Example usage for weka.classifiers Classifier distributionForInstance

List of usage examples for weka.classifiers Classifier distributionForInstance

Introduction

In this page you can find the example usage for weka.classifiers Classifier distributionForInstance.

Prototype

public double[] distributionForInstance(Instance instance) throws Exception;

Source Link

Document

Predicts the class memberships for a given instance.

Usage

From source file:bme.mace.logicdomain.Evaluation.java

License:Open Source License

/**
 * Evaluates the classifier on a single instance.
 * //from  w ww  . ja  va  2s .c  o  m
 * @param classifier machine learning classifier
 * @param instance the test instance to be classified
 * @return the prediction made by the clasifier
 * @throws Exception if model could not be evaluated successfully or the data
 *           contains string attributes
 */
public double evaluateModelOnce(Classifier classifier, Instance instance) throws Exception {

    Instance classMissing = (Instance) instance.copy();
    double pred = 0;
    classMissing.setDataset(instance.dataset());
    classMissing.setClassMissing();
    if (m_ClassIsNominal) {
        double[] dist = classifier.distributionForInstance(classMissing);
        pred = Utils.maxIndex(dist);
        if (dist[(int) pred] <= 0) {
            pred = Instance.missingValue();
        }
        updateStatsForClassifier(dist, instance);
    } else {
        pred = classifier.classifyInstance(classMissing);
        updateStatsForPredictor(pred, instance);
    }
    return pred;
}

From source file:bme.mace.logicdomain.Evaluation.java

License:Open Source License

/**
 * store the prediction made by the classifier as a string
 * /* w w w. j a  va2 s  .  c om*/
 * @param classifier the classifier to use
 * @param inst the instance to generate text from
 * @param instNum the index in the dataset
 * @param attributesToOutput the indices of the attributes to output
 * @param printDistribution prints the complete distribution for nominal
 *          classes, not just the predicted value
 * @return the prediction as a String
 * @throws Exception if something goes wrong
 * @see #printClassifications(Classifier, Instances, String, int, Range,
 *      boolean)
 */
protected static String predictionText(Classifier classifier, Instance inst, int instNum,
        Range attributesToOutput, boolean printDistribution)

        throws Exception {

    StringBuffer result = new StringBuffer();
    int width = 10;
    int prec = 3;

    Instance withMissing = (Instance) inst.copy();
    withMissing.setDataset(inst.dataset());
    withMissing.setMissing(withMissing.classIndex());
    double predValue = classifier.classifyInstance(withMissing);

    // index
    result.append(Utils.padLeft("" + (instNum + 1), 6));

    if (inst.dataset().classAttribute().isNumeric()) {
        // actual
        if (inst.classIsMissing()) {
            result.append(" " + Utils.padLeft("?", width));
        } else {
            result.append(" " + Utils.doubleToString(inst.classValue(), width, prec));
        }
        // predicted
        if (Instance.isMissingValue(predValue)) {
            result.append(" " + Utils.padLeft("?", width));
        } else {
            result.append(" " + Utils.doubleToString(predValue, width, prec));
        }
        // error
        if (Instance.isMissingValue(predValue) || inst.classIsMissing()) {
            result.append(" " + Utils.padLeft("?", width));
        } else {
            result.append(" " + Utils.doubleToString(predValue - inst.classValue(), width, prec));
        }
    } else {
        // actual
        result.append(" "
                + Utils.padLeft(((int) inst.classValue() + 1) + ":" + inst.toString(inst.classIndex()), width));
        // predicted
        if (Instance.isMissingValue(predValue)) {
            result.append(" " + Utils.padLeft("?", width));
        } else {
            result.append(" " + Utils.padLeft(
                    ((int) predValue + 1) + ":" + inst.dataset().classAttribute().value((int) predValue),
                    width));
        }
        // error?
        if (!Instance.isMissingValue(predValue) && !inst.classIsMissing()
                && ((int) predValue + 1 != (int) inst.classValue() + 1)) {
            result.append(" " + "  +  ");
        } else {
            result.append(" " + "     ");
        }
        // prediction/distribution
        if (printDistribution) {
            if (Instance.isMissingValue(predValue)) {
                result.append(" " + "?");
            } else {
                result.append(" ");
                double[] dist = classifier.distributionForInstance(withMissing);
                for (int n = 0; n < dist.length; n++) {
                    if (n > 0) {
                        result.append(",");
                    }
                    if (n == (int) predValue) {
                        result.append("*");
                    }
                    result.append(Utils.doubleToString(dist[n], prec));
                }
            }
        } else {
            if (Instance.isMissingValue(predValue)) {
                result.append(" " + "?");
            } else {
                result.append(" " + Utils.doubleToString(
                        classifier.distributionForInstance(withMissing)[(int) predValue], prec));
            }
        }
    }

