Examples with DelimitedTextParser smile.data.parser.DelimitedTextParser used on opensource projects

Example 11 with DelimitedTextParser

use of smile.data.parser.DelimitedTextParser in project smile by haifengl.

the class AdaBoostTest method testUSPS.

/**
     * Test of learn method, of class AdaBoost.
     */
@Test
public void testUSPS() {
    System.out.println("USPS");
    DelimitedTextParser parser = new DelimitedTextParser();
    parser.setResponseIndex(new NominalAttribute("class"), 0);
    try {
        AttributeDataset train = parser.parse("USPS Train", smile.data.parser.IOUtils.getTestDataFile("usps/zip.train"));
        AttributeDataset test = parser.parse("USPS Test", smile.data.parser.IOUtils.getTestDataFile("usps/zip.test"));
        double[][] x = train.toArray(new double[train.size()][]);
        int[] y = train.toArray(new int[train.size()]);
        double[][] testx = test.toArray(new double[test.size()][]);
        int[] testy = test.toArray(new int[test.size()]);
        for (int i = 0; i < y.length; i++) {
            if (y[i] != 0)
                y[i] = 1;
        }
        for (int i = 0; i < testy.length; i++) {
            if (testy[i] != 0)
                testy[i] = 1;
        }
        AdaBoost forest = new AdaBoost(x, y, 100, 6);
        int error = 0;
        for (int i = 0; i < testx.length; i++) {
            if (forest.predict(testx[i]) != testy[i]) {
                error++;
            }
        }
        System.out.println("AdaBoost error = " + error);
        System.out.format("USPS error rate = %.2f%%%n", 100.0 * error / testx.length);
        assertTrue(error <= 25);
    } catch (Exception ex) {
        System.err.println(ex);
    }
}

Example 12 with DelimitedTextParser

use of smile.data.parser.DelimitedTextParser in project smile by haifengl.

the class AdaBoostTest method testUSPSNominal.

/**
     * Test of learn method, of class AdaBoost.
     */
@Test
public void testUSPSNominal() {
    System.out.println("USPS nominal");
    DelimitedTextParser parser = new DelimitedTextParser();
    parser.setResponseIndex(new NominalAttribute("class"), 0);
    try {
        AttributeDataset train = parser.parse("USPS Train", smile.data.parser.IOUtils.getTestDataFile("usps/zip.train"));
        AttributeDataset test = parser.parse("USPS Test", smile.data.parser.IOUtils.getTestDataFile("usps/zip.test"));
        double[][] x = train.toArray(new double[train.size()][]);
        int[] y = train.toArray(new int[train.size()]);
        double[][] testx = test.toArray(new double[test.size()][]);
        int[] testy = test.toArray(new int[test.size()]);
        for (double[] xi : x) {
            for (int i = 0; i < xi.length; i++) {
                xi[i] = Math.round(255 * (xi[i] + 1) / 2);
            }
        }
        for (double[] xi : testx) {
            for (int i = 0; i < xi.length; i++) {
                xi[i] = Math.round(255 * (xi[i] + 1) / 2);
            }
        }
        Attribute[] attributes = new Attribute[256];
        String[] values = new String[attributes.length];
        for (int i = 0; i < attributes.length; i++) {
            values[i] = String.valueOf(i);
        }
        for (int i = 0; i < attributes.length; i++) {
            attributes[i] = new NominalAttribute("V" + i, values);
        }
        for (int i = 0; i < y.length; i++) {
            if (y[i] != 0)
                y[i] = 1;
        }
        for (int i = 0; i < testy.length; i++) {
            if (testy[i] != 0)
                testy[i] = 1;
        }
        AdaBoost forest = new AdaBoost(attributes, x, y, 100, 6);
        int error = 0;
        for (int i = 0; i < testx.length; i++) {
            if (forest.predict(testx[i]) != testy[i]) {
                error++;
            }
        }
        System.out.println("AdaBoost error = " + error);
        System.out.format("USPS error rate = %.2f%%%n", 100.0 * error / testx.length);
        assertTrue(error <= 25);
    } catch (Exception ex) {
        System.err.println(ex);
    }
}

Example 13 with DelimitedTextParser

use of smile.data.parser.DelimitedTextParser in project smile by haifengl.

the class SpectralClusteringTest method testUSPSNystrom.

