Example usage for weka.core Instances Instances

Introduction

In this page you can find the example usage for weka.core Instances Instances.

Prototype

public Instances(String name, ArrayList<Attribute> attInfo, int capacity) 

Source Link

Document

Creates an empty set of instances.

Usage

From source file:CJWeka.java

License:Open Source License

public Object addInstance(Object args) throws Exception {
    if (!(args instanceof String)) {
        throw new RuntimeException("Invalid type for execute");
    }/*from   w w  w  .  ja  v  a  2  s . c  o  m*/

    StringBuffer retbuf = new StringBuffer("");

    // function code goes in here

    String floatstring = (String) args;

    // convert floatstring to float/double array to instance
    String[] flostr = floatstring.split(" ");
    int nvalues = flostr.length;

    // add instance to ii

    if (my_attributes.isEmpty()) {
        // create attributes for all instances
        for (int j = 0; j < nvalues - 1; j++) {
            Attribute a = new Attribute(Integer.toString(j));
            my_attributes.add(a);
        }

        classvals.add("0");
        classvals.add("1");
        /*     classvals.add("2");
        classvals.add("3");
        classvals.add("4");
        classvals.add("5");
        classvals.add("6");
        classvals.add("7");*/

        Attribute cls = new Attribute("class", classvals);

        my_attributes.add(cls);

        ii = new Instances("my_instances", my_attributes, 0);
    }

    ii.setClassIndex(nvalues - 1);

    Instance inst = this.floatstringToInst(floatstring, ii, true);
    ii.add(inst);

    retbuf.append(ii.numInstances()); // return number of Instances in ii
    return retbuf.toString();
}

---

From source file:TextDirectoryToArff.java

License:Open Source License

public Instances createDataset(String directoryPath) throws Exception {

    FastVector atts = new FastVector(2);
    atts.addElement(new Attribute("filename", (FastVector) null));
    atts.addElement(new Attribute("contents", (FastVector) null));
    Instances data = new Instances("text_files_in_" + directoryPath, atts, 0);

    File dir = new File(directoryPath);
    String[] files = dir.list();/*from   w ww  . j  ava2s  .co m*/
    for (int i = 0; i < files.length; i++) {
        if (files[i].endsWith(".txt")) {
            try {
                double[] newInst = new double[2];
                newInst[0] = (double) data.attribute(0).addStringValue(files[i]);
                File txt = new File(directoryPath + File.separator + files[i]);
                InputStreamReader is;
                is = new InputStreamReader(new FileInputStream(txt));
                StringBuffer txtStr = new StringBuffer();
                int c;
                while ((c = is.read()) != -1) {
                    txtStr.append((char) c);
                }
                newInst[1] = (double) data.attribute(1).addStringValue(txtStr.toString());
                data.add(new Instance(1.0, newInst));
            } catch (Exception e) {
                //System.err.println("failed to convert file: " + directoryPath + File.separator + files[i]);
            }
        }
    }
    return data;
}

---

From source file:WekaClassify.java

License:Open Source License

public void SplitRun(Instances anInstance, double split) throws Exception {

    anInstance.randomize(new java.util.Random(0));

    int trainSize = (int) Math.round(anInstance.numInstances() * split);
    int testSize = anInstance.numInstances() - trainSize;
    Instances train = new Instances(anInstance, 0, trainSize);
    Instances test = new Instances(anInstance, trainSize, testSize);

    NumberFormat percentFormat = NumberFormat.getPercentInstance();
    percentFormat.setMaximumFractionDigits(1);
    String result = percentFormat.format(split);

    System.out.println("Evaluating with : Split percentage : " + result);
    m_Evaluation.evaluateModel(m_Classifier, anInstance);
}

---

From source file:PCADetector.java

License:Apache License

public Instances getInstances() {
    int numAtts = m_oriDataMatrix.size();
    if (numAtts < 0)
        return null;
    ArrayList<Attribute> atts = new ArrayList<Attribute>(numAtts);
    for (int att = 0; att < numAtts; att++) {
        atts.add(new Attribute(Integer.toString(att), att));
    }//w w  w.j av  a  2 s  .  com
    int numInstances = m_oriDataMatrix.get(0).size();
    if (numInstances <= 0)
        return null;
    Instances dataset = new Instances("MetricInstances", atts, numInstances);
    for (int inst = 0; inst < numInstances; inst++) {
        Instance newInst = new DenseInstance(numAtts);
        for (int att = 0; att < numAtts; att++) {
            newInst.setValue(att, m_oriDataMatrix.get(att).get(inst));
        }
        dataset.add(newInst);
    }
    return dataset;
}

