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:development.GoodHonoursPrediction.java

public static void main(String[] args) {
    Instances data = ClassifierTools.loadData("C:\\Admin\\Perfomance Analysis\\GoodHonsClassification");
    RandomForest rf = new RandomForest();
    double[][] a = ClassifierTools.crossValidationWithStats(rf, data, data.numInstances());
    System.out.println(" Random forest LOOCV accuracy =" + a[0][0]);
    J48 tree = new J48();
    a = ClassifierTools.crossValidationWithStats(tree, data, data.numInstances());
    System.out.println(" C4.5 LOOCV accuracy =" + a[0][0]);
    IBk knn = new IBk(11);
    knn.setCrossValidate(true);/*from w  w w  . ja va2 s  . c  om*/
    a = ClassifierTools.crossValidationWithStats(knn, data, data.numInstances());
    System.out.println(" KNN LOOCV accuracy =" + a[0][0]);
    NaiveBayes nb = new NaiveBayes();
    a = ClassifierTools.crossValidationWithStats(nb, data, data.numInstances());
    System.out.println(" Naive Bayes LOOCV accuracy =" + a[0][0]);

    /*       try {
    tree.buildClassifier(data);
           System.out.println(" Tree ="+tree);
           Classifier cls = new J48();
            Evaluation eval = new Evaluation(data);
            Random rand = new Random(1);  // using seed = 1
            int folds = data.numInstances();
            eval.crossValidateModel(cls, data, folds, rand);
            System.out.println(eval.toSummaryString());        
                   
           tree.getTechnicalInformation();
           } catch (Exception ex) {
    Logger.getLogger(GoodHonoursPrediction.class.getName()).log(Level.SEVERE, null, ex);
           }
           */

}

---

From source file:DiversifyQuery.DivTopK.java

public static void table4_5() throws Exception {

    // Initialise classifiers required for this experiment
    classifiers = new Classifier[8];
    classifiers[0] = new ShapeletTreeClassifier("infoTree.txt");
    classifiers[1] = new J48();
    classifiers[2] = new IB1();
    classifiers[3] = new NaiveBayes();
    classifiers[4] = new BayesNet();
    classifiers[5] = new RandomForest();
    classifiers[6] = new RotationForest();
    classifiers[7] = new SMO();

    // Set up names for the classifiers - only used for output
    classifierNames = new String[8];
    classifierNames[0] = "ShapeletTree";
    classifierNames[1] = "C4.5";
    classifierNames[2] = "1NN";
    classifierNames[3] = "Naive Bayes";
    classifierNames[4] = "Bayesian Network";
    classifierNames[5] = "Random Forest";
    classifierNames[6] = "Rotation Forest";
    classifierNames[7] = "SVM (linear)";

    //        if ((classifierToProcessIndex < 1 || classifierToProcessIndex > classifiers.length) && classifierToProcessIndex != -1) {
    //            throw new IOException("Invalid classifier identifier.");
    //        } else {
    //            if (classifierToProcessIndex != -1) {
    //                classifierToProcessIndex--;
    //            }
    //        }//from   w  w w.j  a v  a2 s.  com

    // Compute classifier accuracies for each classifier
    double accuracies[] = new double[classifiers.length];

    for (int i = 1; i < classifiers.length; i++) {

        //if (i == classifierToProcessIndex || classifierToProcessIndex == -1) {
        accuracies[i] = classifierAccuracy(i, true, true);

    }

    // Write experiment output to file 
    writeFileContent(accuracies);
}

---

From source file:edu.brandeis.wisedb.scheduler.training.decisiontree.DTSearcher.java

License:Open Source License

private void init(Instances is, QueryTimePredictor qtp, ModelSLA sla) throws Exception {
    wekaDataSet = is;/*from  w w w .j a  v  a2s  . c  om*/

    this.qtp = qtp;
    this.sla = sla;

    // the last attribute is the action / class label
    wekaDataSet.setClassIndex(wekaDataSet.numAttributes() - 1);

    // build the tree with a pruning level of 0.25
    // and a minimum of 2 instances per leaf node
    String[] options = new String[] { "-C", "0.05", "-M", "2" };

    tree = new J48();
    tree.setOptions(options);

