Examples with EuclideanDistance smile.math.distance.EuclideanDistance used on opensource projects

Example 21 with EuclideanDistance

use of smile.math.distance.EuclideanDistance in project smile by haifengl.

the class ValidationTest method testBootstrap_5args_2.

/**
     * Test of bootstrap method, of class Validation.
     */
@Test
public void testBootstrap_5args_2() {
    System.out.println("bootstrap");
    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);
        RegressionMeasure[] measures = { new RMSE(), new AbsoluteDeviation() };
        double[][] results = Validation.bootstrap(100, trainer, x, y, measures);
        System.out.println("100-fold bootstrap RMSE average = " + Math.mean(results[0]));
        System.out.println("100-fold bootstrap RMSE std.dev = " + Math.sd(results[0]));
        System.out.println("100-fold bootstrap AbsoluteDeviation average = " + Math.mean(results[1]));
        System.out.println("100-fold bootstrap AbsoluteDeviation std.dev = " + Math.sd(results[1]));
    } catch (Exception ex) {
        System.err.println(ex);
    }
}

Example 22 with EuclideanDistance

use of smile.math.distance.EuclideanDistance in project smile by haifengl.

the class ValidationTest method testBootstrap_4args_2.

/**
     * Test of bootstrap method, of class Validation.
     */
@Test
public void testBootstrap_4args_2() {
    System.out.println("bootstrap");
    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.bootstrap(100, trainer, x, y);
        System.out.println("100-fold bootstrap RMSE average = " + Math.mean(rmse));
        System.out.println("100-fold bootstrap RMSE std.dev = " + Math.sd(rmse));
    } catch (Exception ex) {
        System.err.println(ex);
    }
}

Example 23 with EuclideanDistance

use of smile.math.distance.EuclideanDistance in project smile by haifengl.

the class RBFNetworkDemo method learn.

@Override
public double[][] learn(double[] x, double[] y) {
    double[][] data = dataset[datasetIndex].toArray(new double[dataset[datasetIndex].size()][]);
    int[] label = dataset[datasetIndex].toArray(new int[dataset[datasetIndex].size()]);
    try {
        k = Integer.parseInt(kField.getText().trim());
        if (k < 2 || k > data.length) {
            JOptionPane.showMessageDialog(this, "Invalid K: " + k, "Error", JOptionPane.ERROR_MESSAGE);
            return null;
        }
    } catch (Exception ex) {
        JOptionPane.showMessageDialog(this, "Invalid K: " + kField.getText(), "Error", JOptionPane.ERROR_MESSAGE);
        return null;
    }
    double[][] centers = new double[k][];
    RadialBasisFunction basis = SmileUtils.learnGaussianRadialBasis(data, centers);
    RBFNetwork<double[]> rbf = new RBFNetwork<>(data, label, new EuclideanDistance(), basis, centers);
    for (int i = 0; i < label.length; i++) {
        label[i] = rbf.predict(data[i]);
    }
    double trainError = error(label, label);
    System.out.format("training error = %.2f%%\n", 100 * trainError);
    double[][] z = new double[y.length][x.length];
    for (int i = 0; i < y.length; i++) {
        for (int j = 0; j < x.length; j++) {
            double[] p = { x[j], y[i] };
            z[i][j] = rbf.predict(p);
        }
    }
    return z;
}

Example 24 with EuclideanDistance

use of smile.math.distance.EuclideanDistance in project smile by haifengl.

the class RBFNetworkTest method testLearn.

/**
     * Test of learn method, of class RBFNetwork.
     */
@Test
public void testLearn() {
    System.out.println("learn");
    ArffParser arffParser = new ArffParser();
    arffParser.setResponseIndex(4);
    try {
        AttributeDataset iris = arffParser.parse(smile.data.parser.IOUtils.getTestDataFile("weka/iris.arff"));
        double[][] x = iris.toArray(new double[iris.size()][]);
        int[] y = iris.toArray(new int[iris.size()]);
        int n = x.length;
        LOOCV loocv = new LOOCV(n);
        int error = 0;
        for (int i = 0; i < n; i++) {
            double[][] trainx = Math.slice(x, loocv.train[i]);
            int[] trainy = Math.slice(y, loocv.train[i]);
            double[][] centers = new double[10][];
            RadialBasisFunction[] basis = SmileUtils.learnGaussianRadialBasis(trainx, centers, 5.0);
            RBFNetwork<double[]> rbf = new RBFNetwork<>(trainx, trainy, new EuclideanDistance(), basis, centers);
            if (y[loocv.test[i]] != rbf.predict(x[loocv.test[i]]))
                error++;
        }
        System.out.println("RBF network error = " + error);
        assertTrue(error <= 6);
    } catch (Exception ex) {
        System.err.println(ex);
    }
}

Example 25 with EuclideanDistance

use of smile.math.distance.EuclideanDistance in project smile by haifengl.

the class RBFNetworkTest method testUSPS.

/**
     * Test of learn method, of class RBFNetwork.
     */
@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()]);
        double[][] centers = new double[200][];
        RadialBasisFunction basis = SmileUtils.learnGaussianRadialBasis(x, centers);
        RBFNetwork<double[]> rbf = new RBFNetwork<>(x, y, new EuclideanDistance(), new GaussianRadialBasis(8.0), centers);
        int error = 0;
        for (int i = 0; i < testx.length; i++) {
            if (rbf.predict(testx[i]) != testy[i]) {
                error++;
            }
        }
        System.out.format("USPS error rate = %.2f%%%n", 100.0 * error / testx.length);
        assertTrue(error <= 150);
    } catch (Exception ex) {
        System.err.println(ex);
    }
}