    // attributes
    result.append(" " + attributeValuesString(withMissing, attributesToOutput) + "\n");

    return result.toString();
}

From source file:core.Core.java

public String run() throws Exception {
    ConverterUtils.DataSource source = new ConverterUtils.DataSource("src/files/powerpuffgirls.arff");

    HashMap<String, Classifier> hash = new HashMap<>();

    hash.put("J48", new J48());
    hash.put("NaiveBayes", new NaiveBayes());
    hash.put("IBk=1", new IBk(1));
    hash.put("IBk=3", new IBk(3));
    hash.put("MultilayerPerceptron", new MultilayerPerceptron());

    LibSVM svm = new LibSVM();
    hash.put("LibSVM", svm);
    Instances ins = source.getDataSet();

    ins.setClassIndex(4);/*  w  w  w . j  av  a2  s. co m*/

    StringBuilder sb = new StringBuilder();

    int blossom = 0;
    int bubbles = 0;

    Instance test = null;

    for (Map.Entry<String, Classifier> entry : hash.entrySet()) {
        Classifier c = entry.getValue();
        c.buildClassifier(ins);

        test = new Instance(5);

        float[] array = classifyImage();

        test.setDataset(ins);
        test.setValue(0, array[0]);
        test.setValue(1, array[1]);
        test.setValue(2, array[2]);
        test.setValue(3, array[3]);

        double prob[] = c.distributionForInstance(test);

        sb.append("<em>");
        sb.append(entry.getKey());
        sb.append(":</em>");
        sb.append("<br/>");

        for (int i = 0; i < prob.length; i++) {
            String value = test.classAttribute().value(i);

            if (getRoundedValue(prob[i]) >= CUT_NOTE) {
                if (getClassValue(value))
                    blossom++;
                else
                    bubbles++;
            }

            sb.append(getClassName(value));
            sb.append(": ");
            sb.append("<strong>");
            sb.append(getRoundedValue(prob[i]) < CUT_NOTE ? "Rejeitado!" : getValueFormatted(prob[i]));
            sb.append("</strong>");
            sb.append("&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;");
        }

        sb.append("<br/>");

        System.out.println("blossom: " + blossom);
        System.out.println("bubbles: " + bubbles);
        System.out.println("=================\n");
    }

    sb.append(blossom > bubbles ? "<h3> a Florzinha!</h3>" : "<h3> a Lindinha!</h3>");

    blossom = 0;
    bubbles = 0;

    return sb.toString();
}

From source file:cotraining.copy.Evaluation_D.java

License:Open Source License

/**
 * Evaluates the classifier on a single instance and records the
 * prediction (if the class is nominal).
 *
 * @param classifier machine learning classifier
 * @param instance the test instance to be classified
 * @return the prediction made by the clasifier
 * @throws Exception if model could not be evaluated 
 * successfully or the data contains string attributes
 *//*from   w  w  w .j a  v a 2s.  c o m*/
public double evaluateModelOnceAndRecordPrediction(Classifier classifier, Instance instance) throws Exception {

