Examples with AttributeDataset smile.data.AttributeDataset used on opensource projects

Example 71 with AttributeDataset

use of smile.data.AttributeDataset in project smile by haifengl.

the class TXTParserTest method testParse.

/**
     * Test of parse method, of class TXTParser.
     */
@Test
public void testParse() throws Exception {
    System.out.println("parse");
    TXTParser parser = new TXTParser();
    try {
        AttributeDataset data = parser.parse("PCL", smile.data.parser.IOUtils.getTestDataFile("microarray/Dunham2002.txt"));
        double[][] x = data.toArray(new double[data.size()][]);
        String[] id = data.toArray(new String[data.size()]);
        for (Attribute attribute : data.attributes()) {
            assertEquals(Attribute.Type.NUMERIC, attribute.getType());
            System.out.println(attribute.getName());
        }
        assertEquals(6694, data.size());
        assertEquals(16, data.attributes().length);
        assertEquals("YKR005C", id[0]);
        assertEquals(-0.43, x[0][0], 1E-7);
        assertEquals(-0.47, x[0][1], 1E-7);
        assertEquals(-0.39, x[0][2], 1E-7);
        assertEquals("YKR004C", id[6693]);
        assertEquals(0.03, x[6693][13], 1E-7);
        assertEquals(-0.53, x[6693][14], 1E-7);
        assertEquals(0.3, x[6693][15], 1E-7);
    } catch (Exception ex) {
        System.err.println(ex);
    }
}

Example 72 with AttributeDataset

use of smile.data.AttributeDataset in project smile by haifengl.

the class RegressionTreeTest method test.

public void test(String dataset, String url, int response) {
    System.out.println(dataset);
    ArffParser parser = new ArffParser();
    parser.setResponseIndex(response);
    try {
        AttributeDataset data = parser.parse(smile.data.parser.IOUtils.getTestDataFile(url));
        double[] datay = data.toArray(new double[data.size()]);
        double[][] datax = data.toArray(new double[data.size()][]);
        int n = datax.length;
        int k = 10;
        CrossValidation cv = new CrossValidation(n, k);
        double rss = 0.0;
        double ad = 0.0;
        for (int i = 0; i < k; i++) {
            double[][] trainx = Math.slice(datax, cv.train[i]);
            double[] trainy = Math.slice(datay, cv.train[i]);
            double[][] testx = Math.slice(datax, cv.test[i]);
            double[] testy = Math.slice(datay, cv.test[i]);
            RegressionTree tree = new RegressionTree(data.attributes(), trainx, trainy, 20);
            for (int j = 0; j < testx.length; j++) {
                double r = testy[j] - tree.predict(testx[j]);
                rss += r * r;
                ad += Math.abs(r);
            }
        }
        System.out.format("10-CV RMSE = %.4f \t AbsoluteDeviation = %.4f%n", Math.sqrt(rss / n), ad / n);
    } catch (Exception ex) {
        System.err.println(ex);
    }
}

Example 73 with AttributeDataset

use of smile.data.AttributeDataset in project smile by haifengl.

the class RegressionTreeTest method testCPU.

/**
     * Test of learn method, of class RegressionTree.
     */
@Test
public void testCPU() {
    System.out.println("CPU");
    ArffParser parser = new ArffParser();
    parser.setResponseIndex(6);
    try {
        AttributeDataset data = parser.parse(smile.data.parser.IOUtils.getTestDataFile("weka/cpu.arff"));
        double[] datay = data.toArray(new double[data.size()]);
        double[][] datax = data.toArray(new double[data.size()][]);
        int n = datax.length;
        int m = 3 * n / 4;
        int[] index = Math.permutate(n);
        double[][] trainx = new double[m][];
        double[] trainy = new double[m];
        for (int i = 0; i < m; i++) {
            trainx[i] = datax[index[i]];
            trainy[i] = datay[index[i]];
        }
        double[][] testx = new double[n - m][];
        double[] testy = new double[n - m];
        for (int i = m; i < n; i++) {
            testx[i - m] = datax[index[i]];
            testy[i - m] = datay[index[i]];
        }
        RegressionTree tree = new RegressionTree(data.attributes(), trainx, trainy, 20);
        System.out.format("RMSE = %.4f%n", Validation.test(tree, testx, testy));
        double[] importance = tree.importance();
        index = QuickSort.sort(importance);
        for (int i = importance.length; i-- > 0; ) {
            System.out.format("%s importance is %.4f%n", data.attributes()[index[i]], importance[i]);
        }
    } catch (Exception ex) {
        System.err.println(ex);
    }
}

Example 74 with AttributeDataset

use of smile.data.AttributeDataset in project smile by haifengl.

the class ValidationTest method testCv_4args_2.

/**
     * Test of cv method, of class Validation.
     */
@Test
public void testCv_4args_2() {
    System.out.println("cv");
    ArffParser parser = new ArffParser();
    parser.setResponseIndex(6);
    try {
        AttributeDataset data = parser.parse(smile.data.parser.IOUtils.getTestDataFile("weka/cpu.arff"));
        double[] y = data.toArray(new double[data.size()]);
        double[][] x = data.toArray(new double[data.size()][]);
        Math.standardize(x);
        RBFNetwork.Trainer<double[]> trainer = new RBFNetwork.Trainer<>(new EuclideanDistance());
        trainer.setNumCenters(20);
        double rmse = Validation.cv(10, trainer, x, y);
        System.out.println("RMSE = " + rmse);
    } catch (Exception ex) {
        System.err.println(ex);
    }
}

Example 75 with AttributeDataset

use of smile.data.AttributeDataset in project smile by haifengl.

the class ValidationTest method testTest_3args_2.

/**
     * Test of test method, of class Validation.
     */
@Test
public void testTest_3args_2() {
    System.out.println("test");
    ArffParser parser = new ArffParser();
    parser.setResponseIndex(6);
    try {
        AttributeDataset data = parser.parse(smile.data.parser.IOUtils.getTestDataFile("weka/cpu.arff"));
        double[] datay = data.toArray(new double[data.size()]);
        double[][] datax = data.toArray(new double[data.size()][]);
        Math.standardize(datax);
        int n = datax.length;
        int m = 3 * n / 4;
        double[][] x = new double[m][];
        double[] y = new double[m];
        double[][] testx = new double[n - m][];
        double[] testy = new double[n - m];
        int[] index = Math.permutate(n);
        for (int i = 0; i < m; i++) {
            x[i] = datax[index[i]];
            y[i] = datay[index[i]];
        }
        for (int i = m; i < n; i++) {
            testx[i - m] = datax[index[i]];
            testy[i - m] = datay[index[i]];
        }
        double[][] centers = new double[20][];
        RadialBasisFunction[] rbf = SmileUtils.learnGaussianRadialBasis(x, centers, 2);
        RBFNetwork<double[]> rkhs = new RBFNetwork<>(x, y, new EuclideanDistance(), rbf, centers);
        double rmse = Validation.test(rkhs, testx, testy);
        System.out.println("RMSE = " + rmse);
    } catch (Exception ex) {
        System.err.println(ex);
    }
}