    // do 10 fold cross validation

    // do NOT train the classifier before evaluation!
    /*
    Evaluation eval = new Evaluation(wekaDataSet);
    eval.crossValidateModel(tree, wekaDataSet, 10, new Random());
    log.info("Model CV: correct/incorrect: " + eval.correct() + "/" + eval.incorrect());
     */

    // build the tree
    tree.buildClassifier(wekaDataSet);

    attributes = new Attribute[wekaDataSet.numAttributes()];
    for (int i = 0; i < wekaDataSet.numAttributes(); i++) {
        attributes[i] = wekaDataSet.attribute(i);
    }

    log.finer("Got attributes: " + Arrays.toString(attributes));
}

---

From source file:edu.cmu.cs.in.hoop.hoops.analyze.HoopWekaML.java

License:Open Source License

/**
 *
 *///from w  w w . java 2  s .  c o  m
public HoopWekaML() {
    setClassName("HoopWekaML");
    debug("HoopWekaML ()");

    removeOutPort("KV");

    setHoopDescription("Run Weka Machine Learning");

    String[] options = new String[1];
    options[0] = "-U"; // unpruned tree
    J48 tree = new J48(); // new instance of tree

    try {
        tree.setOptions(options);
    } catch (Exception e1) {
        // TODO Auto-generated catch block
        e1.printStackTrace();
    }

    // Declare a nominal attribute along with its values
    FastVector fvNominalVal = new FastVector(3);
    fvNominalVal.addElement("blue");
    fvNominalVal.addElement("gray");
    fvNominalVal.addElement("black");

    // Declare the class attribute along with its values
    FastVector fvClassVal = new FastVector(2);
    fvClassVal.addElement("positive");
    fvClassVal.addElement("negative");
    Attribute ClassAttribute = new Attribute("theClass", fvClassVal);

    // Declare two numeric attributes
    Attribute Attribute1 = new Attribute("firstNumeric");
    Attribute Attribute2 = new Attribute("secondNumeric");
    Attribute Attribute3 = new Attribute("aNominal", fvNominalVal);

    // Declare the feature vector
    FastVector fvWekaAttributes = new FastVector(4);
    fvWekaAttributes.addElement(Attribute1);
    fvWekaAttributes.addElement(Attribute2);
    fvWekaAttributes.addElement(Attribute3);
    fvWekaAttributes.addElement(ClassAttribute);

    // Create an empty training set
    Instances isTrainingSet = new Instances("Rel", fvWekaAttributes, 10);

    // Set class index
    isTrainingSet.setClassIndex(3);

    try {
        tree.buildClassifier(isTrainingSet);
    } catch (Exception e) {
        // TODO Auto-generated catch block
        e.printStackTrace();
    }
}

---

From source file:edu.cuny.qc.speech.AuToBI.featureextractor.XValSpectrumPADFeatureExtractor.java

License:Open Source License

/**
 * Generates cross validated pitch accent detection hypotheses using energy information drawn from the assigned
 * spectral region.//from  ww  w.  j  a v a 2 s .c  o  m
 *
 * @param regions The regions to extract features from.
 * @throws FeatureExtractorException if something goes wrong.
 */
public void extractFeatures(List regions) throws FeatureExtractorException {
    // Construct a feature set.
    FeatureSet feature_set = fs.newInstance();

    // Extract spectrum features.
    feature_set.setDataPoints((List<Word>) regions);
    try {
        PartitionUtils.assignStratifiedFoldNum((List<Word>) regions, FOLD_ASSIGNMENT_FEATURE, num_folds,
                feature_set.getClassAttribute());
    } catch (AuToBIException e) {
        throw new FeatureExtractorException(e.getMessage());
    }

    // Train n-fold cross validated prediction features.
    for (int fold_num = 0; fold_num < num_folds; ++fold_num) {
        AuToBIClassifier classifier = new WekaClassifier(new J48());

        FeatureSet training_fs = fs.newInstance();