    Instance classMissing = (Instance) instance.copy();
    double pred = 0;
    classMissing.setDataset(instance.dataset());
    classMissing.setClassMissing();
    if (m_ClassIsNominal) {
        if (m_Predictions == null) {
            m_Predictions = new FastVector();
        }
        double[] dist = classifier.distributionForInstance(classMissing);
        pred = Utils.maxIndex(dist);
        if (dist[(int) pred] <= 0) {
            pred = Instance.missingValue();
        }
        updateStatsForClassifier(dist, instance);
        m_Predictions.addElement(new NominalPrediction(instance.classValue(), dist, instance.weight()));
    } else {
        pred = classifier.classifyInstance(classMissing);
        updateStatsForPredictor(pred, instance);
    }
    return pred;
}

From source file:cotraining.copy.Evaluation_D.java

License:Open Source License

/**
 * store the prediction made by the classifier as a string
 * /*from   w  ww  .jav a  2  s. c o  m*/
 * @param classifier      the classifier to use
 * @param inst      the instance to generate text from
 * @param instNum      the index in the dataset
 * @param attributesToOutput   the indices of the attributes to output
 * @param printDistribution   prints the complete distribution for nominal 
 *             classes, not just the predicted value
 * @return                    the prediction as a String
 * @throws Exception      if something goes wrong
 * @see         #printClassifications(Classifier, Instances, String, int, Range, boolean)
 */
protected static String predictionText(Classifier classifier, Instance inst, int instNum,
        Range attributesToOutput, boolean printDistribution)

        throws Exception {

    StringBuffer result = new StringBuffer();
    int width = 10;
    int prec = 3;

    Instance withMissing = (Instance) inst.copy();
    withMissing.setDataset(inst.dataset());
    withMissing.setMissing(withMissing.classIndex());
    double predValue = classifier.classifyInstance(withMissing);

    // index
    result.append(Utils.padLeft("" + (instNum + 1), 6));

    if (inst.dataset().classAttribute().isNumeric()) {
        // actual
        if (inst.classIsMissing())
            result.append(" " + Utils.padLeft("?", width));
        else
            result.append(" " + Utils.doubleToString(inst.classValue(), width, prec));
        // predicted
        if (Instance.isMissingValue(predValue))
            result.append(" " + Utils.padLeft("?", width));
        else
            result.append(" " + Utils.doubleToString(predValue, width, prec));
        // error
        if (Instance.isMissingValue(predValue) || inst.classIsMissing())
            result.append(" " + Utils.padLeft("?", width));
        else
            result.append(" " + Utils.doubleToString(predValue - inst.classValue(), width, prec));
    } else {
        // actual
        result.append(" "
                + Utils.padLeft(((int) inst.classValue() + 1) + ":" + inst.toString(inst.classIndex()), width));
        // predicted
        if (Instance.isMissingValue(predValue))
            result.append(" " + Utils.padLeft("?", width));
        else
            result.append(" " + Utils.padLeft(
                    ((int) predValue + 1) + ":" + inst.dataset().classAttribute().value((int) predValue),
                    width));
        // error?
        if (!Instance.isMissingValue(predValue) && !inst.classIsMissing()
                && ((int) predValue + 1 != (int) inst.classValue() + 1))
            result.append(" " + "  +  ");
        else
            result.append(" " + "     ");
        // prediction/distribution
        if (printDistribution) {
            if (Instance.isMissingValue(predValue)) {
                result.append(" " + "?");
            } else {
                result.append(" ");
                double[] dist = classifier.distributionForInstance(withMissing);
                for (int n = 0; n < dist.length; n++) {
                    if (n > 0)
                        result.append(",");
                    if (n == (int) predValue)
                        result.append("*");
                    result.append(Utils.doubleToString(dist[n], prec));
                }
            }
        } else {
            if (Instance.isMissingValue(predValue))
                result.append(" " + "?");
            else
                result.append(" " + Utils.doubleToString(
                        classifier.distributionForInstance(withMissing)[(int) predValue], prec));
        }
    }

    // attributes
    result.append(" " + attributeValuesString(withMissing, attributesToOutput) + "\n");

    return result.toString();
}

From source file:csav2.Weka_additive.java

public void classifyTestSet1(String input) throws Exception {
    String ids = "";
    ReaderWriter rw = new ReaderWriter();

