Examples with NormalDistribution de.lmu.ifi.dbs.elki.math.statistics.distribution.NormalDistribution used on opensource projects

Example 1 with NormalDistribution

use of de.lmu.ifi.dbs.elki.math.statistics.distribution.NormalDistribution in project elki by elki-project.

the class BestFitEstimatorTest method testNormalDistribution.

@Test
public void testNormalDistribution() {
    BestFitEstimator est = init();
    Random r = new Random(0L);
    double[] data = new double[10000];
    for (int i = 0; i < data.length; i++) {
        data[i] = 2 + 3 * r.nextGaussian();
    }
    Distribution edist = est.estimate(data, DoubleArrayAdapter.STATIC);
    assertEquals("Wrong class of distribution", NormalDistribution.class, edist.getClass());
    NormalDistribution good = (NormalDistribution) edist;
    assertEquals("Mean not as expected from trimmed estimator.", 2., good.getMean(), 2e-2);
    assertEquals("Stddev not as expected from trimmed estimator.", 3., good.getStddev(), 4e-2);
}

Example 2 with NormalDistribution

use of de.lmu.ifi.dbs.elki.math.statistics.distribution.NormalDistribution in project elki by elki-project.

the class WinsorizingEstimatorTest method testNormalDistribution.

@Test
public void testNormalDistribution() {
    final double trim = .01;
    NormalMOMEstimator mom = NormalMOMEstimator.STATIC;
    // We could instantiate directly, but we also want to cover the
    // parameterizer class.
    ListParameterization config = new ListParameterization();
    config.addParameter(WinsorizingEstimator.Parameterizer.INNER_ID, mom);
    config.addParameter(WinsorizingEstimator.Parameterizer.WINSORIZE_ID, trim);
    WinsorizingEstimator<NormalDistribution> est = ClassGenericsUtil.parameterizeOrAbort(WinsorizingEstimator.class, config);
    Random r = new Random(0L);
    double[] data = new double[10000];
    final int corrupt = (int) Math.floor(data.length * trim * .5);
    for (int i = 0; i < data.length; i++) {
        data[i] = i < corrupt ? 1e10 : r.nextGaussian();
    }
    NormalDistribution bad = mom.estimate(data, DoubleArrayAdapter.STATIC);
    NormalDistribution good = est.estimate(data, DoubleArrayAdapter.STATIC);
    assertEquals("Mean not as expected from naive estimator.", 5e7, bad.getMean(), 1e-2);
    assertEquals("Stddev not as expected from naive estimator.", 7e8, bad.getStddev(), 1e7);
    assertEquals("Mean not as expected from trimmed estimator.", 0, good.getMean(), 2e-2);
    assertEquals("Stddev not as expected from trimmed estimator.", 1.0, good.getStddev(), 2e-2);
}

Example 3 with NormalDistribution

use of de.lmu.ifi.dbs.elki.math.statistics.distribution.NormalDistribution in project elki by elki-project.

the class NormalMADEstimatorTest method testEstimator.

@Test
public void testEstimator() {
    final NormalMADEstimator est = instantiate(NormalMADEstimator.class, NormalDistribution.class);
    load("norm.ascii.gz");
    double[] data = this.data.get("random_01_01");
    NormalDistribution dist = est.estimate(data, DoubleArrayAdapter.STATIC);
    assertStat("mean", dist.getMean(), 0.1, -0.012695629177971263);
    assertStat("stddev", dist.getStddev(), 0.1, -0.026518777589684295);
    data = this.data.get("random_0_1");
    dist = est.estimate(data, DoubleArrayAdapter.STATIC);
    assertStat("mean", dist.getMean(), 0., 0.01835053032901817);
    assertStat("stddev", dist.getStddev(), 1., -0.0826324972827217);
    data = this.data.get("random_1_3");
    dist = est.estimate(data, DoubleArrayAdapter.STATIC);
    assertStat("mean", dist.getMean(), 1., -0.6071640630952582);
    assertStat("stddev", dist.getStddev(), 3., 0.46390113946568645);
}

Example 4 with NormalDistribution

use of de.lmu.ifi.dbs.elki.math.statistics.distribution.NormalDistribution in project elki by elki-project.

the class TrimmedEstimatorTest method testNormalDistribution.

