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

Example 41 with DelimitedTextParser

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

the class GMeansTest method testUSPS.

/**
     * Test of learn method, of class GMeans.
     */
@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()]);
        AdjustedRandIndex ari = new AdjustedRandIndex();
        RandIndex rand = new RandIndex();
        GMeans gmeans = new GMeans(x, 10);
        double r = rand.measure(y, gmeans.getClusterLabel());
        double r2 = ari.measure(y, gmeans.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 > 0.4);
        int[] p = new int[testx.length];
        for (int i = 0; i < testx.length; i++) {
            p[i] = gmeans.predict(testx[i]);
        }
        r = rand.measure(testy, p);
        r2 = ari.measure(testy, p);
        System.out.format("Testing rand index = %.2f%%\tadjusted rand index = %.2f%%%n", 100.0 * r, 100.0 * r2);
        assertTrue(r > 0.85);
        assertTrue(r2 > 0.4);
    } catch (Exception ex) {
        System.err.println(ex);
    }
}

Example 42 with DelimitedTextParser

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

the class HierarchicalClusteringTest method testUSPS.

/**
     * Test of learn method, of class GMeans.
     */
@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()]);
        int n = x.length;
        double[][] proximity = new double[n][];
        for (int i = 0; i < n; i++) {
            proximity[i] = new double[i + 1];
            for (int j = 0; j < i; j++) {
                proximity[i][j] = Math.distance(x[i], x[j]);
            }
        }
        AdjustedRandIndex ari = new AdjustedRandIndex();
        RandIndex rand = new RandIndex();
        HierarchicalClustering hc = new HierarchicalClustering(new SingleLinkage(proximity));
        int[] label = hc.partition(10);
        double r = rand.measure(y, label);
        double r2 = ari.measure(y, label);
        System.out.format("SingleLinkage rand index = %.2f%%\tadjusted rand index = %.2f%%%n", 100.0 * r, 100.0 * r2);
        assertTrue(r > 0.1);
        hc = new HierarchicalClustering(new CompleteLinkage(proximity));
        label = hc.partition(10);
        r = rand.measure(y, label);
        r2 = ari.measure(y, label);
        System.out.format("CompleteLinkage rand index = %.2f%%\tadjusted rand index = %.2f%%%n", 100.0 * r, 100.0 * r2);
        assertTrue(r > 0.75);
        hc = new HierarchicalClustering(new UPGMALinkage(proximity));
        label = hc.partition(10);
        r = rand.measure(y, label);
        r2 = ari.measure(y, label);
        System.out.format("UPGMA rand index = %.2f%%\tadjusted rand index = %.2f%%%n", 100.0 * r, 100.0 * r2);
        assertTrue(r > 0.1);
        hc = new HierarchicalClustering(new WPGMALinkage(proximity));
        label = hc.partition(10);
        r = rand.measure(y, label);
        r2 = ari.measure(y, label);
        System.out.format("WPGMA rand index = %.2f%%\tadjusted rand index = %.2f%%%n", 100.0 * r, 100.0 * r2);
        assertTrue(r > 0.2);
        hc = new HierarchicalClustering(new UPGMCLinkage(proximity));
        label = hc.partition(10);
        r = rand.measure(y, label);
        r2 = ari.measure(y, label);
        System.out.format("UPGMC rand index = %.2f%%\tadjusted rand index = %.2f%%%n", 100.0 * r, 100.0 * r2);
        assertTrue(r > 0.1);
        hc = new HierarchicalClustering(new WPGMCLinkage(proximity));
        label = hc.partition(10);
        r = rand.measure(y, label);
        r2 = ari.measure(y, label);
        System.out.format("WPGMC rand index = %.2f%%\tadjusted rand index = %.2f%%%n", 100.0 * r, 100.0 * r2);
        assertTrue(r > 0.1);
        hc = new HierarchicalClustering(new WardLinkage(proximity));
        label = hc.partition(10);
        r = rand.measure(y, label);
        r2 = ari.measure(y, label);
        System.out.format("Ward rand index = %.2f%%\tadjusted rand index = %.2f%%%n", 100.0 * r, 100.0 * r2);
        assertTrue(r > 0.9);
        assertTrue(r2 > 0.5);
    } catch (Exception ex) {
        System.err.println(ex);
    }
}

Example 43 with DelimitedTextParser

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

the class FLDTest method testUSPS.

/**
     * Test of learn method, of class FDA.
     */
@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()]);
        FLD fisher = new FLD(x, y);
        int error = 0;
        for (int i = 0; i < testx.length; i++) {
            if (fisher.predict(testx[i]) != testy[i]) {
                error++;
            }
        }
        System.out.format("USPS error rate = %.2f%%%n", 100.0 * error / testx.length);
        assertEquals(561, error);
    } catch (Exception ex) {
        System.err.println(ex);
    }
}

Example 44 with DelimitedTextParser

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

the class KNNTest method testUSPS.

/**
     * Test of learn method, of class KNN.
     */
@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()]);
        KNN<double[]> knn = KNN.learn(x, y);
        int error = 0;
        for (int i = 0; i < testx.length; i++) {
            if (knn.predict(testx[i]) != testy[i]) {
                error++;
            }
        }
        System.out.format("USPS error rate = %.2f%%%n", 100.0 * error / testx.length);
        assertEquals(113, error);
    } catch (Exception ex) {
        System.err.println(ex);
    }
}

Example 45 with DelimitedTextParser

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

the class LDATest method testUSPS.

/**
     * Test of learn method, of class LDA.
     */
@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()]);
        LDA lda = new LDA(x, y);
        int error = 0;
        for (int i = 0; i < testx.length; i++) {
            if (lda.predict(testx[i]) != testy[i]) {
                error++;
            }
        }
        System.out.format("USPS error rate = %.2f%%%n", 100.0 * error / testx.length);
        assertEquals(256, error);
    } catch (Exception ex) {
        System.err.println(ex);
    }
}