    //ATTRIBUTES//from  w ww.  j  a va2 s .  c o  m
    Attribute attr[] = new Attribute[50];

    //numeric
    attr[0] = new Attribute("Autosentiment");

    //class
    FastVector classValue = new FastVector(3);
    classValue.addElement("p");
    classValue.addElement("n");
    classValue.addElement("o");
    attr[1] = new Attribute("answer", classValue);

    FastVector attrs = new FastVector();
    attrs.addElement(attr[0]);
    attrs.addElement(attr[1]);

    // Add Instances
    Instances dataset = new Instances("my_dataset", attrs, 0);

    StringTokenizer tokenizer = new StringTokenizer(input);

    while (tokenizer.hasMoreTokens()) {
        Instance example = new Instance(2);
        for (int j = 0; j < 2; j++) {
            String st = tokenizer.nextToken();
            System.out.println(j + " " + st);
            if (j == 0)
                example.setValue(attr[j], Float.parseFloat(st));
            else if (j == 1)
                example.setValue(attr[j], st);
            else
                example.setValue(attr[j], Integer.parseInt(st));
        }
        ids += tokenizer.nextToken() + "\t";
        dataset.add(example);
    }

    //Save dataset
    String file = "Classifier\\featurefile_additive_test1.arff";
    ArffSaver saver = new ArffSaver();
    saver.setInstances(dataset);
    saver.setFile(new File(file));
    saver.writeBatch();

    //Read dataset
    ArffLoader loader = new ArffLoader();
    loader.setFile(new File(file));
    dataset = loader.getDataSet();

    //Build classifier
    dataset.setClassIndex(1);

    //Read classifier back
    String file1 = "Classifier\\classifier_add_autosentiment.model";
    InputStream is = new FileInputStream(file1);
    Classifier classifier;
    ObjectInputStream objectInputStream = new ObjectInputStream(is);
    classifier = (Classifier) objectInputStream.readObject();

    //Evaluate
    Instances test = new Instances(dataset, 0, dataset.numInstances());
    test.setClassIndex(1);

    //Do eval
    Evaluation eval = new Evaluation(test); //trainset
    eval.evaluateModel(classifier, test); //testset
    System.out.println(eval.toSummaryString());
    System.out.println("WEIGHTED F-MEASURE:" + eval.weightedFMeasure());
    System.out.println("WEIGHTED PRECISION:" + eval.weightedPrecision());
    System.out.println("WEIGHTED RECALL:" + eval.weightedRecall());

    //output predictions
    String optest = "", val = "";
    StringTokenizer op = new StringTokenizer(ids);
    int count = 0;
    while (op.hasMoreTokens()) {
        double[] prediction = classifier.distributionForInstance(test.instance(count));

        count += 1;
        //optest+=op.nextToken()+" "+Double.toString((double) Math.round((prediction[0]) * 1000) / 1000)+"\n";                
        if (prediction[0] > prediction[1]) {
            if (prediction[0] > prediction[2]) {
                val = "p: " + Double.toString((double) Math.round((prediction[0]) * 1000) / 1000);
            } else {
                val = "o: " + Double.toString((double) Math.round((prediction[2]) * 1000) / 1000);
            }
        } else {
            if (prediction[1] > prediction[2]) {
                val = "n: " + Double.toString((double) Math.round((prediction[1]) * 1000) / 1000);
            } else {
                val = "o: " + Double.toString((double) Math.round((prediction[2]) * 1000) / 1000);
            }
        }
        optest += op.nextToken() + "\t" + val + "\n";
    }
    rw.writeToFile(optest, "Answers_additive_Test1", "txt");
}

From source file:csav2.Weka_additive.java

public void classifyTestSet2(String input) throws Exception {
    String ids = "";
    ReaderWriter rw = new ReaderWriter();

    //ATTRIBUTES/*  w ww  .j  a  v a2s  . c  o m*/
    Attribute attr[] = new Attribute[50];