        List<Word> training_regions = new ArrayList<Word>();
        List<Word> testing_regions = new ArrayList<Word>();
        try {
            PartitionUtils.splitData((List<Word>) regions, training_regions, testing_regions, fold_num,
                    FOLD_ASSIGNMENT_FEATURE);
        } catch (AuToBIException e) {
            // This should never happen.  If there is a problem with splitData it would have thrown
            // an exception during the fold assignment method assignStratifiedFoldNum
            throw new FeatureExtractorException(e.getMessage());
        }
        training_fs.setDataPoints(training_regions);
        training_fs.constructFeatures();
        try {
            classifier.train(training_fs);
        } catch (Exception e) {
            throw new FeatureExtractorException(e.getMessage());
        }

        for (Word w : testing_regions) {
            try {
                Distribution result = classifier.distributionForInstance(w);

                w.setAttribute("nominal_bark_" + low + "_" + high + "__prediction",
                        result.getKeyWithMaximumValue());
                w.setAttribute("bark_" + low + "_" + high + "__prediction_confidence",
                        result.get(result.getKeyWithMaximumValue()));
                w.setAttribute("bark_" + low + "_" + high + "__prediction_confidence_accented",
                        result.get(ACCENTED_VALUE));
            } catch (Exception e) {
                throw new FeatureExtractorException(e.getMessage());
            }
        }
    }
}

---

From source file:epsi.i5.datamining.Weka.java

public void excutionAlgo() throws FileNotFoundException, IOException, Exception {
    BufferedReader reader = new BufferedReader(new FileReader("src/epsi/i5/data/" + fileOne + ".arff"));
    Instances data = new Instances(reader);
    reader.close();/* w  w  w .j a va2  s.c o m*/
    //System.out.println(data.attribute(0));
    data.setClass(data.attribute(0));
    NaiveBayes NB = new NaiveBayes();
    NB.buildClassifier(data);
    Evaluation naiveBayes = new Evaluation(data);
    naiveBayes.crossValidateModel(NB, data, 10, new Random(1));
    naiveBayes.evaluateModel(NB, data);
    //System.out.println(test.confusionMatrix() + "1");
    //System.out.println(test.correct() + "2");
    System.out.println("*****************************");
    System.out.println("******** Naive Bayes ********");
    System.out.println(naiveBayes.toMatrixString());
    System.out.println("*****************************");
    System.out.println("**** Pourcentage Correct ****");
    System.out.println(naiveBayes.pctCorrect());
    System.out.println("");
    J48 j = new J48();
    j.buildClassifier(data);
    Evaluation jeval = new Evaluation(data);
    jeval.crossValidateModel(j, data, 10, new Random(1));
    jeval.evaluateModel(j, data);
    System.out.println("*****************************");
    System.out.println("************ J48 ************");
    System.out.println(jeval.toMatrixString());
    System.out.println("*****************************");
    System.out.println("**** Pourcentage Correct ****");
    System.out.println(jeval.pctCorrect());
    System.out.println("");
    DecisionTable DT = new DecisionTable();
    DT.buildClassifier(data);
    Evaluation decisionTable = new Evaluation(data);
    decisionTable.crossValidateModel(DT, data, 10, new Random(1));
    decisionTable.evaluateModel(DT, data);
    System.out.println("*****************************");
    System.out.println("******* DecisionTable *******");
    System.out.println(decisionTable.toMatrixString());
    System.out.println("*****************************");
    System.out.println("**** Pourcentage Correct ****");
    System.out.println(decisionTable.pctCorrect());
    System.out.println("");
    OneR OR = new OneR();
    OR.buildClassifier(data);
    Evaluation oneR = new Evaluation(data);
    oneR.crossValidateModel(OR, data, 10, new Random(1));
    oneR.evaluateModel(OR, data);
    System.out.println("*****************************");
    System.out.println("************ OneR ***********");
    System.out.println(oneR.toMatrixString());
    System.out.println("*****************************");
    System.out.println("**** Pourcentage Correct ****");
    System.out.println(oneR.pctCorrect());

    //Polarit
    data.setClass(data.attribute(1));
    System.out.println("");
    M5Rules MR = new M5Rules();
    MR.buildClassifier(data);
    Evaluation m5rules = new Evaluation(data);
    m5rules.crossValidateModel(MR, data, 10, new Random(1));
    m5rules.evaluateModel(MR, data);
    System.out.println("*****************************");
    System.out.println("********** M5Rules **********");
    System.out.println(m5rules.correlationCoefficient());

