Example usage for weka.core Instances add

Introduction

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

Prototype

@Override
public boolean add(Instance instance)

Source Link

Document

Adds one instance to the end of the set.

Usage

From source file:wekimini.DataManager.java

public Instance[] getClassifiableInstancesForAllOutputs(double[] vals) {

    double data[] = new double[numMetaData + numInputs + numOutputs];

    System.arraycopy(vals, 0, data, numMetaData, vals.length);
    /* for (int i = 0; i < numFeatures; i++) {
     data[numMetaData + i] = d[i];//from   w  w  w  . jav a 2  s  .  com
     } */

    Instance[] is = new Instance[numOutputs];
    for (int i = 0; i < numOutputs; i++) {
        is[i] = new Instance(1.0, data);
        Instances tmp = new Instances(dummyInstances);
        tmp.add(is[i]);
        try {
            tmp = Filter.useFilter(tmp, outputFilters[i]);
            tmp.setClassIndex(tmp.numAttributes() - 1);
            is[i] = tmp.firstInstance();
        } catch (Exception ex) {
            logger.log(Level.SEVERE, "Could not filter");
            Logger.getLogger(DataManager.class.getName()).log(Level.SEVERE, null, ex);
        }
        tmp.setClassIndex(tmp.numAttributes() - 1);
    }
    return is;
}

From source file:wekimini.kadenze.LoadableInstanceMaker.java

public Instance convertInputsToInstance(double[] vals) {
    double data[] = new double[numMetaData + numInputs + numOutputs];
    System.arraycopy(vals, 0, data, numMetaData, vals.length);
    Instance instance = new Instance(1.0, data);
    Instances tmp = new Instances(dummyInstances);
    tmp.add(instance);
    try {/*from   w ww .j ava  2  s. c om*/
        tmp = Filter.useFilter(tmp, outputFilter);
        tmp.setClassIndex(tmp.numAttributes() - 1);
        instance = tmp.firstInstance();
    } catch (Exception ex) {
        logger.log(Level.SEVERE, "Could not filter");
        Logger.getLogger(DataManager.class.getName()).log(Level.SEVERE, null, ex);
    }
    tmp.setClassIndex(tmp.numAttributes() - 1);
    return instance;
}

From source file:wekimini.kadenze.LoadableInstanceMaker.java

public Instance convertInputsToInstance(double val) {
    double data[] = new double[numMetaData + numInputs + numOutputs];
    data[numMetaData] = val;
    Instance instance = new Instance(1.0, data);
    Instances tmp = new Instances(dummyInstances);
    tmp.add(instance);
    try {//from   ww w.j a  v a 2 s . c o  m
        tmp = Filter.useFilter(tmp, outputFilter);
        tmp.setClassIndex(tmp.numAttributes() - 1);
        instance = tmp.firstInstance();
    } catch (Exception ex) {
        logger.log(Level.SEVERE, "Could not filter");
        Logger.getLogger(DataManager.class.getName()).log(Level.SEVERE, null, ex);
    }
    tmp.setClassIndex(tmp.numAttributes() - 1);
    return instance;
}

From source file:wekimini.learning.LinearRegressionAttributeTransformer.java

@Override
public Instances transformedData(Instances data) throws Exception {
    Instances output;
    output = new Instances(exampleInstances);

    for (int i = 0; i < data.numInstances(); i++) {
        Instance converted = convertInstance(data.instance(i));
        output.add(converted);
    }/*from   w w w.j  ava  2s.  com*/
    return output;
}

From source file:Windows.windowGenerating.java

/**
 * Metoda zamienia liste zbiorw na instance. Pierwsza ptla tworzy list
 * wartoci jakie mog przybiera atrybut.//from w  ww  .  ja  v a2 s  .  c  o m
 *
 * @param atr lista atryburw
 * @param s lista zawierajaca kombinajcie uzupenionych danych
 * @return
 *
 */
public static Instances setToInstances(List<Set<String>> atr, Set<List<String>> s) {

    ArrayList<Attribute> lAtrib = new ArrayList<>();

    for (int i = 0; i < atr.size(); i++) {
        FastVector labels = new FastVector(); //Utworzenie obiektu kolekcji wartosci nowego atrybutu symbolicznego
        Set<String> setValuesAtr = atr.get(i);
        Iterator ite = setValuesAtr.iterator();
        while (ite.hasNext()) {
            Object e = ite.next();
            labels.addElement(e);
        }
        Attribute attrib = new Attribute(listOfHeather.get(i), labels);
        lAtrib.add(attrib);
    }

    Instances dataNewObj = new Instances("Nowa tablica", lAtrib, 0);

    for (int i = 0; i < numOfNewInstance; i++) {
        Instance n = new DenseInstance(lAtrib.size());
        dataNewObj.add(n);
    }
    System.out.println(dataNewObj.numInstances() + " jest instancji nowo wygenerowanych");
    int iteratorek = 0;
    Iterator iter = s.iterator();
    while (iter.hasNext()) {
        Instance instance = dataNewObj.instance(iteratorek); //Pobranie obiektu o podanym numerze
        List<String> str = (List<String>) iter.next();
        for (int j = 0; j < dataNewObj.numAttributes(); j++) {
            instance.setValue(j, str.get(j));
        }
        iteratorek++;
    }
    return dataNewObj;
}

From source file:wtute.engine.AnalysisEngine.java

public void train() throws Exception {

    Instances trainingInstances = createInstances("TRAINING INS");
    for (int i = 0; i < data.numInstances(); i++) {
        Instance instance = convertInstance(data.instance(i));

        instance.setDataset(trainingInstances);
        trainingInstances.add(instance);
    }/*from ww w .  ja  v a2s . c  o  m*/

    System.out.println(data);
    J48 classifier = new J48();

    try {
        //classifier training code
        classifier.buildClassifier(trainingInstances);

        //storing the trained classifier to a file for future use
        weka.core.SerializationHelper.write("J48.model", classifier);
    } catch (Exception ex) {
        System.out.println("Exception in training the classifier.");
    }
}