    //numeric
    attr[0] = new Attribute("Autosentiment");
    attr[1] = new Attribute("PostiveMatch");
    attr[2] = new Attribute("NegativeMatch");

    //class
    FastVector classValue = new FastVector(3);
    classValue.addElement("p");
    classValue.addElement("n");
    classValue.addElement("o");
    attr[3] = new Attribute("answer", classValue);

    FastVector attrs = new FastVector();
    attrs.addElement(attr[0]);
    attrs.addElement(attr[1]);
    attrs.addElement(attr[2]);
    attrs.addElement(attr[3]);

    // Add Instances
    Instances dataset = new Instances("my_dataset", attrs, 0);

    StringTokenizer tokenizer = new StringTokenizer(input);

    while (tokenizer.hasMoreTokens()) {
        Instance example = new Instance(4);
        for (int j = 0; j < 4; j++) {
            String st = tokenizer.nextToken();
            System.out.println(j + " " + st);
            if (j == 0)
                example.setValue(attr[j], Float.parseFloat(st));
            else if (j == 3)
                example.setValue(attr[j], st);
            else
                example.setValue(attr[j], Integer.parseInt(st));
        }
        ids += tokenizer.nextToken() + "\t";
        dataset.add(example);
    }

    //Save dataset
    String file = "Classifier\\featurefile_additive_test2.arff";
    ArffSaver saver = new ArffSaver();
    saver.setInstances(dataset);
    saver.setFile(new File(file));
    saver.writeBatch();

    //Read dataset
    ArffLoader loader = new ArffLoader();
    loader.setFile(new File(file));
    dataset = loader.getDataSet();

    //Build classifier
    dataset.setClassIndex(3);

    //Read classifier back
    String file1 = "Classifier\\classifier_add_asAndpolarwords.model";
    InputStream is = new FileInputStream(file1);
    Classifier classifier;
    ObjectInputStream objectInputStream = new ObjectInputStream(is);
    classifier = (Classifier) objectInputStream.readObject();

    //Evaluate
    Instances test = new Instances(dataset, 0, dataset.numInstances());
    test.setClassIndex(3);

    //Do eval
    Evaluation eval = new Evaluation(test); //trainset
    eval.evaluateModel(classifier, test); //testset
    System.out.println(eval.toSummaryString());
    System.out.println("WEIGHTED F-MEASURE:" + eval.weightedFMeasure());
    System.out.println("WEIGHTED PRECISION:" + eval.weightedPrecision());
    System.out.println("WEIGHTED RECALL:" + eval.weightedRecall());

    //output predictions
    String optest = "", val = "";
    StringTokenizer op = new StringTokenizer(ids);
    int count = 0;
    while (op.hasMoreTokens()) {
        double[] prediction = classifier.distributionForInstance(test.instance(count));
        count += 1;
        if (prediction[0] > prediction[1]) {
            if (prediction[0] > prediction[2]) {
                val = "p: " + Double.toString((double) Math.round((prediction[0]) * 1000) / 1000);
            } else {
                val = "o: " + Double.toString((double) Math.round((prediction[2]) * 1000) / 1000);
            }
        } else {
            if (prediction[1] > prediction[2]) {
                val = "n: " + Double.toString((double) Math.round((prediction[1]) * 1000) / 1000);
            } else {
                val = "o: " + Double.toString((double) Math.round((prediction[2]) * 1000) / 1000);
            }
        }
        optest += op.nextToken() + "\t" + val + "\n";
    }
    rw.writeToFile(optest, "Answers_additive_Test2", "txt");
}

From source file:csav2.Weka_additive.java

public void classifyTestSet3(String input) throws Exception {
    String ids = "";
    ReaderWriter rw = new ReaderWriter();

    //ATTRIBUTES// w  w  w  .  ja  v  a  2 s.com
    Attribute attr[] = new Attribute[50];

    //numeric
    attr[0] = new Attribute("Autosentiment");
    attr[1] = new Attribute("PositiveMatch");
    attr[2] = new Attribute("NegativeMatch");
    attr[3] = new Attribute("FW");
    attr[4] = new Attribute("JJ");
    attr[5] = new Attribute("RB");
    attr[6] = new Attribute("RB_JJ");