    System.out.println("");
    LinearRegression LR = new LinearRegression();
    LR.buildClassifier(data);
    Evaluation linearR = new Evaluation(data);
    linearR.crossValidateModel(LR, data, 10, new Random(1));
    linearR.evaluateModel(LR, data);
    System.out.println("*****************************");
    System.out.println("********** linearR **********");
    System.out.println(linearR.correlationCoefficient());
}

---

From source file:ergasia2pkg.ergasia2_main.java

public static void ML_RUS_exec() throws InvalidDataFormatException, Exception {

    ML_RUS transformer_under = new ML_RUS(0.1f);

    MultiLabelInstances mli = new MultiLabelInstances("enron.arff", "enron.xml");
    MultiLabelInstances mliCloneUnder = transformer_under.transformInstances(mli);

    RAkEL rak = new RAkEL();
    HOMER hom = new HOMER();
    CalibratedLabelRanking cal = new CalibratedLabelRanking(new J48());
    IBLR_ML ibl = new IBLR_ML();
    Evaluator eval = new Evaluator();
    MultipleEvaluation evaluationsUnder_rak = eval.crossValidate(rak, mliCloneUnder, 10);
    MultipleEvaluation evaluationsUnder_hom = eval.crossValidate(hom, mliCloneUnder, 10);
    MultipleEvaluation evaluationsUnder_cal = eval.crossValidate(cal, mliCloneUnder, 10);
    MultipleEvaluation evaluationsUnder_ibl = eval.crossValidate(ibl, mliCloneUnder, 10);
    System.out.println("========== ML-Undersampling Evaluations (RAkEL) =========");
    System.out.println("Example-Based Accuracy: " + evaluationsUnder_rak.getMean("Example-Based Accuracy"));
    System.out.println("Micro-averaged F-Measure: " + evaluationsUnder_rak.getMean("Micro-averaged F-Measure"));
    System.out.println("Macro-averaged F-Measure: " + evaluationsUnder_rak.getMean("Macro-averaged F-Measure"));
    System.out.println("========== ML-Undersampling Evaluations (HOMER) =========");
    System.out.println("Example-Based Accuracy: " + evaluationsUnder_hom.getMean("Example-Based Accuracy"));
    System.out.println("Micro-averaged F-Measure: " + evaluationsUnder_hom.getMean("Micro-averaged F-Measure"));
    System.out.println("Macro-averaged F-Measure: " + evaluationsUnder_hom.getMean("Macro-averaged F-Measure"));
    System.out.println("========== ML-Undersampling Evaluations (CalibratedLabelRanking) =========");
    System.out.println("Example-Based Accuracy: " + evaluationsUnder_cal.getMean("Example-Based Accuracy"));
    System.out.println("Micro-averaged F-Measure: " + evaluationsUnder_cal.getMean("Micro-averaged F-Measure"));
    System.out.println("Macro-averaged F-Measure: " + evaluationsUnder_cal.getMean("Macro-averaged F-Measure"));
    System.out.println("========== ML-Undersampling Evaluations (IBLR_ML) =========");
    System.out.println("Example-Based Accuracy: " + evaluationsUnder_ibl.getMean("Example-Based Accuracy"));
    System.out.println("Micro-averaged F-Measure: " + evaluationsUnder_ibl.getMean("Micro-averaged F-Measure"));
    System.out.println("Macro-averaged F-Measure: " + evaluationsUnder_ibl.getMean("Macro-averaged F-Measure"));
}

---

From source file:ergasia2pkg.ergasia2_main.java

public static void ML_ROS_exec() throws InvalidDataFormatException, Exception {

    ML_ROS transformer_over = new ML_ROS(0.1f);

    MultiLabelInstances mli = new MultiLabelInstances("CAL500.arff", "CAL500.xml");
    MultiLabelInstances mliCloneOver = transformer_over.transformInstances(mli);

