Examples with DelimitedTextParser smile.data.parser.DelimitedTextParser used on opensource projects

Example 26 with DelimitedTextParser

use of smile.data.parser.DelimitedTextParser in project smile by haifengl.

the class NumericAttributeFeatureTest method testNORMALIZATION.

/**
     * Test of f method, of class NumericAttributeFeature.
     */
@Test
public void testNORMALIZATION() {
    System.out.println("NORMALIZATION");
    DelimitedTextParser parser = new DelimitedTextParser();
    parser.setResponseIndex(new NominalAttribute("class"), 0);
    try {
        AttributeDataset data = parser.parse("USPS Train", smile.data.parser.IOUtils.getTestDataFile("usps/zip.train"));
        double[][] x = data.toArray(new double[data.size()][]);
        double[] min = Math.colMin(x);
        double[] max = Math.colMax(x);
        NumericAttributeFeature naf = new NumericAttributeFeature(data.attributes(), NumericAttributeFeature.Scaling.NORMALIZATION, x);
        Attribute[] attributes = naf.attributes();
        assertEquals(256, attributes.length);
        for (int i = 0; i < x.length; i++) {
            double[] y = new double[attributes.length];
            for (int j = 0; j < y.length; j++) {
                y[j] = naf.f(x[i], j);
                assertEquals((x[i][j] - min[j]) / (max[j] - min[j]), y[j], 1E-7);
            }
        }
    } catch (Exception ex) {
        System.err.println(ex);
    }
}

Example 27 with DelimitedTextParser

use of smile.data.parser.DelimitedTextParser in project smile by haifengl.

the class NumericAttributeFeatureTest method testLOGARITHM.

/**
     * Test of f method, of class NumericAttributeFeature.
     */
@Test
public void testLOGARITHM() {
    System.out.println("LOGARITHM");
    DelimitedTextParser parser = new DelimitedTextParser();
    parser.setResponseIndex(new NominalAttribute("class"), 0);
    try {
        AttributeDataset data = parser.parse("USPS Train", smile.data.parser.IOUtils.getTestDataFile("usps/zip.train"));
        double[][] x = data.toArray(new double[data.size()][]);
        for (int i = 0; i < x.length; i++) {
            for (int j = 0; j < x[i].length; j++) {
                x[i][j] += 2.0;
            }
        }
        NumericAttributeFeature naf = new NumericAttributeFeature(data.attributes(), NumericAttributeFeature.Scaling.LOGARITHM);
        Attribute[] attributes = naf.attributes();
        assertEquals(256, attributes.length);
        for (int i = 0; i < x.length; i++) {
            double[] y = new double[attributes.length];
            for (int j = 0; j < y.length; j++) {
                y[j] = naf.f(x[i], j);
                assertEquals(Math.log(x[i][j]), y[j], 1E-7);
            }
        }
    } catch (Exception ex) {
        System.err.println(ex);
    }
}

Example 28 with DelimitedTextParser

use of smile.data.parser.DelimitedTextParser in project smile by haifengl.

the class SumSquaresRatioTest method testLearn.

/**
     * Test of learn method, of class SumSquaresRatio.
     */
@Test
public void testLearn() {
    System.out.println("USPS");
    try {
        DelimitedTextParser parser = new DelimitedTextParser();
        parser.setResponseIndex(new NominalAttribute("class"), 0);
        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()]);
        SumSquaresRatio ssr = new SumSquaresRatio();
        double[] score = ssr.rank(x, y);
        int[] index = QuickSort.sort(score);
        int p = 135;
        int n = x.length;
        double[][] xx = new double[n][p];
        for (int j = 0; j < p; j++) {
            for (int i = 0; i < n; i++) {
                xx[i][j] = x[i][index[255 - j]];
            }
        }
        int testn = testx.length;
        double[][] testxx = new double[testn][p];
        for (int j = 0; j < p; j++) {
            for (int i = 0; i < testn; i++) {
                testxx[i][j] = testx[i][index[255 - j]];
            }
        }
        LDA lda = new LDA(xx, y);
        int[] prediction = new int[testn];
        for (int i = 0; i < testn; i++) {
            prediction[i] = lda.predict(testxx[i]);
        }
        double accuracy = new Accuracy().measure(testy, prediction);
        System.out.format("SSR %.2f%%%n", 100 * accuracy);
    } catch (Exception ex) {
        System.err.println(ex);
    }
}

Example 29 with DelimitedTextParser

use of smile.data.parser.DelimitedTextParser in project smile by haifengl.

the class VQDemo method actionPerformed.

@Override
public void actionPerformed(ActionEvent e) {
    if ("startButton".equals(e.getActionCommand())) {
        try {
            clusterNumber = Integer.parseInt(clusterNumberField.getText().trim());
            if (clusterNumber < 2) {
                JOptionPane.showMessageDialog(this, "Invalid K: " + clusterNumber, "Error", JOptionPane.ERROR_MESSAGE);
                return;
            }
            if (clusterNumber > dataset[datasetIndex].length / 2) {
                JOptionPane.showMessageDialog(this, "Too large K: " + clusterNumber, "Error", JOptionPane.ERROR_MESSAGE);
                return;
            }
        } catch (Exception ex) {
            JOptionPane.showMessageDialog(this, "Invalid K: " + clusterNumberField.getText(), "Error", JOptionPane.ERROR_MESSAGE);
            return;
        }
        Thread thread = new Thread(this);
        thread.start();
    } else if ("datasetBox".equals(e.getActionCommand())) {
        datasetIndex = datasetBox.getSelectedIndex();
        if (dataset[datasetIndex] == null) {
            DelimitedTextParser parser = new DelimitedTextParser();
            parser.setDelimiter("[\t ]+");
            try {
                AttributeDataset data = parser.parse(datasetName[datasetIndex], smile.data.parser.IOUtils.getTestDataFile(datasource[datasetIndex]));
                dataset[datasetIndex] = data.toArray(new double[data.size()][]);
            } catch (Exception ex) {
                JOptionPane.showMessageDialog(null, "Failed to load dataset.", "ERROR", JOptionPane.ERROR_MESSAGE);
                System.err.println(ex);
            }
        }
        remove(canvas);
        if (dataset[datasetIndex].length < 500) {
            pointLegend = 'o';
        } else {
            pointLegend = '.';
        }
        canvas = ScatterPlot.plot(dataset[datasetIndex], pointLegend);
        add(canvas, BorderLayout.CENTER);
        validate();
    }
}

Example 30 with DelimitedTextParser

use of smile.data.parser.DelimitedTextParser in project smile by haifengl.

the class ValidationTest method testTest_3args_1.

/**
     * Test of test method, of class Validation.
     */
@Test
public void testTest_3args_1() {
    System.out.println("test");
    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()]);
        LDA lda = new LDA(x, y);
        double accuracy = Validation.test(lda, testx, testy);
        System.out.println("accuracy = " + accuracy);
        assertEquals(0.8724, accuracy, 1E-4);
    } catch (Exception ex) {
        System.err.println(ex);
    }
}