    //class
    FastVector classValue = new FastVector(3);
    classValue.addElement("p");
    classValue.addElement("n");
    classValue.addElement("o");
    attr[7] = new Attribute("answer", classValue);

    FastVector attrs = new FastVector();
    attrs.addElement(attr[0]);
    attrs.addElement(attr[1]);
    attrs.addElement(attr[2]);
    attrs.addElement(attr[3]);
    attrs.addElement(attr[4]);
    attrs.addElement(attr[5]);
    attrs.addElement(attr[6]);
    attrs.addElement(attr[7]);

    // Add Instances
    Instances dataset = new Instances("my_dataset", attrs, 0);

    StringTokenizer tokenizer = new StringTokenizer(input);

    while (tokenizer.hasMoreTokens()) {
        Instance example = new Instance(8);
        for (int j = 0; j < 8; j++) {
            String st = tokenizer.nextToken();
            System.out.println(j + " " + st);
            if (j == 0)
                example.setValue(attr[j], Float.parseFloat(st));
            else if (j == 7)
                example.setValue(attr[j], st);
            else
                example.setValue(attr[j], Integer.parseInt(st));
        }
        ids += tokenizer.nextToken() + "\t";
        dataset.add(example);
    }

    //Save dataset
    String file = "Classifier\\featurefile_additive_test3.arff";
    ArffSaver saver = new ArffSaver();
    saver.setInstances(dataset);
    saver.setFile(new File(file));
    saver.writeBatch();

    //Read dataset
    ArffLoader loader = new ArffLoader();
    loader.setFile(new File(file));
    dataset = loader.getDataSet();

    //Build classifier
    dataset.setClassIndex(7);

    //Read classifier back
    String file1 = "Classifier\\classifier_add_asAndpolarwordsAndpos.model";
    InputStream is = new FileInputStream(file1);
    Classifier classifier;
    ObjectInputStream objectInputStream = new ObjectInputStream(is);
    classifier = (Classifier) objectInputStream.readObject();

    //Evaluate
    Instances test = new Instances(dataset, 0, dataset.numInstances());
    test.setClassIndex(7);

    //Do eval
    Evaluation eval = new Evaluation(test); //trainset
    eval.evaluateModel(classifier, test); //testset
    System.out.println(eval.toSummaryString());
    System.out.println("WEIGHTED F-MEASURE:" + eval.weightedFMeasure());
    System.out.println("WEIGHTED PRECISION:" + eval.weightedPrecision());
    System.out.println("WEIGHTED RECALL:" + eval.weightedRecall());

    //output predictions
    String optest = "", val = "";
    StringTokenizer op = new StringTokenizer(ids);
    int count = 0;
    while (op.hasMoreTokens()) {
        double[] prediction = classifier.distributionForInstance(test.instance(count));
        count += 1;

        if (prediction[0] > prediction[1]) {
            if (prediction[0] > prediction[2]) {
                val = "p: " + Double.toString((double) Math.round((prediction[0]) * 1000) / 1000);
            } else {
                val = "o: " + Double.toString((double) Math.round((prediction[2]) * 1000) / 1000);
            }
        } else {
            if (prediction[1] > prediction[2]) {
                val = "n: " + Double.toString((double) Math.round((prediction[1]) * 1000) / 1000);
            } else {
                val = "o: " + Double.toString((double) Math.round((prediction[2]) * 1000) / 1000);
            }
        }
        optest += op.nextToken() + "\t" + val + "\n";
    }
    rw.writeToFile(optest, "Answers_additive_Test3", "txt");
}

From source file:csav2.Weka_additive.java

public void classifyTestSet4(String input) throws Exception {
    String ids = "";
    ReaderWriter rw = new ReaderWriter();

    //ATTRIBUTES/*from w  w  w . j av a  2 s .  c  o  m*/
    Attribute attr[] = new Attribute[50];

