Example usage for weka.classifiers.trees J48 J48

Introduction

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

Prototype

J48

Source Link

Usage

From source file:homemadeWEKA.java

public static void treeLearning(Instances data) throws Exception {
    //        Evaluation eval = new Evaluation(data);
    Classifier model_tree = (Classifier) new J48();
    model_tree.buildClassifier(data); // build classifier pruned tree, succeed
    //        String forPredictionsPrinting = null;
    //        double[] print_eval;
    //        print_eval = eval.evaluateModel(model_tree, data, forPredictionsPrinting);
    //        System.out.println(forPredictionsPrinting);
    save_model(model_tree);/*from  w w w  . j ava 2  s  .  c o m*/
    //        return model_tree; 
}

---

From source file:homemadeWEKA.java

public static void treeLearning_crossVal(Instances data) throws Exception {
    Evaluation eval = new Evaluation(data);
    J48 tree = new J48();
    eval.crossValidateModel(tree, data, 10, new Random(1));
    save_modelWithEval(tree, eval);//from w w w  . j  ava2s  . co  m
    //        System.out.println(eval.toSummaryString("\nResult of tree learning with cross validation 10 folds\n \n",false));
}

---

From source file:ClassificationClass.java

public Evaluation cls_c4_5(Instances data) {
    Evaluation eval = null;// w w  w.  ja v  a 2 s.  com
    try {
        Classifier classifier;
        PreparingSteps preparingSteps = new PreparingSteps();
        data.setClassIndex(data.numAttributes() - 1);
        classifier = new J48();
        classifier.buildClassifier(data);
        eval = new Evaluation(data);
        eval.evaluateModel(classifier, data);

        System.out.println(eval.toSummaryString());
    } catch (Exception ex) {
        Logger.getLogger(ClassificationClass.class.getName()).log(Level.SEVERE, null, ex);
    }
    return eval;
}

---

From source file:adams.ml.model.classification.WekaClassifier.java

License:Open Source License

/**
 * Adds options to the internal list of options.
 *///from  w w  w  . j  av a 2 s  . c  o  m
@Override
public void defineOptions() {
    super.defineOptions();

    m_OptionManager.add("classifier", "classifier", new J48());
}

---

From source file:algoritmogeneticocluster.NewClass.java

public static void main(String[] args) throws Exception {
    BufferedReader datafile = readDataFile("tabela10.arff");

    Instances data = new Instances(datafile);
    data.setClassIndex(data.numAttributes() - 1);

    // Do 10-split cross validation
    Instances[][] split = crossValidationSplit(data, 10);

    // Separate split into training and testing arrays
    Instances[] trainingSplits = split[0];
    Instances[] testingSplits = split[1];

    // Use a set of classifiers
    Classifier[] models = { new SMO(), new J48(), // a decision tree
            new PART(), new DecisionTable(), //decision table majority classifier
            new DecisionStump() //one-level decision tree

    };//from  www .j a v  a 2  s .c  o  m

    // Run for each model
    for (int j = 0; j < models.length; j++) {

        // Collect every group of predictions for current model in a FastVector
        FastVector predictions = new FastVector();

        // For each training-testing split pair, train and test the classifier
        for (int i = 0; i < trainingSplits.length; i++) {
            Evaluation validation = classify(models[j], trainingSplits[i], testingSplits[i]);

            predictions.appendElements(validation.predictions());

            // Uncomment to see the summary for each training-testing pair.
            //System.out.println(models[j].toString());
        }

        // Calculate overall accuracy of current classifier on all splits
        double accuracy = calculateAccuracy(predictions);

        // Print current classifier's name and accuracy in a complicated,
        // but nice-looking way.
        System.out.println("Accuracy of " + models[j].getClass().getSimpleName() + ": "
                + String.format("%.2f%%", accuracy) + "\n---------------------------------");
    }