---

From source file:aaa.util.test.CreateArff.java

License:Open Source License

/**
 * Generates the Instances object and outputs it in ARFF format to stdout.
 *
 * @param args   ignored//from w ww  . ja v a  2 s.c o m
 * @throws Exception   if generation of instances fails
 */
public static void main(String[] args) throws Exception {
    ArrayList<Attribute> atts;
    ArrayList<Attribute> attsRel;
    ArrayList<String> attVals;
    ArrayList<String> attValsRel;
    Instances data;
    Instances dataRel;
    double[] vals;
    double[] valsRel;
    int i;

    // 1. set up attributes
    atts = new ArrayList<Attribute>();
    // - numeric
    atts.add(new Attribute("att1"));
    // - nominal
    attVals = new ArrayList<String>();
    for (i = 0; i < 5; i++)
        attVals.add("val" + (i + 1));
    atts.add(new Attribute("att2", attVals));
    // - string
    atts.add(new Attribute("att3", (ArrayList<String>) null));
    // - date
    atts.add(new Attribute("att4", "yyyy-MM-dd"));
    // - relational
    attsRel = new ArrayList<Attribute>();
    // -- numeric
    attsRel.add(new Attribute("att5.1"));
    // -- nominal
    attValsRel = new ArrayList<String>();
    for (i = 0; i < 5; i++)
        attValsRel.add("val5." + (i + 1));
    attsRel.add(new Attribute("att5.2", attValsRel));
    dataRel = new Instances("att5", attsRel, 0);
    atts.add(new Attribute("att5", dataRel, 0));

    // 2. create Instances object
    data = new Instances("MyRelation", atts, 0);

    // 3. fill with data
    // first instance
    vals = new double[data.numAttributes()];
    // - numeric
    vals[0] = Math.PI;
    // - nominal
    vals[1] = attVals.indexOf("val3");
    // - string
    vals[2] = data.attribute(2).addStringValue("This is a string!");
    // - date
    vals[3] = data.attribute(3).parseDate("2001-11-09");
    // - relational
    dataRel = new Instances(data.attribute(4).relation(), 0);
    // -- first instance
    valsRel = new double[2];
    valsRel[0] = Math.PI + 1;
    valsRel[1] = attValsRel.indexOf("val5.3");
    dataRel.add(new DenseInstance(1.0, valsRel));
    // -- second instance
    valsRel = new double[2];
    valsRel[0] = Math.PI + 2;
    valsRel[1] = attValsRel.indexOf("val5.2");
    dataRel.add(new DenseInstance(1.0, valsRel));
    vals[4] = data.attribute(4).addRelation(dataRel);
    // add
    data.add(new DenseInstance(1.0, vals));

    // second instance
    vals = new double[data.numAttributes()]; // important: needs NEW array!
    // - numeric
    vals[0] = Math.E;
    // - nominal
    vals[1] = attVals.indexOf("val1");
    // - string
    vals[2] = data.attribute(2).addStringValue("And another one!");
    // - date
    vals[3] = data.attribute(3).parseDate("2000-12-01");
    // - relational
    dataRel = new Instances(data.attribute(4).relation(), 0);
    // -- first instance
    valsRel = new double[2];
    valsRel[0] = Math.E + 1;
    valsRel[1] = attValsRel.indexOf("val5.4");
    dataRel.add(new DenseInstance(1.0, valsRel));
    // -- second instance
    valsRel = new double[2];
    valsRel[0] = Math.E + 2;
    valsRel[1] = attValsRel.indexOf("val5.1");
    dataRel.add(new DenseInstance(1.0, valsRel));
    vals[4] = data.attribute(4).addRelation(dataRel);
    // add
    data.add(new DenseInstance(1.0, vals));

    // 4. output data
    System.out.println(data);
}

---

From source file:activeSegmentation.feature.FeatureExtraction.java

License:Open Source License

/**
 * Create training instances out of the user markings
 * @return set of instances (feature vectors in Weka format)
 *///from w w w  .  j av  a 2  s  . co m
@Override
public void createTrainingInstance(List<String> classLabels, int classes,
        List<Vector<ArrayList<Roi>>> examples) {
    ArrayList<Attribute> attributes = createFeatureHeader();
    attributes.add(new Attribute(Common.CLASS, addClasstoHeader(classes, classLabels)));

