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

Example 1 with Attribute

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

the class GCTParserTest method testParse.

/**
     * Test of parse method, of class GCTParser.
     */
@Test
public void testParse() throws Exception {
    System.out.println("parse");
    GCTParser parser = new GCTParser();
    try {
        AttributeDataset data = parser.parse("GCT", smile.data.parser.IOUtils.getTestDataFile("microarray/allaml.dataset.gct"));
        double[][] x = data.toArray(new double[data.size()][]);
        String[] id = data.toArray(new String[data.size()]);
        for (Attribute attribute : data.attributes()) {
            assertEquals(Attribute.Type.NUMERIC, attribute.getType());
            System.out.println(attribute.getName());
        }
        assertEquals(12564, data.size());
        assertEquals(48, data.attributes().length);
        assertEquals("AFFX-MurIL2_at", id[0]);
        assertEquals(-161.8, x[0][0], 1E-7);
        assertEquals(-231.0, x[0][1], 1E-7);
        assertEquals(-279.0, x[0][2], 1E-7);
        assertEquals("128_at", id[12563]);
        assertEquals(95.0, x[12563][45], 1E-7);
        assertEquals(108.0, x[12563][46], 1E-7);
        assertEquals(346.0, x[12563][47], 1E-7);
    } catch (Exception ex) {
        System.err.println(ex);
    }
}

Example 2 with Attribute

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

the class GCTParser method parse.

/**
     * Parse a GCT dataset from an input stream.
     * @param name the name of dataset.
     * @param stream the input stream of data.
     * @throws java.io.IOException
     */
public AttributeDataset parse(String name, InputStream stream) throws IOException, ParseException {
    BufferedReader reader = new BufferedReader(new InputStreamReader(stream));
    String line = reader.readLine();
    if (line == null) {
        throw new IOException("Empty data source.");
    }
    if (!line.equals("#1.2")) {
        throw new IOException("Invalid version.");
    }
    line = reader.readLine();
    if (line == null) {
        throw new IOException("Premature end of file.");
    }
    String[] tokens = line.split("\t", -1);
    if (tokens.length != 2) {
        throw new IOException("Invalid data size inforamation.");
    }
    int n = Integer.parseInt(tokens[0]);
    int p = Integer.parseInt(tokens[1]);
    if (n <= 0 || p <= 0) {
        throw new IOException(String.format("Invalid data size %d x %d.", n, p));
    }
    Attribute[] attributes = new Attribute[p];
    line = reader.readLine();
    if (line == null) {
        throw new IOException("Premature end of file.");
    }
    tokens = line.split("\t", -1);
    if (tokens.length != p + 2) {
        throw new IOException("Invalid title header.");
    }
    for (int i = 0; i < p; i++) {
        attributes[i] = new NumericAttribute(tokens[i + 2]);
    }
    AttributeDataset data = new AttributeDataset(name, attributes);
    for (int i = 0; i < n; i++) {
        line = reader.readLine();
        if (line == null) {
            throw new IOException("Premature end of file.");
        }
        tokens = line.split("\t", -1);
        if (tokens.length != p + 2) {
            throw new IOException(String.format("Invalid number of elements of line %d: %d", i + 4, tokens.length));
        }
        double[] x = new double[p];
        for (int j = 0; j < p; j++) {
            if (tokens[j + 2].isEmpty()) {
                x[j] = Double.NaN;
            } else {
                x[j] = Double.valueOf(tokens[j + 2]);
            }
        }
        Datum<double[]> datum = new Datum<>(x);
        datum.name = tokens[0];
        datum.description = tokens[1];
        data.add(datum);
    }
    reader.close();
    return data;
}

Example 3 with Attribute

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

the class PCLParser method parse.

