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

Example 36 with AttributeDataset

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

the class QDATest method testLearn.

/**
     * Test of learn method, of class QDA.
     */
@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;
        double[] posteriori = new double[3];
        for (int i = 0; i < n; i++) {
            double[][] trainx = Math.slice(x, loocv.train[i]);
            int[] trainy = Math.slice(y, loocv.train[i]);
            QDA qda = new QDA(trainx, trainy);
            if (y[loocv.test[i]] != qda.predict(x[loocv.test[i]], posteriori))
                error++;
        //System.out.println(posteriori[0]+"\t"+posteriori[1]+"\t"+posteriori[2]);
        }
        System.out.println("QDA error = " + error);
        assertEquals(4, error);
    } catch (Exception ex) {
        System.err.println(ex);
    }
}

Example 37 with AttributeDataset

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

the class RBFNetworkTest method testSegment.

/**
     * Test of learn method, of class RBFNetwork.
     */
@Test
public void testSegment() {
    System.out.println("Segment");
    ArffParser parser = new ArffParser();
    parser.setResponseIndex(19);
    try {
        AttributeDataset train = parser.parse(smile.data.parser.IOUtils.getTestDataFile("weka/segment-challenge.arff"));
        AttributeDataset test = parser.parse(smile.data.parser.IOUtils.getTestDataFile("weka/segment-test.arff"));
        double[][] x = train.toArray(new double[0][]);
        int[] y = train.toArray(new int[0]);
        double[][] testx = test.toArray(new double[0][]);
        int[] testy = test.toArray(new int[0]);
        double[][] centers = new double[100][];
        RadialBasisFunction[] basis = SmileUtils.learnGaussianRadialBasis(x, centers, 5.0);
        RBFNetwork<double[]> rbf = new RBFNetwork<>(x, y, new EuclideanDistance(), basis, centers);
        int error = 0;
        for (int i = 0; i < testx.length; i++) {
            if (rbf.predict(testx[i]) != testy[i]) {
                error++;
            }
        }
        System.out.format("Segment error rate = %.2f%%%n", 100.0 * error / testx.length);
        assertTrue(error <= 210);
    } catch (Exception ex) {
        System.err.println(ex);
    }
}

Example 38 with AttributeDataset

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

the class RDATest method testLearn.

/**
     * Test of learn method, of class RDA.
     */
@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]);
            RDA rda = new RDA(trainx, trainy, 0.0);
            if (y[loocv.test[i]] != rda.predict(x[loocv.test[i]]))
                error++;
        }
        System.out.println("RDA (0.0) error = " + error);
        assertEquals(22, error);
        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]);
            RDA rda = new RDA(trainx, trainy, 0.1);
            if (y[loocv.test[i]] != rda.predict(x[loocv.test[i]]))
                error++;
        }
        System.out.println("RDA (0.1) error = " + error);
        assertEquals(24, error);
        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]);
            RDA rda = new RDA(trainx, trainy, 0.2);
            if (y[loocv.test[i]] != rda.predict(x[loocv.test[i]]))
                error++;
        }
        System.out.println("RDA (0.2) error = " + error);
        assertEquals(20, error);
        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]);
            RDA rda = new RDA(trainx, trainy, 0.3);
            if (y[loocv.test[i]] != rda.predict(x[loocv.test[i]]))
                error++;
        }
        System.out.println("RDA (0.3) error = " + error);
        assertEquals(19, error);
        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]);
            RDA rda = new RDA(trainx, trainy, 0.4);
            if (y[loocv.test[i]] != rda.predict(x[loocv.test[i]]))
                error++;
        }
        System.out.println("RDA (0.4) error = " + error);
        assertEquals(16, error);
        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]);
            RDA rda = new RDA(trainx, trainy, 0.5);
            if (y[loocv.test[i]] != rda.predict(x[loocv.test[i]]))
                error++;
        }
        System.out.println("RDA (0.5) error = " + error);
        assertEquals(12, error);
        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]);
            RDA rda = new RDA(trainx, trainy, 0.6);
            if (y[loocv.test[i]] != rda.predict(x[loocv.test[i]]))
                error++;
        }
        System.out.println("RDA (0.6) error = " + error);
        assertEquals(11, error);
        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]);
            RDA rda = new RDA(trainx, trainy, 0.7);
            if (y[loocv.test[i]] != rda.predict(x[loocv.test[i]]))
                error++;
        }
        System.out.println("RDA (0.7) error = " + error);
        assertEquals(9, error);
        error = 0;
        double[] posteriori = new double[3];
        for (int i = 0; i < n; i++) {
            double[][] trainx = Math.slice(x, loocv.train[i]);
            int[] trainy = Math.slice(y, loocv.train[i]);
            RDA rda = new RDA(trainx, trainy, 0.8);
            if (y[loocv.test[i]] != rda.predict(x[loocv.test[i]], posteriori))
                error++;
        //System.out.println(posteriori[0]+"\t"+posteriori[1]+"\t"+posteriori[2]);
        }
        System.out.println("RDA (0.8) error = " + error);
        assertEquals(6, error);
        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]);
            RDA rda = new RDA(trainx, trainy, 0.9);
            if (y[loocv.test[i]] != rda.predict(x[loocv.test[i]]))
                error++;
        }
        System.out.println("RDA (0.9) error = " + error);
        assertEquals(3, error);
        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]);
            RDA rda = new RDA(trainx, trainy, 1.0);
            if (y[loocv.test[i]] != rda.predict(x[loocv.test[i]]))
                error++;
        }
        System.out.println("RDA (1.0) error = " + error);
        assertEquals(4, error);
    } catch (Exception ex) {
        System.err.println(ex);
    }
}

Example 39 with AttributeDataset

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

the class RandomForestTest method testUSPSNominal.

/**
     * Test of learn method, of class RandomForest.
     */
@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);
        }
        RandomForest forest = new RandomForest(attributes, x, y, 200);
        int error = 0;
        for (int i = 0; i < testx.length; i++) {
            if (forest.predict(testx[i]) != testy[i]) {
                error++;
            }
        }
        System.out.println(error);
        System.out.format("USPS OOB error rate = %.2f%%%n", 100.0 * forest.error());
        System.out.format("USPS error rate = %.2f%%%n", 100.0 * error / testx.length);
        double[] accuracy = forest.test(testx, testy);
        for (int i = 1; i <= accuracy.length; i++) {
            System.out.format("%d trees accuracy = %.2f%%%n", i, 100.0 * accuracy[i - 1]);
        }
        double[] importance = forest.importance();
        int[] index = QuickSort.sort(importance);
        for (int i = importance.length; i-- > 0; ) {
            System.out.format("%s importance is %.4f%n", train.attributes()[index[i]], importance[i]);
        }
        assertTrue(error <= 150);
    } catch (Exception ex) {
        System.err.println(ex);
    }
}

Example 40 with AttributeDataset

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

the class RandomForestTest method testIris.

/**
     * Test of learn method, of class RandomForest.
     */
@Test
public void testIris() {
    System.out.println("Iris");
    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]);
            RandomForest forest = new RandomForest(iris.attributes(), trainx, trainy, 100);
            if (y[loocv.test[i]] != forest.predict(x[loocv.test[i]]))
                error++;
        }
        System.out.println("Random Forest error = " + error);
        assertTrue(error <= 9);
    } catch (Exception ex) {
        System.err.println(ex);
    }
}