    // create initial set of instances
    trainingData = new Instances(Common.INSTANCE_NAME, attributes, 1);
    // Set the index of the class attribute
    trainingData.setClassIndex(filterManager.getNumOfFeatures());
    for (int classIndex = 0; classIndex < classes; classIndex++) {
        int nl = 0;

        // Read all lists of examples
        for (int sliceNum = 1; sliceNum <= filterManager.getOriginalImageSize(); sliceNum++)
            for (int j = 0; j < examples.get(sliceNum - 1).get(classIndex).size(); j++) {
                Roi r = examples.get(sliceNum - 1).get(classIndex).get(j);
                nl += addRectangleRoiInstances(trainingData, classIndex, sliceNum, r);
            }
        IJ.log("# of pixels selected as " + classLabels.get(classIndex) + ": " + nl);
    }

}

---

From source file:activeSegmentation.feature.FeatureExtraction.java

License:Open Source License

/**
 * Add training samples from a rectangular roi
 * /*from  w w  w .  j a v a 2s  .c o m*/
 * @param trainingData set of instances to add to
 * @param classIndex class index value
 * @param sliceNum number of 2d slice being processed
 * @param r shape roi
 * @return number of instances added
 */
private Instances addRectangleRoiInstances(int sliceNum, List<String> classLabels, int classes) {

    Instances testingData;
    ArrayList<Attribute> attributes = createFeatureHeader();
    attributes.add(new Attribute(Common.CLASS, addClasstoHeader(classes, classLabels)));
    System.out.println(attributes.toString());
    // create initial set of instances
    testingData = new Instances(Common.INSTANCE_NAME, attributes, 1);
    // Set the index of the class attribute
    testingData.setClassIndex(filterManager.getNumOfFeatures());

    for (int x = 0; x < originalImage.getWidth(); x++) {
        for (int y = 0; y < originalImage.getHeight(); y++) {

            testingData.add(filterManager.createInstance(x, y, 0, sliceNum));

        }
    }
    // increase number of instances for this class

    System.out.println("SIZe" + testingData.size());
    System.out.println(testingData.get(1).toString());
    return testingData;
}

---

From source file:activeSegmentation.learning.WekaDataSet.java

License:Open Source License

/**
 * Creates a Weka Dataset from a portion of the IDataset object
 *
 * @param dataset The dataset//from w w w  .ja  va  2 s .co  m
 * @param first The position of the first instance to copy
 * @param toCopy The number of instances to copy
 */
public WekaDataSet(IDataSet dataset, int first, int toCopy) {
    this.dataset = new Instances(dataset.getDataset(), first, toCopy);
}

---

From source file:adams.data.conversion.ReportToWekaInstance.java

License:Open Source License

/**
 * Performs the actual conversion./*from   w  w  w .j a v  a2s  .  com*/
 *
 * @return      the converted data
 * @throws Exception   if something goes wrong with the conversion
 */
protected Object doConvert() throws Exception {
    Report report;
    Instance result;
    ArrayList atts;
    ArrayList attValues;
    int i;
    double[] values;

    report = (Report) m_Input;

    // generate header
    if (m_Header == null) {
        atts = new ArrayList();
        for (i = 0; i < m_Fields.length; i++) {
            switch (m_Fields[i].getDataType()) {
            case NUMERIC:
                atts.add(new Attribute(m_Fields[i].getName()));
                break;
            case BOOLEAN:
                attValues = new ArrayList();
                attValues.add("false");
                attValues.add("true");
                atts.add(new Attribute(m_Fields[i].getName(), attValues));
                break;
            default:
                atts.add(new Attribute(m_Fields[i].getName(), (List) null));
                break;
            }
        }
        m_Header = new Instances(getClass().getName(), atts, 0);
    }