/**
     * Test of learn method, of class SpectralClustering.
     */
@Test
public void testUSPSNystrom() {
    System.out.println("USPS Nystrom approximation");
    DelimitedTextParser parser = new DelimitedTextParser();
    parser.setResponseIndex(new NominalAttribute("class"), 0);
    try {
        AttributeDataset train = parser.parse("USPS Train", smile.data.parser.IOUtils.getTestDataFile("usps/zip.train"));
        double[][] x = train.toArray(new double[train.size()][]);
        int[] y = train.toArray(new int[train.size()]);
        SpectralClustering spectral = new SpectralClustering(x, 10, 100, 8.0);
        AdjustedRandIndex ari = new AdjustedRandIndex();
        RandIndex rand = new RandIndex();
        double r = rand.measure(y, spectral.getClusterLabel());
        double r2 = ari.measure(y, spectral.getClusterLabel());
        System.out.format("Training rand index = %.2f%%\tadjusted rand index = %.2f%%%n", 100.0 * r, 100.0 * r2);
        assertTrue(r > 0.8);
        assertTrue(r2 > 0.35);
    } catch (Exception ex) {
        System.err.println(ex);
    }
}

Example 14 with DelimitedTextParser

use of smile.data.parser.DelimitedTextParser in project smile by haifengl.

the class SpectralClusteringTest method testUSPS.

/**
     * Test of learn method, of class SpectralClustering.
     */
@Test
public void testUSPS() {
    System.out.println("USPS");
    DelimitedTextParser parser = new DelimitedTextParser();
    parser.setResponseIndex(new NominalAttribute("class"), 0);
    try {
        AttributeDataset train = parser.parse("USPS Train", smile.data.parser.IOUtils.getTestDataFile("usps/zip.train"));
        double[][] x = train.toArray(new double[train.size()][]);
        int[] y = train.toArray(new int[train.size()]);
        SpectralClustering spectral = new SpectralClustering(x, 10, 8.0);
        AdjustedRandIndex ari = new AdjustedRandIndex();
        RandIndex rand = new RandIndex();
        double r = rand.measure(y, spectral.getClusterLabel());
        double r2 = ari.measure(y, spectral.getClusterLabel());
        System.out.format("Training rand index = %.2f%%\tadjusted rand index = %.2f%%%n", 100.0 * r, 100.0 * r2);
        assertTrue(r > 0.85);
        assertTrue(r2 > 0.45);
    } catch (Exception ex) {
        System.err.println(ex);
    }
}

Example 15 with DelimitedTextParser

use of smile.data.parser.DelimitedTextParser in project smile by haifengl.

the class GAFeatureSelectionTest method testLearn.

/**
     * Test of learn method, of class GAFeatureSelection.
     */
@Test
public void testLearn() {
    System.out.println("learn");
    int size = 100;
    int generation = 20;
    ClassifierTrainer<double[]> trainer = new LDA.Trainer();
    ClassificationMeasure measure = new Accuracy();
    DelimitedTextParser parser = new DelimitedTextParser();
    parser.setResponseIndex(new NominalAttribute("class"), 0);
    try {
        AttributeDataset train = parser.parse("USPS Train", smile.data.parser.IOUtils.getTestDataFile("usps/zip.train"));
        AttributeDataset test = parser.parse("USPS Test", smile.data.parser.IOUtils.getTestDataFile("usps/zip.test"));
        double[][] x = train.toArray(new double[train.size()][]);
        int[] y = train.toArray(new int[train.size()]);
        double[][] testx = test.toArray(new double[test.size()][]);
        int[] testy = test.toArray(new int[test.size()]);
        GAFeatureSelection instance = new GAFeatureSelection();
        BitString[] result = instance.learn(size, generation, trainer, measure, x, y, testx, testy);
        for (BitString bits : result) {
            System.out.format("%.2f%% %d ", 100 * bits.fitness(), Math.sum(bits.bits()));
            for (int i = 0; i < x[0].length; i++) {
                System.out.print(bits.bits()[i] + " ");
            }
            System.out.println();
        }
        assertTrue(result[result.length - 1].fitness() > 0.88);
    } catch (Exception ex) {
        System.err.println(ex);
    }
}