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

Example 51 with AttributeDataset

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

the class NeuralNetworkTest method testSegmentLMS.

/**
     * Test of learn method, of class NeuralNetwork.
     */
@Test
public void testSegmentLMS() {
    System.out.println("Segment LMS");
    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]);
        int p = x[0].length;
        double[] mu = Math.colMin(x);
        double[] sd = Math.colMax(x);
        for (int i = 0; i < x.length; i++) {
            for (int j = 0; j < p; j++) {
                x[i][j] = (x[i][j] - mu[j]) / sd[j];
            }
        }
        for (int i = 0; i < testx.length; i++) {
            for (int j = 0; j < p; j++) {
                testx[i][j] = (testx[i][j] - mu[j]) / sd[j];
            }
        }
        NeuralNetwork net = new NeuralNetwork(NeuralNetwork.ErrorFunction.LEAST_MEAN_SQUARES, NeuralNetwork.ActivationFunction.LOGISTIC_SIGMOID, x[0].length, 30, Math.max(y) + 1);
        for (int j = 0; j < 30; j++) {
            net.learn(x, y);
        }
        int error = 0;
        for (int i = 0; i < testx.length; i++) {
            if (net.predict(testx[i]) != testy[i]) {
                error++;
            }
        }
        System.out.format("Segment error rate = %.2f%%%n", 100.0 * error / testx.length);
    } catch (Exception ex) {
        System.err.println(ex);
    }
}

Example 52 with AttributeDataset

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

the class DecisionTreeTest method testIris.

/**
     * Test of learn method, of class DecisionTree.
     */
@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]);
            DecisionTree tree = new DecisionTree(iris.attributes(), trainx, trainy, 4);
            if (y[loocv.test[i]] != tree.predict(x[loocv.test[i]]))
                error++;
        }
        System.out.println("Decision Tree error = " + error);
        assertEquals(7, error);
    } catch (Exception ex) {
        System.err.println(ex);
    }
}

Example 53 with AttributeDataset

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

the class DecisionTreeTest method testUSPS.

/**
     * Test of learn method, of class DecisionTree.
     */
@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()]);
        DecisionTree tree = new DecisionTree(x, y, 350, DecisionTree.SplitRule.ENTROPY);
        int error = 0;
        for (int i = 0; i < testx.length; i++) {
            if (tree.predict(testx[i]) != testy[i]) {
                error++;
            }
        }
        System.out.format("USPS error rate = %.2f%%%n", 100.0 * error / testx.length);
        assertEquals(328, error);
    } catch (Exception ex) {
        System.err.println(ex);
    }
}

Example 54 with AttributeDataset

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

the class DecisionTreeTest method testUSPSNominal.

/**
     * Test of learn method, of class DecisionTree.
     */
@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(127 + 127 * xi[i]);
            }
        }
        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);
        }
        DecisionTree tree = new DecisionTree(attributes, x, y, 350, 2, DecisionTree.SplitRule.ENTROPY);
        int error = 0;
        for (int i = 0; i < testx.length; i++) {
            if (tree.predict(testx[i]) != testy[i]) {
                error++;
            }
        }
        System.out.format("USPS error rate = %.2f%%%n", 100.0 * error / testx.length);
        double[] importance = tree.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]);
        }
        assertEquals(324, error);
    } catch (Exception ex) {
        System.err.println(ex);
    }
}

Example 55 with AttributeDataset

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

the class FLDTest method testPredict.

/**
     * Test of predict method, of class FDA.
     */
@Test
public void testPredict() {
    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]);
            FLD fisher = new FLD(trainx, trainy);
            if (y[loocv.test[i]] != fisher.predict(x[loocv.test[i]]))
                error++;
        }
        System.out.println("FLD error = " + error);
        assertEquals(5, error);
    } catch (Exception ex) {
        System.err.println(ex);
    }
}