    // generate instance
    values = new double[m_Header.numAttributes()];
    for (i = 0; i < m_Fields.length; i++) {
        if (report.hasValue(m_Fields[i])) {
            switch (m_Fields[i].getDataType()) {
            case NUMERIC:
                values[i] = report.getDoubleValue(m_Fields[i]);
                break;
            case BOOLEAN:
                if (report.getBooleanValue(m_Fields[i]))
                    values[i] = 1;
                else
                    values[i] = 0;
                break;
            default:
                values[i] = m_Header.attribute(i).addStringValue("" + report.getValue(m_Fields[i]));
                break;
            }
        } else {
            values[i] = weka.core.Utils.missingValue();
        }
    }
    result = new DenseInstance(1.0, values);
    result.setDataset(m_Header);

    return result;
}

---

From source file:adams.data.conversion.SpreadSheetToWekaInstances.java

License:Open Source License

/**
 * Performs the actual conversion.// w ww .ja  v a  2  s .  c  om
 *
 * @return      the converted data
 * @throws Exception   if something goes wrong with the conversion
 */
@Override
protected Object doConvert() throws Exception {
    Instances result;
    SpreadSheet sheet;
    DenseInstance inst;
    ArrayList<Attribute> atts;
    HashSet<String> unique;
    ArrayList<String> labels;
    Row row;
    Cell cell;
    int i;
    int n;
    double[] values;
    Collection<ContentType> types;
    ContentType type;
    boolean added;
    int[] classIndices;

    sheet = (SpreadSheet) m_Input;

    // create header
    atts = new ArrayList<>();
    for (i = 0; i < sheet.getColumnCount(); i++) {
        added = false;
        types = sheet.getContentTypes(i);
        if (types.contains(ContentType.DOUBLE))
            types.remove(ContentType.LONG);
        if (types.contains(ContentType.LONG)) {
            types.add(ContentType.DOUBLE);
            types.remove(ContentType.LONG);
        }

        if (types.size() == 1) {
            type = (ContentType) types.toArray()[0];
            if (type == ContentType.DOUBLE) {
                atts.add(new Attribute(sheet.getHeaderRow().getCell(i).getContent()));
                added = true;
            } else if (type == ContentType.DATE) {
                atts.add(new Attribute(sheet.getHeaderRow().getCell(i).getContent(),
                        Constants.TIMESTAMP_FORMAT));
                added = true;
            } else if (type == ContentType.TIME) {
                atts.add(new Attribute(sheet.getHeaderRow().getCell(i).getContent(), Constants.TIME_FORMAT));
                added = true;
            }
        }

        if (!added) {
            unique = new HashSet<>();
            for (n = 0; n < sheet.getRowCount(); n++) {
                row = sheet.getRow(n);
                cell = row.getCell(i);
                if ((cell != null) && !cell.isMissing())
                    unique.add(cell.getContent());
            }
            if ((unique.size() > m_MaxLabels) || (m_MaxLabels < 1)) {
                atts.add(new Attribute(sheet.getHeaderRow().getCell(i).getContent(), (FastVector) null));
            } else {
                labels = new ArrayList<>(unique);
                Collections.sort(labels);
                atts.add(new Attribute(sheet.getHeaderRow().getCell(i).getContent(), labels));
            }
        }
    }
    result = new Instances(Environment.getInstance().getProject(), atts, sheet.getRowCount());
    if (sheet.hasName())
        result.setRelationName(sheet.getName());

    // add data
    for (n = 0; n < sheet.getRowCount(); n++) {
        row = sheet.getRow(n);
        values = new double[result.numAttributes()];
        for (i = 0; i < result.numAttributes(); i++) {
            cell = row.getCell(i);
            values[i] = weka.core.Utils.missingValue();
            if ((cell != null) && !cell.isMissing()) {
                if (result.attribute(i).type() == Attribute.DATE) {
                    if (cell.isTime())
                        values[i] = cell.toTime().getTime();
                    else
                        values[i] = cell.toDate().getTime();
                } else if (result.attribute(i).isNumeric()) {
                    values[i] = Utils.toDouble(cell.getContent());
                } else if (result.attribute(i).isString()) {
                    values[i] = result.attribute(i).addStringValue(cell.getContent());
                } else {
                    values[i] = result.attribute(i).indexOfValue(cell.getContent());
                }
            }
        }
        inst = new DenseInstance(1.0, values);
        result.add(inst);
    }

    if (sheet instanceof Dataset) {
        classIndices = ((Dataset) sheet).getClassAttributeIndices();
        if (classIndices.length > 0)
            result.setClassIndex(classIndices[0]);
    }

    return result;
}

---

• «
• 1
• 2
• 3
• 4
• 5
• 6
• 7
• 8
• 9
• 10
• 11
• 12
• 13
• 14
• 15
• 16
• 17
• 18
• 19
• 20
• 21
• »