Example usage for weka.core Instances classAttribute

List of usage examples for weka.core Instances classAttribute

  1. HOME
  2. Java
  3. weka
  4. weka.core.*
  5. Instances
  6. classAttribute

Introduction

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

Prototype


publicAttribute classAttribute()

Source Link

Document

Returns the class attribute.

Usage

From source file:classif.dropx.PrototyperSorted.java

License:Open Source License

/**
 * Balance the classes in the train test
 * @param data//from   www.ja  v  a 2  s  .  c om
 */
protected void buildSpecificClassifierByClass(Instances data) {
    if (sortedSequences == null) {
        buildSortedSequences(data);
        buildSortedSequencesPerClass(data);
    }

    int max = nbPrototypesPerClass;
    if (isNbPrototypesPerClass) {
        max = this.nbPrototypesPerClass * data.numClasses();
    }

    Attribute classAttribute = data.classAttribute();
    for (int i = 0; i < classAttribute.numValues(); i++) {
        ArrayList<ClassedSequence> tmpClassObj = sortedSequencesByClass.get(classAttribute.value(i));
        for (int j = 0; j < max & j < tmpClassObj.size(); j++) {
            prototypes.add(tmpClassObj.get(j));
        }
    }
}

From source file:classif.dropx.PrototyperSorted.java

License:Open Source License

private void buildSortedSequencesPerClass(Instances data) {
    sortedSequencesByClass = new HashMap<String, ArrayList<ClassedSequence>>();
    Attribute classAttribute = data.classAttribute();

    for (int i = 0; i < classAttribute.numValues(); i++) {
        sortedSequencesByClass.put(classAttribute.value(i), new ArrayList<ClassedSequence>());
    }//w ww.  j  a v a 2 s  . co m

    for (int i = 0; i < sortedSequences.size(); i++) {
        ClassedSequence instance = sortedSequences.get(i);
        sortedSequencesByClass.get(instance.classValue).add(instance);
    }
}

From source file:classif.Prototyper.java

License:Open Source License

@Override
public void buildClassifier(Instances data) throws Exception {
    trainingData = data;//from  w w  w  .j a  v  a  2s .  co m
    Attribute classAttribute = data.classAttribute();
    prototypes = new ArrayList<>();

    classedData = new HashMap<String, ArrayList<Sequence>>();
    indexClassedDataInFullData = new HashMap<String, ArrayList<Integer>>();
    for (int c = 0; c < data.numClasses(); c++) {
        classedData.put(data.classAttribute().value(c), new ArrayList<Sequence>());
        indexClassedDataInFullData.put(data.classAttribute().value(c), new ArrayList<Integer>());
    }

    sequences = new Sequence[data.numInstances()];
    classMap = new String[sequences.length];
    for (int i = 0; i < sequences.length; i++) {
        Instance sample = data.instance(i);
        MonoDoubleItemSet[] sequence = new MonoDoubleItemSet[sample.numAttributes() - 1];
        int shift = (sample.classIndex() == 0) ? 1 : 0;
        for (int t = 0; t < sequence.length; t++) {
            sequence[t] = new MonoDoubleItemSet(sample.value(t + shift));
        }
        sequences[i] = new Sequence(sequence);
        String clas = sample.stringValue(classAttribute);
        classMap[i] = clas;
        classedData.get(clas).add(sequences[i]);
        indexClassedDataInFullData.get(clas).add(i);
        //         System.out.println("Element "+i+" of train is classed "+clas+" and went to element "+(indexClassedDataInFullData.get(clas).size()-1));
    }

    buildSpecificClassifier(data);

    if (fillPrototypes)
        addMissingPrototypesRandom();
}

From source file:classif.Prototyper.java

License:Open Source License

public static ClassedSequence[] convertWekaSetToClassedSequence(Instances test) {