    RAkEL rak = new RAkEL();
    HOMER hom = new HOMER();
    CalibratedLabelRanking cal = new CalibratedLabelRanking(new J48());
    IBLR_ML ibl = new IBLR_ML();
    Evaluator eval = new Evaluator();
    MultipleEvaluation evaluationsUnder_rak = eval.crossValidate(rak, mliCloneOver, 10);
    MultipleEvaluation evaluationsUnder_hom = eval.crossValidate(hom, mliCloneOver, 10);
    MultipleEvaluation evaluationsUnder_cal = eval.crossValidate(cal, mliCloneOver, 10);
    MultipleEvaluation evaluationsUnder_ibl = eval.crossValidate(ibl, mliCloneOver, 10);
    System.out.println("========== ML-Undersampling Evaluations (RAkEL) =========");
    System.out.println("Example-Based Accuracy: " + evaluationsUnder_rak.getMean("Example-Based Accuracy"));
    System.out.println("Micro-averaged F-Measure: " + evaluationsUnder_rak.getMean("Micro-averaged F-Measure"));
    System.out.println("Macro-averaged F-Measure: " + evaluationsUnder_rak.getMean("Macro-averaged F-Measure"));
    System.out.println("========== ML-Undersampling Evaluations (HOMER) =========");
    System.out.println("Example-Based Accuracy: " + evaluationsUnder_hom.getMean("Example-Based Accuracy"));
    System.out.println("Micro-averaged F-Measure: " + evaluationsUnder_hom.getMean("Micro-averaged F-Measure"));
    System.out.println("Macro-averaged F-Measure: " + evaluationsUnder_hom.getMean("Macro-averaged F-Measure"));
    System.out.println("========== ML-Undersampling Evaluations (CalibratedLabelRanking) =========");
    System.out.println("Example-Based Accuracy: " + evaluationsUnder_cal.getMean("Example-Based Accuracy"));
    System.out.println("Micro-averaged F-Measure: " + evaluationsUnder_cal.getMean("Micro-averaged F-Measure"));
    System.out.println("Macro-averaged F-Measure: " + evaluationsUnder_cal.getMean("Macro-averaged F-Measure"));
    System.out.println("========== ML-Undersampling Evaluations (IBLR_ML) =========");
    System.out.println("Example-Based Accuracy: " + evaluationsUnder_ibl.getMean("Example-Based Accuracy"));
    System.out.println("Micro-averaged F-Measure: " + evaluationsUnder_ibl.getMean("Micro-averaged F-Measure"));
    System.out.println("Macro-averaged F-Measure: " + evaluationsUnder_ibl.getMean("Macro-averaged F-Measure"));
}

---

From source file:ergasia2pkg.ergasia2_main.java

public static void LP_ROS_exec() throws InvalidDataFormatException, Exception {
    LP_ROS transformer_over = new LP_ROS(0.1f);

    MultiLabelInstances mli = new MultiLabelInstances("CAL500.arff", "CAL500.xml");
    MultiLabelInstances mliCloneOver = transformer_over.transformInstances(mli);

    RAkEL rak = new RAkEL();
    HOMER hom = new HOMER();
    CalibratedLabelRanking cal = new CalibratedLabelRanking(new J48());
    IBLR_ML ibl = new IBLR_ML();
    Evaluator eval = new Evaluator();
    MultipleEvaluation evaluationsUnder_rak = eval.crossValidate(rak, mliCloneOver, 10);
    MultipleEvaluation evaluationsUnder_hom = eval.crossValidate(hom, mliCloneOver, 10);
    MultipleEvaluation evaluationsUnder_cal = eval.crossValidate(cal, mliCloneOver, 10);
    MultipleEvaluation evaluationsUnder_ibl = eval.crossValidate(ibl, mliCloneOver, 10);
    System.out.println("========== ML-Undersampling Evaluations (RAkEL) =========");
    System.out.println("Example-Based Accuracy: " + evaluationsUnder_rak.getMean("Example-Based Accuracy"));
    System.out.println("Micro-averaged F-Measure: " + evaluationsUnder_rak.getMean("Micro-averaged F-Measure"));
    System.out.println("Macro-averaged F-Measure: " + evaluationsUnder_rak.getMean("Macro-averaged F-Measure"));
    System.out.println("========== ML-Undersampling Evaluations (HOMER) =========");
    System.out.println("Example-Based Accuracy: " + evaluationsUnder_hom.getMean("Example-Based Accuracy"));
    System.out.println("Micro-averaged F-Measure: " + evaluationsUnder_hom.getMean("Micro-averaged F-Measure"));
    System.out.println("Macro-averaged F-Measure: " + evaluationsUnder_hom.getMean("Macro-averaged F-Measure"));
    System.out.println("========== ML-Undersampling Evaluations (CalibratedLabelRanking) =========");
    System.out.println("Example-Based Accuracy: " + evaluationsUnder_cal.getMean("Example-Based Accuracy"));
    System.out.println("Micro-averaged F-Measure: " + evaluationsUnder_cal.getMean("Micro-averaged F-Measure"));
    System.out.println("Macro-averaged F-Measure: " + evaluationsUnder_cal.getMean("Macro-averaged F-Measure"));
    System.out.println("========== ML-Undersampling Evaluations (IBLR_ML) =========");
    System.out.println("Example-Based Accuracy: " + evaluationsUnder_ibl.getMean("Example-Based Accuracy"));
    System.out.println("Micro-averaged F-Measure: " + evaluationsUnder_ibl.getMean("Micro-averaged F-Measure"));
    System.out.println("Macro-averaged F-Measure: " + evaluationsUnder_ibl.getMean("Macro-averaged F-Measure"));
}

