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

Example 11 with NominalAttribute

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

the class GAFeatureSelectionTest method testLearn.

/**
     * Test of learn method, of class GAFeatureSelection.
     */
@Test
public void testLearn() {
    System.out.println("learn");
    int size = 100;
    int generation = 20;
    ClassifierTrainer<double[]> trainer = new LDA.Trainer();
    ClassificationMeasure measure = new Accuracy();
    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()]);
        GAFeatureSelection instance = new GAFeatureSelection();
        BitString[] result = instance.learn(size, generation, trainer, measure, x, y, testx, testy);
        for (BitString bits : result) {
            System.out.format("%.2f%% %d ", 100 * bits.fitness(), Math.sum(bits.bits()));
            for (int i = 0; i < x[0].length; i++) {
                System.out.print(bits.bits()[i] + " ");
            }
            System.out.println();
        }
        assertTrue(result[result.length - 1].fitness() > 0.88);
    } catch (Exception ex) {
        System.err.println(ex);
    }
}

Example 12 with NominalAttribute

use of smile.data.NominalAttribute 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 13 with NominalAttribute

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

the class BIRCHTest method testUSPS.

/**
     * Test of learn method, of class BIRCH.
     */
@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()]);
        BIRCH birch = new BIRCH(x[0].length, 5, 16.0);
        for (int i = 0; i < 20; i++) {
            int[] index = Math.permutate(x.length);
            for (int j = 0; j < x.length; j++) {
                birch.add(x[index[j]]);
            }
        }
        birch.partition(10);
        AdjustedRandIndex ari = new AdjustedRandIndex();
        RandIndex rand = new RandIndex();
        int[] p = new int[x.length];
        for (int i = 0; i < x.length; i++) {
            p[i] = birch.predict(x[i]);
        }
        double r = rand.measure(y, p);
        double r2 = ari.measure(y, p);
        System.out.format("Training rand index = %.2f%%\tadjusted rand index = %.2f%%%n", 100.0 * r, 100.0 * r2);
        assertTrue(r > 0.65);
        assertTrue(r2 > 0.20);
        p = new int[testx.length];
        for (int i = 0; i < testx.length; i++) {
            p[i] = birch.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 > 0.65);
        assertTrue(r2 > 0.20);
    } catch (Exception ex) {
        System.err.println(ex);
    }
}

Example 14 with NominalAttribute

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

the class NeuralNetworkTest method testUSPS.

/**
     * Test of learn method, of class NeuralNetwork.
     */
@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()]);
        int p = x[0].length;
        double[] mu = Math.colMean(x);
        double[] sd = Math.colSd(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.CROSS_ENTROPY, NeuralNetwork.ActivationFunction.SOFTMAX, x[0].length, 40, 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("USPS error rate = %.2f%%%n", 100.0 * error / testx.length);
    } catch (Exception ex) {
        System.err.println(ex);
    }
}

Example 15 with NominalAttribute

use of smile.data.NominalAttribute 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);
    }
}