/**
     * Parse a PCL dataset from an input stream.
     * @param name the name of dataset.
     * @param stream the input stream of data.
     * @throws java.io.IOException
     */
public AttributeDataset parse(String name, InputStream stream) throws IOException, ParseException {
    BufferedReader reader = new BufferedReader(new InputStreamReader(stream));
    String line = reader.readLine();
    if (line == null) {
        throw new IOException("Empty data source.");
    }
    String[] tokens = line.split("\t", -1);
    int p = tokens.length - 3;
    line = reader.readLine();
    if (line == null) {
        throw new IOException("Premature end of file.");
    }
    String[] weight = line.split("\t", -1);
    if (weight.length != tokens.length) {
        throw new IOException("Invalid sample weight header.");
    }
    Attribute[] attributes = new Attribute[p];
    for (int i = 0; i < p; i++) {
        attributes[i] = new NumericAttribute(tokens[i + 3], null, Double.valueOf(weight[i + 3]));
    }
    AttributeDataset data = new AttributeDataset(name, attributes);
    for (int i = 3; (line = reader.readLine()) != null; i++) {
        tokens = line.split("\t", -1);
        if (tokens.length != weight.length) {
            throw new IOException(String.format("Invalid number of elements of line %d: %d", i, tokens.length));
        }
        double[] x = new double[p];
        for (int j = 0; j < p; j++) {
            if (tokens[j + 3].isEmpty()) {
                x[j] = Double.NaN;
            } else {
                x[j] = Double.valueOf(tokens[j + 3]);
            }
        }
        Datum<double[]> datum = new Datum<>(x);
        datum.name = tokens[0];
        datum.description = tokens[1];
        datum.weight = Double.valueOf(tokens[2]);
        data.add(datum);
    }
    reader.close();
    return data;
}

Example 4 with Attribute

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

the class TXTParser method parse.

/**
     * Parse a TXT dataset from an input stream.
     * @param name the name of dataset.
     * @param stream the input stream of data.
     * @throws java.io.IOException
     */
public AttributeDataset parse(String name, InputStream stream) throws IOException, ParseException {
    BufferedReader reader = new BufferedReader(new InputStreamReader(stream));
    String line = reader.readLine();
    if (line == null) {
        throw new IOException("Empty data source.");
    }
    String[] tokens = line.split("\t", -1);
    int start = 1;
    int p = tokens.length - 1;
    if (tokens[1].equalsIgnoreCase("description")) {
        start = 2;
        p = tokens.length - 2;
    }
    Attribute[] attributes = new Attribute[p];
    for (int i = 0; i < p; i++) {
        attributes[i] = new NumericAttribute(tokens[i + start]);
    }
    AttributeDataset data = new AttributeDataset(name, attributes);
    for (int i = 2; (line = reader.readLine()) != null; i++) {
        tokens = line.split("\t", -1);
        if (tokens.length != p + start) {
            throw new IOException(String.format("Invalid number of elements of line %d: %d", i, tokens.length));
        }
        double[] x = new double[p];
        for (int j = 0; j < p; j++) {
            if (tokens[j + start].isEmpty()) {
                x[j] = Double.NaN;
            } else {
                x[j] = Double.valueOf(tokens[j + start]);
            }
        }
        Datum<double[]> datum = new Datum<>(x);
        datum.name = tokens[0];
        if (start == 2) {
            datum.description = tokens[1];
        }
        data.add(datum);
    }
    reader.close();
    return data;
}

Example 5 with Attribute

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

the class ArffParserTest method testParseWeather.

/**
     * Test of parse method, of class ArffParser.
     */
@Test
public void testParseWeather() throws Exception {
    System.out.println("weather");
    try {
        ArffParser arffParser = new ArffParser();
        arffParser.setResponseIndex(4);
        AttributeDataset weather = arffParser.parse(smile.data.parser.IOUtils.getTestDataFile("weka/weather.nominal.arff"));
        double[][] x = weather.toArray(new double[weather.size()][]);
        int[] y = weather.toArray(new int[weather.size()]);
        assertEquals(Attribute.Type.NOMINAL, weather.response().getType());
        for (Attribute attribute : weather.attributes()) {
            assertEquals(Attribute.Type.NOMINAL, attribute.getType());
        }
        assertEquals(14, weather.size());
        assertEquals(4, weather.attributes().length);
        assertEquals("no", weather.response().toString(y[0]));
        assertEquals("no", weather.response().toString(y[1]));
        assertEquals("yes", weather.response().toString(y[2]));
        assertEquals("sunny", weather.attributes()[0].toString(x[0][0]));
        assertEquals("hot", weather.attributes()[1].toString(x[0][1]));
        assertEquals("high", weather.attributes()[2].toString(x[0][2]));
        assertEquals("FALSE", weather.attributes()[3].toString(x[0][3]));
        assertEquals("no", weather.response().toString(y[13]));
        assertEquals("rainy", weather.attributes()[0].toString(x[13][0]));
        assertEquals("mild", weather.attributes()[1].toString(x[13][1]));
        assertEquals("high", weather.attributes()[2].toString(x[13][2]));
        assertEquals("TRUE", weather.attributes()[3].toString(x[13][3]));
    } catch (Exception ex) {
        System.err.println(ex);
    }
}