    Attribute classAttribute = test.classAttribute();
    ClassedSequence[] testSequences = new ClassedSequence[test.numInstances()];
    for (int i = 0; i < testSequences.length; i++) {
        Instance sample = test.instance(i);
        MonoDoubleItemSet[] sequence = new MonoDoubleItemSet[sample.numAttributes() - 1];
        int shift = (sample.classIndex() == 0) ? 1 : 0;
        for (int t = 0; t < sequence.length; t++) {
            sequence[t] = new MonoDoubleItemSet(sample.value(t + shift));
        }/*from  w w w .j a v  a2  s .  c  om*/
        String clas = sample.stringValue(classAttribute);
        testSequences[i] = new ClassedSequence(new Sequence(sequence), clas);
    }

    return testSequences;

}

From source file:classif.PrototyperUtil.java

License:Open Source License

public static int[] getPrototypesPerClassDistribution(ArrayList<ClassedSequence> prototypes, Instances train) {
    HashMap<String, Integer> distrib = new HashMap<String, Integer>();

    Enumeration classValues = train.classAttribute().enumerateValues();
    List<String> list = Collections.list(classValues);
    Collections.sort(list);// w  w  w  .ja v  a  2s . co m

    for (String integer : list) {
        distrib.put(integer, 0);
    }

    for (ClassedSequence symbolicSequenceClassed : prototypes) {
        String classValue = symbolicSequenceClassed.classValue;
        distrib.put(classValue, distrib.get(classValue) + 1);
    }
    int[] classDistribution = new int[list.size()];
    for (int i = 0; i < classDistribution.length; i++) {
        classDistribution[i] = distrib.get(list.get(i));
    }

    return classDistribution;
}

From source file:classification.classifiers.LDA.java

License:Open Source License

/**
 * Modification on Dr. Wolfgang Lenhard's code.
 * This was necessary because this classifier had to implements
 * "buildClassifier" and "classifyInstance" to be like a classifier of WEKA(R).
 * //from   ww  w. j  ava2 s.c o m
 * @param data
 * @throws Exception
 */
public void buildClassifier(Instances data) throws Exception {
    int n = data.numInstances();
    int a = data.numAttributes();
    int k = data.numClasses();
    int[] g = new int[n];

    double[][] d = new double[n][a];
    for (int i = 0; i < n; i++) {
        double[] d_i = data.instance(i).toDoubleArray();
        d[i] = d_i;

        /**
         * To print the attribute with the correspondent double
         *
         * System.out.print("\n"); for(int j=0; j<a; j++){
         * System.out.print(data.instance(i).stringValue(data.attribute(j))
         * + " = ");
         * System.out.print(data.instance(i).value(data.attribute(j)) +
         * ";  "); } System.out.print("\n"); /
         **/
    }

    // Gives the number of objects belonging to class i in the trainingSet.
    int classIndex = a - 1;
    valueClass = new double[k];

    data.setClassIndex(classIndex);

    for (int i = 0; i < k; i++) {
        // Reference class
        String refClass = data.classAttribute().value(i);
        //
        // System.out.println("refClass: " + refClass + " ");

        for (int j = 0; j < n; j++) {
            // Object class
            String objectClass = data.instance(j).stringValue(classIndex);
            //
            // System.out.println("objectClass: " + objectClass + " - value:
            // " + data.instance(j).value(data.attribute(classIndex)));

            // Building two vectors of classes, one in int format and
            // another in double format.
            if (objectClass == refClass) {

                // Object class as a double
                valueClass[i] = data.instance(j).value(data.attribute(classIndex));
                // Object class as an int
                g[j] = i;

                //
                // System.out.println("value of class (int): " + g[j] + "
                // ___ value (double): " + valueClass[i]);
            }
        }

    }

    this.BuildLDA(d, g, true);
}

From source file:cn.ict.zyq.bestConf.bestConf.BestConf.java

License:Open Source License

public static void testCOMT2() throws Exception {
    BestConf bestconf = new BestConf();
    Instances trainingSet = DataIOFile.loadDataFromArffFile("data/trainingBestConf0.arff");
    trainingSet.setClassIndex(trainingSet.numAttributes() - 1);