}

---

From source file:aprendizadodemaquina.classificadores.ClassificadorDT.java

License:Open Source License

@Override
public int treinar(File arquivoTreinamento, String parametros) {

    Logger.getLogger("ARS logger").info("Treinamento de classificador J48");
    // TODO: Verificar por que os parmetros dos classificadores no esto funcionando

    try {//from   w ww.  ja  v  a2  s  .  co  m

        ConverterUtils.DataSource fonte = new ConverterUtils.DataSource(arquivoTreinamento.getAbsolutePath());
        dadosTreinamento = fonte.getDataSet();

        // Identifica o atributo que ser a classe de interesse (ltimo atributo = qual relao )
        dadosTreinamento.setClassIndex(dadosTreinamento.numAttributes() - 1);

        // Cria um classificador que aceita filtros
        classificador = new FilteredClassifier();
        classificador.setClassifier(new J48());

        // Seleciona os atributos que no so parte da classificacao
        // TODO: SE OS DADOS DE TREINAMENTO TIVEREM A FEATURE DE IDENTIFICAO...
        /*
        Remove remove = new Remove();
        int[] atributosRemovidos = new int[4];
        atributosRemovidos[0] = 0;   // ID da sentena
        atributosRemovidos[1] = 1;   // termo1
        atributosRemovidos[2] = 2;   // termo2
        remove.setAttributeIndicesArray( atributosRemovidos );
        // Acopla o filtro de remoo ao classificador
        fc.setFilter( remove );
        */
        // FIM-SE

        //                String []param = weka.core.Utils.splitOptions(parametros[cmbTipoClassificador1.getSelectedIndex()]);
        //                fc.setOptions(param);

        // Faz o treinamento do classificador
        classificador.buildClassifier(dadosTreinamento);

        return 0;

    } catch (Exception ex) {
        Logger.getLogger("ARS logger").log(Level.SEVERE, null, ex);
        if (ex instanceof IllegalArgumentException) {
            javax.swing.JOptionPane.showMessageDialog(null,
                    "O arquivo de treinamento fornecido no  um arquivo ARFF vlido", "Erro",
                    javax.swing.JOptionPane.ERROR_MESSAGE);
        }
        return 1;
    }

}

---

From source file:at.aictopic1.sentimentanalysis.machinelearning.impl.J48Classifier.java

/**
 * sets classifier/*  w  ww .j ava 2  s  .c o m*/
 */
@Override
protected void setClassifier() {

    //classifier
    this.usedClassifier = new J48();
    //.. other options
    this.fcClassifier.setClassifier(this.usedClassifier);
}

---

From source file:au.edu.usyd.it.yangpy.sampling.BPSO.java

License:Open Source License

/**
 * the target function in fitness form/*w w  w . ja  v a 2 s  .c o m*/
 * 
 * @return   classification accuracy
 */
public double ensembleClassify() {
    double fitnessValue = 0.0;
    double classifiersScore = 0.0;

    /* load in the modified data set */
    try {
        Instances reducedSet = new Instances(new BufferedReader(new FileReader("reduced.arff")));
        reducedSet.setClassIndex(reducedSet.numAttributes() - 1);

        // calculating the evaluation values using each classifier respectively
        if (verbose == true) {
            System.out.println();
            System.out.println(" |----------J4.8-----------|");
            System.out.println(" |            |            |");
        }
        J48 tree = new J48();
        classifiersScore = classify(tree, reducedSet, internalTest);
        fitnessValue += classifiersScore;

        if (verbose == true) {
            System.out.println();
            System.out.println(" |-----3NearestNeighbor----|");
            System.out.println(" |            |            |");
        }
        IBk nn3 = new IBk(3);
        classifiersScore = classify(nn3, reducedSet, internalTest);
        fitnessValue += classifiersScore;

        if (verbose == true) {
            System.out.println();
            System.out.println(" |--------NaiveBayes-------|");
            System.out.println(" |            |            |");
        }
        NaiveBayes nb = new NaiveBayes();
        classifiersScore = classify(nb, reducedSet, internalTest);
        fitnessValue += classifiersScore;

        if (verbose == true) {
            System.out.println();
            System.out.println(" |-------RandomForest------|");
            System.out.println(" |            |            |");
        }
        RandomForest rf5 = new RandomForest();
        rf5.setNumTrees(5);
        classifiersScore = classify(rf5, reducedSet, internalTest);
        fitnessValue += classifiersScore;

        if (verbose == true) {
            System.out.println();
            System.out.println(" |---------Logistic--------|");
            System.out.println(" |            |            |");
        }
        Logistic log = new Logistic();
        classifiersScore = classify(log, reducedSet, internalTest);
        fitnessValue += classifiersScore;