    //numeric
    attr[0] = new Attribute("Autosentiment");
    attr[1] = new Attribute("PositiveMatch");
    attr[2] = new Attribute("NegativeMatch");
    attr[3] = new Attribute("FW");
    attr[4] = new Attribute("JJ");
    attr[5] = new Attribute("RB");
    attr[6] = new Attribute("RB_JJ");
    attr[7] = new Attribute("amod");
    attr[8] = new Attribute("acomp");
    attr[9] = new Attribute("advmod");

    //class
    FastVector classValue = new FastVector(3);
    classValue.addElement("p");
    classValue.addElement("n");
    classValue.addElement("o");
    attr[10] = new Attribute("answer", classValue);

    FastVector attrs = new FastVector();
    attrs.addElement(attr[0]);
    attrs.addElement(attr[1]);
    attrs.addElement(attr[2]);
    attrs.addElement(attr[3]);
    attrs.addElement(attr[4]);
    attrs.addElement(attr[5]);
    attrs.addElement(attr[6]);
    attrs.addElement(attr[7]);
    attrs.addElement(attr[8]);
    attrs.addElement(attr[9]);
    attrs.addElement(attr[10]);

    // Add Instances
    Instances dataset = new Instances("my_dataset", attrs, 0);

    StringTokenizer tokenizer = new StringTokenizer(input);

    while (tokenizer.hasMoreTokens()) {
        Instance example = new Instance(11);
        for (int j = 0; j < 11; j++) {
            String st = tokenizer.nextToken();
            System.out.println(j + " " + st);
            if (j == 0)
                example.setValue(attr[j], Float.parseFloat(st));
            else if (j == 10)
                example.setValue(attr[j], st);
            else
                example.setValue(attr[j], Integer.parseInt(st));
        }
        ids += tokenizer.nextToken() + "\t";
        dataset.add(example);
    }

    //Save dataset
    String file = "Classifier\\featurefile_additive_test4.arff";
    ArffSaver saver = new ArffSaver();
    saver.setInstances(dataset);
    saver.setFile(new File(file));
    saver.writeBatch();

    //Read dataset
    ArffLoader loader = new ArffLoader();
    loader.setFile(new File(file));
    dataset = loader.getDataSet();

    //Build classifier
    dataset.setClassIndex(10);

    //Read classifier back
    String file1 = "Classifier\\classifier_add_asAndpolarwordsAndposAnddep.model";
    InputStream is = new FileInputStream(file1);
    Classifier classifier;
    ObjectInputStream objectInputStream = new ObjectInputStream(is);
    classifier = (Classifier) objectInputStream.readObject();

    //Evaluate
    Instances test = new Instances(dataset, 0, dataset.numInstances());
    test.setClassIndex(10);

    //Do eval
    Evaluation eval = new Evaluation(test); //trainset
    eval.evaluateModel(classifier, test); //testset
    System.out.println(eval.toSummaryString());
    System.out.println("WEIGHTED F-MEASURE:" + eval.weightedFMeasure());
    System.out.println("WEIGHTED PRECISION:" + eval.weightedPrecision());
    System.out.println("WEIGHTED RECALL:" + eval.weightedRecall());

    //output predictions
    String optest = "", val = "";
    StringTokenizer op = new StringTokenizer(ids);
    int count = 0;
    while (op.hasMoreTokens()) {
        double[] prediction = classifier.distributionForInstance(test.instance(count));
        count += 1;
        if (prediction[0] > prediction[1]) {
            if (prediction[0] > prediction[2]) {
                val = "p: " + Double.toString((double) Math.round((prediction[0]) * 1000) / 1000);
            } else {
                val = "o: " + Double.toString((double) Math.round((prediction[2]) * 1000) / 1000);
            }
        } else {
            if (prediction[1] > prediction[2]) {
                val = "n: " + Double.toString((double) Math.round((prediction[1]) * 1000) / 1000);
            } else {
                val = "o: " + Double.toString((double) Math.round((prediction[2]) * 1000) / 1000);
            }
        }
        optest += op.nextToken() + "\t" + val + "\n";
    }
    rw.writeToFile(optest, "Answers_additive_Test4", "txt");
}

