Example usage for weka.classifiers.trees J48 setConfidenceFactor

Introduction

In this page you can find the example usage for weka.classifiers.trees J48 setConfidenceFactor.

Prototype

public void setConfidenceFactor(float v) 

Source Link

Document

Set the value of CF.

Usage

From source file:kfst.classifier.WekaClassifier.java

License:Open Source License

/**
 * This method builds and evaluates the decision tree(DT) classifier.
 * The j48 are used as the DT classifier implemented in the Weka software.
 *
 * @param pathTrainData the path of the train set
 * @param pathTestData the path of the test set
 * @param confidenceValue The confidence factor used for pruning
 * @param minNumSampleInLeaf The minimum number of instances per leaf
 * /*from   ww  w  .j av a  2 s  .  co  m*/
 * @return the classification accuracy
 */
public static double dTree(String pathTrainData, String pathTestData, double confidenceValue,
        int minNumSampleInLeaf) {
    double resultValue = 0;
    try {
        BufferedReader readerTrain = new BufferedReader(new FileReader(pathTrainData));
        Instances dataTrain = new Instances(readerTrain);
        readerTrain.close();
        dataTrain.setClassIndex(dataTrain.numAttributes() - 1);

        BufferedReader readerTest = new BufferedReader(new FileReader(pathTestData));
        Instances dataTest = new Instances(readerTest);
        readerTest.close();
        dataTest.setClassIndex(dataTest.numAttributes() - 1);

        J48 decisionTree = new J48();
        decisionTree.setConfidenceFactor((float) confidenceValue);
        decisionTree.setMinNumObj(minNumSampleInLeaf);
        decisionTree.buildClassifier(dataTrain);
        Evaluation eval = new Evaluation(dataTest);
        eval.evaluateModel(decisionTree, dataTest);
        resultValue = 100 - (eval.errorRate() * 100);
    } catch (Exception ex) {
        Logger.getLogger(WekaClassifier.class.getName()).log(Level.SEVERE, null, ex);
    }
    return resultValue;
}

---

From source file:KFST.featureSelection.embedded.TreeBasedMethods.DecisionTreeBasedMethod.java

License:Open Source License

/**
 * {@inheritDoc }//w  w  w. ja  v a  2  s  .  c o  m
 */
@Override
protected String buildClassifier(Instances dataTrain) {
    try {
        if (TREE_TYPE == TreeType.C45) {
            J48 decisionTreeC45 = new J48();
            decisionTreeC45.setConfidenceFactor((float) confidenceValue);
            decisionTreeC45.setMinNumObj(minNumSampleInLeaf);
            decisionTreeC45.buildClassifier(dataTrain);
            return decisionTreeC45.toString();
        } else if (TREE_TYPE == TreeType.RANDOM_TREE) {
            RandomTree decisionTreeRandomTree = new RandomTree();
            decisionTreeRandomTree.setKValue(randomTreeKValue);
            decisionTreeRandomTree.setMaxDepth(randomTreeMaxDepth);
            decisionTreeRandomTree.setMinNum(randomTreeMinNum);
            decisionTreeRandomTree.setMinVarianceProp(randomTreeMinVarianceProp);
            decisionTreeRandomTree.buildClassifier(dataTrain);
            return decisionTreeRandomTree.toString();
        }
    } catch (Exception ex) {
        Logger.getLogger(DecisionTreeBasedMethod.class.getName()).log(Level.SEVERE, null, ex);
    }
    return "";
}

---

From source file:org.openml.webapplication.fantail.dc.landmarking.J48BasedLandmarker.java

License:Open Source License

public Map<String, Double> characterize(Instances data) {

    int numFolds = m_NumFolds;

    double score1 = 0.5;
    double score2 = 0.5;
    // double score3 = 0.5;

    double score3 = 0.5;
    double score4 = 0.5;
    // double score3 = 0.5;

    double score5 = 0.5;
    double score6 = 0.5;

    double score7 = 0.5;
    double score8 = 0.5;
    double score9 = 0.5;

    weka.classifiers.trees.J48 cls = new weka.classifiers.trees.J48();
    cls.setConfidenceFactor(0.00001f);

    try {/*from w  w  w. j  a  va  2  s  .c  om*/

        weka.classifiers.Evaluation eval = new weka.classifiers.Evaluation(data);

        eval.crossValidateModel(cls, data, numFolds, new java.util.Random(1));

        score1 = eval.pctIncorrect();
        score2 = eval.weightedAreaUnderROC();

        score7 = eval.kappa();

    } catch (Exception e) {
        e.printStackTrace();
    }

    //
    cls = new weka.classifiers.trees.J48();
    cls.setConfidenceFactor(0.0001f);

    try {

        weka.classifiers.Evaluation eval = new weka.classifiers.Evaluation(data);
        eval.crossValidateModel(cls, data, numFolds, new java.util.Random(1));

        score3 = eval.pctIncorrect();
        score4 = eval.weightedAreaUnderROC();

        score8 = eval.kappa();

    } catch (Exception e) {
        e.printStackTrace();
    }

    //
    cls = new weka.classifiers.trees.J48();
    cls.setConfidenceFactor(0.001f);

    try {

        weka.classifiers.Evaluation eval = new weka.classifiers.Evaluation(data);
        eval.crossValidateModel(cls, data, numFolds, new java.util.Random(1));

        score5 = eval.pctIncorrect();
        score6 = eval.weightedAreaUnderROC();

        score9 = eval.kappa();

    } catch (Exception e) {
        e.printStackTrace();
    }

    Map<String, Double> qualities = new HashMap<String, Double>();
    qualities.put(ids[0], score1);
    qualities.put(ids[1], score2);
    qualities.put(ids[2], score3);
    qualities.put(ids[3], score4);
    qualities.put(ids[4], score5);
    qualities.put(ids[5], score6);
    qualities.put(ids[6], score7);
    qualities.put(ids[7], score8);
    qualities.put(ids[8], score9);
    return qualities;
}

---

From source file:uv.datamining.tp2.WekaModeler.java

public static void generarArbol(File file, float cm) throws Exception {
    ArffLoader loader = new ArffLoader();
    loader.setFile(file);//w  w  w  .  java2 s  .  co m
    Instances data = loader.getDataSet();
    data.setClassIndex(data.numAttributes() - 1); //columna con el atributo clase
    J48 tree = new J48();
    tree.setConfidenceFactor(cm);
    tree.buildClassifier(data);
    Evaluation eval = new Evaluation(data);
    eval.evaluateModel(tree, data);
    System.out.println(eval.toSummaryString());

    weka.core.SerializationHelper.write(
            file.getAbsolutePath().substring(0, file.getAbsolutePath().lastIndexOf(".")) + ".model", tree);

}

---