---

From source file:ergasia2pkg.ergasia2_main.java

public static void LP_RUS_exec() throws InvalidDataFormatException, Exception {
    LP_RUS transformer_under = new LP_RUS(0.1f);

    MultiLabelInstances mli = new MultiLabelInstances("CAL500.arff", "CAL500.xml");
    MultiLabelInstances mliCloneUnder = transformer_under.transformInstances(mli);

    RAkEL rak = new RAkEL();
    HOMER hom = new HOMER();
    CalibratedLabelRanking cal = new CalibratedLabelRanking(new J48());
    IBLR_ML ibl = new IBLR_ML();
    Evaluator eval = new Evaluator();
    MultipleEvaluation evaluationsUnder_rak = eval.crossValidate(rak, mliCloneUnder, 10);
    MultipleEvaluation evaluationsUnder_hom = eval.crossValidate(hom, mliCloneUnder, 10);
    MultipleEvaluation evaluationsUnder_cal = eval.crossValidate(cal, mliCloneUnder, 10);
    MultipleEvaluation evaluationsUnder_ibl = eval.crossValidate(ibl, mliCloneUnder, 10);
    System.out.println("========== ML-Undersampling Evaluations (RAkEL) =========");
    System.out.println("Example-Based Accuracy: " + evaluationsUnder_rak.getMean("Example-Based Accuracy"));
    System.out.println("Micro-averaged F-Measure: " + evaluationsUnder_rak.getMean("Micro-averaged F-Measure"));
    System.out.println("Macro-averaged F-Measure: " + evaluationsUnder_rak.getMean("Macro-averaged F-Measure"));
    System.out.println("========== ML-Undersampling Evaluations (HOMER) =========");
    System.out.println("Example-Based Accuracy: " + evaluationsUnder_hom.getMean("Example-Based Accuracy"));
    System.out.println("Micro-averaged F-Measure: " + evaluationsUnder_hom.getMean("Micro-averaged F-Measure"));
    System.out.println("Macro-averaged F-Measure: " + evaluationsUnder_hom.getMean("Macro-averaged F-Measure"));
    System.out.println("========== ML-Undersampling Evaluations (CalibratedLabelRanking) =========");
    System.out.println("Example-Based Accuracy: " + evaluationsUnder_cal.getMean("Example-Based Accuracy"));
    System.out.println("Micro-averaged F-Measure: " + evaluationsUnder_cal.getMean("Micro-averaged F-Measure"));
    System.out.println("Macro-averaged F-Measure: " + evaluationsUnder_cal.getMean("Macro-averaged F-Measure"));
    System.out.println("========== ML-Undersampling Evaluations (IBLR_ML) =========");
    System.out.println("Example-Based Accuracy: " + evaluationsUnder_ibl.getMean("Example-Based Accuracy"));
    System.out.println("Micro-averaged F-Measure: " + evaluationsUnder_ibl.getMean("Micro-averaged F-Measure"));
    System.out.println("Macro-averaged F-Measure: " + evaluationsUnder_ibl.getMean("Macro-averaged F-Measure"));
}

---

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