@Test
public void testNormalDistribution() {
    final double trim = .01;
    NormalMOMEstimator mom = NormalMOMEstimator.STATIC;
    // We could instantiate directly, but we also want to cover the
    // parameterizer class.
    ListParameterization config = new ListParameterization();
    config.addParameter(TrimmedEstimator.Parameterizer.INNER_ID, mom);
    config.addParameter(TrimmedEstimator.Parameterizer.TRIM_ID, trim);
    TrimmedEstimator<NormalDistribution> est = ClassGenericsUtil.parameterizeOrAbort(TrimmedEstimator.class, config);
    Random r = new Random(0L);
    double[] data = new double[10000];
    final int corrupt = (int) Math.floor(data.length * trim * .5);
    for (int i = 0; i < data.length; i++) {
        data[i] = i < corrupt ? 1e10 : r.nextGaussian();
    }
    NormalDistribution bad = mom.estimate(data, DoubleArrayAdapter.STATIC);
    NormalDistribution good = est.estimate(data, DoubleArrayAdapter.STATIC);
    assertEquals("Mean not as expected from naive estimator.", 5e7, bad.getMean(), 1e-2);
    assertEquals("Stddev not as expected from naive estimator.", 7e8, bad.getStddev(), 1e7);
    assertEquals("Mean not as expected from trimmed estimator.", 0, good.getMean(), 1e-2);
    assertEquals("Stddev not as expected from trimmed estimator.", 1.0, good.getStddev(), 3e-2);
}

Example 5 with NormalDistribution

use of de.lmu.ifi.dbs.elki.math.statistics.distribution.NormalDistribution in project elki by elki-project.

the class ReplaceNaNWithRandomFilterTest method parameters.

/**
 * Test with standard normal distribution as parameter.
 */
@Test
public void parameters() {
    String filename = UNITTEST + "nan-test-1.csv";
    ReplaceNaNWithRandomFilter filter = // 
    new ELKIBuilder<>(ReplaceNaNWithRandomFilter.class).with(// 
    ReplaceNaNWithRandomFilter.Parameterizer.REPLACEMENT_DISTRIBUTION, new NormalDistribution(0, 1, new Random(0L))).build();
    MultipleObjectsBundle filteredBundle = readBundle(filename, filter);
    // Load the test data again without a filter.
    MultipleObjectsBundle unfilteredBundle = readBundle(filename);
    // Ensure the first column are the vectors.
    assertTrue("Test file not as expected", TypeUtil.NUMBER_VECTOR_FIELD.isAssignableFromType(filteredBundle.meta(0)));
    assertTrue("Test file not as expected", TypeUtil.NUMBER_VECTOR_FIELD.isAssignableFromType(unfilteredBundle.meta(0)));
    // This cast is now safe (vector field):
    int dimFiltered = ((FieldTypeInformation) unfilteredBundle.meta(0)).getDimensionality();
    int dimUnfiltered = ((FieldTypeInformation) unfilteredBundle.meta(0)).getDimensionality();
    assertEquals("Dimensionality expected equal", dimFiltered, dimUnfiltered);
    // Note the indices of the NaN(s) in the data.
    List<IntegerVector> NaNs = new ArrayList<IntegerVector>();
    for (int row = 0; row < unfilteredBundle.dataLength(); row++) {
        Object obj = unfilteredBundle.data(row, 0);
        assertEquals("Unexpected data type", DoubleVector.class, obj.getClass());
        DoubleVector d = (DoubleVector) obj;
        for (int col = 0; col < dimUnfiltered; col++) {
            final double v = d.doubleValue(col);
            if (Double.isNaN(v)) {
                NaNs.add(new IntegerVector(new int[] { row, col }));
            }
        }
    }
    // Verify that at least a single NaN exists in the unfiltered bundle.
    assertTrue("NaN expected in unfiltered data", NaNs.size() > 0);
    for (IntegerVector iv : NaNs) {
        Object obj = filteredBundle.data(iv.intValue(0), 0);
        assertEquals("Unexpected data type", DoubleVector.class, obj.getClass());
        DoubleVector d = (DoubleVector) obj;
        final double v = d.doubleValue(iv.intValue(1));
        assertFalse("NaN not expected", Double.isNaN(v));
    }
}