    } catch (IOException ioe) {
        ioe.printStackTrace();
    }

    fitnessValue /= 5;

    if (verbose == true) {
        System.out.println();
        System.out.println("Fitness: " + fitnessValue);
        System.out.println("---------------------------------------------------");
    }

    return fitnessValue;
}

---

From source file:au.edu.usyd.it.yangpy.snp.Ensemble.java

License:Open Source License

public void ensemble(String mode) throws Exception {

    numInstances = test.numInstances();//from  ww  w .  ja  v a  2s.c o  m
    numClasses = test.numClasses();
    givenValue = new double[numInstances];
    predictDistribution = new double[numClassifiers][numInstances][numClasses];
    predictValue = new double[numClassifiers][numInstances];
    voteValue = new double[numInstances][numClasses];

    // Setting the given class values of the test instances.
    for (int i = 0; i < numInstances; i++) {
        givenValue[i] = test.instance(i).classValue();
    }

    // Calculating the predicted class values using each classifier respectively.
    // J48 coverTree1NN KStar coverTree3NN coverTree5NN

    J48 tree = new J48();
    tree.setUnpruned(true);
    aucClassifiers[0] = classify(tree, 0);

    KStar kstar = new KStar();
    aucClassifiers[1] = classify(kstar, 1);

    IBk ctnn1 = new IBk(1);
    CoverTree search = new CoverTree();
    ctnn1.setNearestNeighbourSearchAlgorithm(search);
    aucClassifiers[2] = classify(ctnn1, 2);

    IBk ctnn3 = new IBk(3);
    ctnn3.setNearestNeighbourSearchAlgorithm(search);
    aucClassifiers[3] = classify(ctnn3, 3);

    IBk ctnn5 = new IBk(5);
    ctnn5.setNearestNeighbourSearchAlgorithm(search);
    aucClassifiers[4] = classify(ctnn5, 4);

    // Print the classification results if in print mode.
    if (mode.equals("v")) {
        System.out.println("J48   AUC: " + aucClassifiers[0]);
        System.out.println("KStar AUC: " + aucClassifiers[1]);
        System.out.println("CTNN1 AUC: " + aucClassifiers[2]);
        System.out.println("CTNN3 AUC: " + aucClassifiers[3]);
        System.out.println("CTNN5 AUC: " + aucClassifiers[4]);
        System.out.println("   -         -   ");
    }
}

---

From source file:boa.aggregators.DecisionTreeAggregator.java

License:Apache License

/** {@inheritDoc} */
@Override//from  www . j a v  a  2s  .c  o  m
public void finish() throws IOException, InterruptedException {
    int NumOfAttributes = this.getVectorSize();
    List<Attribute> attributes = new ArrayList<Attribute>();
    FastVector fvAttributes = new FastVector(NumOfAttributes);

    for (int i = 0; i < NumOfAttributes; i++) {
        attributes.add(new Attribute("Attribute" + i));
        fvAttributes.addElement(attributes.get(i));
    }

    Instances trainingSet = new Instances("DecisionTree", fvAttributes, 1);
    trainingSet.setClassIndex(NumOfAttributes - 1);

    for (List<Double> vector : this.vectors.values()) {
        Instance instance = new Instance(NumOfAttributes);
        for (int i = 0; i < vector.size(); i++) {
            instance.setValue((Attribute) fvAttributes.elementAt(i), vector.get(i));
        }
        trainingSet.add(instance);
    }

    try {
        this.model = new J48();
        this.model.setOptions(options);
        this.model.buildClassifier(trainingSet);
    } catch (Exception ex) {
    }

    this.saveModel(this.model);
}

---

• «
• 1
• 2
• 3
• 4
• 5
• 6
• 7
• 8
• 9
• 10
• 11
• 12
• 13
• 14
• »