    Instances samplePoints = LHSInitializer.getMultiDimContinuous(bestconf.getAttributes(),
            InitialSampleSetSize, false);
    samplePoints.insertAttributeAt(trainingSet.classAttribute(), samplePoints.numAttributes());
    samplePoints.setClassIndex(samplePoints.numAttributes() - 1);

    COMT2 comt = new COMT2(samplePoints, COMT2Iteration);

    comt.buildClassifier(trainingSet);/*  w w  w.j  av a 2s . c o m*/

    Evaluation eval = new Evaluation(trainingSet);
    eval.evaluateModel(comt, trainingSet);
    System.err.println(eval.toSummaryString());

    Instance best = comt.getInstanceWithPossibleMaxY(samplePoints.firstInstance());
    Instances bestInstances = new Instances(trainingSet, 2);
    bestInstances.add(best);
    DataIOFile.saveDataToXrffFile("data/trainingBestConf_COMT2.arff", bestInstances);

    //now we output the training set with the class value updated as the predicted value
    Instances output = new Instances(trainingSet, trainingSet.numInstances());
    Enumeration<Instance> enu = trainingSet.enumerateInstances();
    while (enu.hasMoreElements()) {
        Instance ins = enu.nextElement();
        double[] values = ins.toDoubleArray();
        values[values.length - 1] = comt.classifyInstance(ins);
        output.add(ins.copy(values));
    }
    DataIOFile.saveDataToXrffFile("data/trainingBestConf0_predict.xrff", output);
}

From source file:com.gamerecommendation.Weatherconditions.Clasificacion.java

public String clasificar(String[] testCases) throws Exception {
    String ruta = "model.model";

    InputStream classModelStream;
    classModelStream = getClass().getResourceAsStream(ruta);
    Classifier clasify = (Classifier) SerializationHelper.read(classModelStream);
    FastVector condition = new FastVector();
    condition.addElement("Cloudy");
    condition.addElement("Clear");
    condition.addElement("Sunny");
    condition.addElement("Fair");
    condition.addElement("Partly_Cloudy");
    condition.addElement("Mostly_Cloudy");
    condition.addElement("Showers");
    condition.addElement("Haze");
    condition.addElement("Dust");
    condition.addElement("Other");
    Attribute _condition = new Attribute("contition", condition);

    FastVector temperature = new FastVector();
    temperature.addElement("Hot");
    temperature.addElement("Mild");
    temperature.addElement("Cool");
    Attribute _temperature = new Attribute("temperature", temperature);

    FastVector chill = new FastVector();
    chill.addElement("Regrettable");
    chill.addElement("Mint");
    Attribute _chill = new Attribute("chill", chill);

    FastVector direction = new FastVector();
    direction.addElement("Mint");
    direction.addElement("Fair");
    direction.addElement("Regular");
    Attribute _direction = new Attribute("direction", direction);

    FastVector speed = new FastVector();
    speed.addElement("Mint");
    speed.addElement("Fair");
    speed.addElement("Regular");
    Attribute _speed = new Attribute("speed", speed);

    FastVector humidity = new FastVector();
    humidity.addElement("High");
    humidity.addElement("Normal");
    humidity.addElement("Low");
    Attribute _humidity = new Attribute("humidity", humidity);

    FastVector visibility = new FastVector();
    visibility.addElement("Recommended");
    visibility.addElement("Not_Recommended");
    Attribute _visibility = new Attribute("visibility", visibility);

    FastVector preassure = new FastVector();
    preassure.addElement("Fair");
    preassure.addElement("Mint");
    Attribute _preassure = new Attribute("preassure", preassure);

    FastVector Class = new FastVector();
    Class.addElement("Recommended");
    Class.addElement("Not_Recommended");
    Attribute _Class = new Attribute("class", Class);

    FastVector atributos = new FastVector(9);
    atributos.addElement(_condition);// ww  w.j a  v a 2 s.  co m
    atributos.addElement(_temperature);
    atributos.addElement(_chill);
    atributos.addElement(_direction);
    atributos.addElement(_speed);
    atributos.addElement(_humidity);
    atributos.addElement(_visibility);
    atributos.addElement(_preassure);
    atributos.addElement(_Class);

