpleDatabase(UNITTEST + "subspace-overlapping-3-4d.ascii", 850);

    // Setup algorithm
    ListParameterization params = new ListParameterization();
    params.addParameter(SUBCLU.EPSILON_ID, 0.04);
    params.addParameter(SUBCLU.MINPTS_ID, 70);
    SUBCLU<DoubleVector> subclu = ClassGenericsUtil.parameterizeOrAbort(SUBCLU.class, params);
    testParameterizationOk(params);

    // run SUBCLU on database
    Clustering<SubspaceModel<DoubleVector>> result = subclu.run(db);
View Full Code Here
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
  @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.MINPTS_ID, 30);
    params.addParameter(DBSCAN.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
View Full Code Here
54
55
56
57
58
59
60
61
62
63
64
65
66
67
  @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
View Full Code Here
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
  @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
View Full Code Here
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
  @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.MINPTS_ID, 15);
    params.addParameter(DBSCAN.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
View Full Code Here
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
   */
  @Test
  public void testORCLUSResults() {
    Database db = makeSimpleDatabase(UNITTEST + "correlation-hierarchy.csv", 450);

    ListParameterization params = new ListParameterization();
    // these parameters are not picked too smartly - room for improvement.
    params.addParameter(ORCLUS.K_ID, 3);
    params.addParameter(ORCLUS.L_ID, 1);
    params.addParameter(ORCLUS.SEED_ID, 2);

    // setup algorithm
    ORCLUS<DoubleVector> orclus = ClassGenericsUtil.parameterizeOrAbort(ORCLUS.class, params);
    testParameterizationOk(params);

View Full Code Here
TOP

Related Classes of de.lmu.ifi.dbs.elki.utilities.optionhandling.parameterization.ListParameterization

  • de.lmu.ifi.dbs.elki.algorithm.AbstractSimpleAlgorithmTest
  • de.lmu.ifi.dbs.elki.algorithm.clustering.AbstractProjectedDBSCAN$Parameterizer
  • de.lmu.ifi.dbs.elki.algorithm.clustering.correlation.CASH
  • de.lmu.ifi.dbs.elki.algorithm.clustering.correlation.COPAC
  • de.lmu.ifi.dbs.elki.algorithm.clustering.correlation.COPAC$Parameterizer
  • de.lmu.ifi.dbs.elki.algorithm.clustering.correlation.ERiC
  • de.lmu.ifi.dbs.elki.algorithm.clustering.correlation.HiCO$Parameterizer
  • de.lmu.ifi.dbs.elki.algorithm.clustering.correlation.TestCASHResults
  • de.lmu.ifi.dbs.elki.algorithm.clustering.correlation.TestCOPACResults
  • de.lmu.ifi.dbs.elki.algorithm.clustering.correlation.TestERiCResults
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.