    ArrayList<Attribute> atributs = new ArrayList<>();
    atributs.add(_condition);
    atributs.add(_temperature);
    atributs.add(_chill);
    atributs.add(_direction);
    atributs.add(_speed);
    atributs.add(_humidity);
    atributs.add(_visibility);
    atributs.add(_preassure);
    atributs.add(_Class);

    //Aqu se crea la instacia, que tiene todos los atributos del modelo
    Instances dataTest = new Instances("TestCases", atributos, 1);
    dataTest.setClassIndex(8);

    Instance setPrueba = new Instance(9);

    int index = -1;
    for (int i = 0; i < 8; i++) {
        index = atributs.get(i).indexOfValue(testCases[i]);
        //System.out.println(i + " " + atributs.get(i)  + " " + index + " " + testCases[i]);
        setPrueba.setValue(atributs.get(i), index);
    }

    //Agregando el set que se desea evaluar.
    dataTest.add(setPrueba);

    //Realizando la Prediccin
    //La instancia es la 0 debido a que es la unica que se encuentra.
    double valorP = clasify.classifyInstance(dataTest.instance(0));
    //get the name of the class value
    String prediccion = dataTest.classAttribute().value((int) valorP);

    return prediccion;
}

From source file:com.guidefreitas.locator.services.PredictionService.java

public Room predict(PredictionRequest request) {
    try {/*from  w w w.  j  a  v  a  2s. c om*/

        String arffData = this.generateTestData(request);
        StringReader reader = new StringReader(arffData);
        Instances unlabeled = new Instances(reader);
        System.out.println("Test data size: " + unlabeled.size());
        unlabeled.setClassIndex(unlabeled.numAttributes() - 1);
        Instances labeled = new Instances(unlabeled);
        Double clsLabel = this.classifier.classifyInstance(unlabeled.get(0));
        labeled.instance(0).setClassValue(clsLabel);
        String roomIdString = unlabeled.classAttribute().value(clsLabel.intValue());

        Long roomId = Long.parseLong(roomIdString);
        Room predictedRoom = RoomService.getInstance().getById(roomId);
        System.out.println(clsLabel + " -> " + roomIdString + " -> " + predictedRoom.getName());
        return predictedRoom;

    } catch (Exception ex) {
        Logger.getLogger(PredictionService.class.getName()).log(Level.SEVERE, null, ex);
    }
    return null;
}

From source file:com.ivanrf.smsspam.SpamClassifier.java

License:Apache License

public static String classify(String model, String text, JTextArea log) {
    FilteredClassifier classifier = loadModel(model, log);

    //Create the instance
    ArrayList<String> fvNominalVal = new ArrayList<String>();
    fvNominalVal.add("ham");
    fvNominalVal.add("spam");

    Attribute attribute1 = new Attribute("spam_class", fvNominalVal);
    Attribute attribute2 = new Attribute("text", (List<String>) null);
    ArrayList<Attribute> fvWekaAttributes = new ArrayList<Attribute>();
    fvWekaAttributes.add(attribute1);/*from w w  w .  j a  va  2  s . c  o m*/
    fvWekaAttributes.add(attribute2);

    Instances instances = new Instances("Test relation", fvWekaAttributes, 1);
    instances.setClassIndex(0);

    DenseInstance instance = new DenseInstance(2);
    instance.setValue(attribute2, text);
    instances.add(instance);

    publishEstado("=== Instance created ===", log);
    publishEstado(instances.toString(), log);

    //Classify the instance
    try {
        publishEstado("=== Classifying instance ===", log);

        double pred = classifier.classifyInstance(instances.instance(0));

        publishEstado("=== Instance classified  ===", log);

        String classPredicted = instances.classAttribute().value((int) pred);
        publishEstado("Class predicted: " + classPredicted, log);

        return classPredicted;
    } catch (Exception e) {
        publishEstado("Error found when classifying the text", log);
        return null;
    }
}