From source file:csav2.Weka_additive.java

public void classifyTestSet5(String input) throws Exception {
    String ids = "";
    ReaderWriter rw = new ReaderWriter();

    //ATTRIBUTES//ww  w. ja  v  a2 s.  c  om
    Attribute attr[] = new Attribute[50];

    //numeric
    attr[0] = new Attribute("Autosentiment");
    attr[1] = new Attribute("PositiveMatch");
    attr[2] = new Attribute("NegativeMatch");
    attr[3] = new Attribute("FW");
    attr[4] = new Attribute("JJ");
    attr[5] = new Attribute("RB");
    attr[6] = new Attribute("RB_JJ");
    attr[7] = new Attribute("amod");
    attr[8] = new Attribute("acomp");
    attr[9] = new Attribute("advmod");
    attr[10] = new Attribute("BLPos");
    attr[11] = new Attribute("BLNeg");

    //class
    FastVector classValue = new FastVector(3);
    classValue.addElement("p");
    classValue.addElement("n");
    classValue.addElement("o");
    attr[12] = new Attribute("answer", classValue);

    FastVector attrs = new FastVector();
    attrs.addElement(attr[0]);
    attrs.addElement(attr[1]);
    attrs.addElement(attr[2]);
    attrs.addElement(attr[3]);
    attrs.addElement(attr[4]);
    attrs.addElement(attr[5]);
    attrs.addElement(attr[6]);
    attrs.addElement(attr[7]);
    attrs.addElement(attr[8]);
    attrs.addElement(attr[9]);
    attrs.addElement(attr[10]);
    attrs.addElement(attr[11]);
    attrs.addElement(attr[12]);

    // Add Instances
    Instances dataset = new Instances("my_dataset", attrs, 0);

    StringTokenizer tokenizer = new StringTokenizer(input);

    while (tokenizer.hasMoreTokens()) {
        Instance example = new Instance(13);
        for (int j = 0; j < 13; j++) {
            String st = tokenizer.nextToken();
            System.out.println(j + " " + st);
            if (j == 0)
                example.setValue(attr[j], Float.parseFloat(st));
            else if (j == 12)
                example.setValue(attr[j], st);
            else
                example.setValue(attr[j], Integer.parseInt(st));
        }
        ids += tokenizer.nextToken() + "\t";
        dataset.add(example);
    }

    //Save dataset
    String file = "Classifier\\featurefile_additive_test5.arff";
    ArffSaver saver = new ArffSaver();
    saver.setInstances(dataset);
    saver.setFile(new File(file));
    saver.writeBatch();

    //Read dataset
    ArffLoader loader = new ArffLoader();
    loader.setFile(new File(file));
    dataset = loader.getDataSet();

    //Build classifier
    dataset.setClassIndex(12);

    //Read classifier back
    String file1 = "Classifier\\classifier_add_asAndpolarwordsAndposAnddepAndbl.model";
    InputStream is = new FileInputStream(file1);
    Classifier classifier;
    ObjectInputStream objectInputStream = new ObjectInputStream(is);
    classifier = (Classifier) objectInputStream.readObject();

    //Evaluate
    Instances test = new Instances(dataset, 0, dataset.numInstances());
    test.setClassIndex(12);

    //Do eval
    Evaluation eval = new Evaluation(test); //trainset
    eval.evaluateModel(classifier, test); //testset
    System.out.println(eval.toSummaryString());
    System.out.println("WEIGHTED F-MEASURE:" + eval.weightedFMeasure());
    System.out.println("WEIGHTED PRECISION:" + eval.weightedPrecision());
    System.out.println("WEIGHTED RECALL:" + eval.weightedRecall());

    //output predictions
    String optest = "", val = "";
    StringTokenizer op = new StringTokenizer(ids);
    int count = 0;
    while (op.hasMoreTokens()) {
        double[] prediction = classifier.distributionForInstance(test.instance(count));
        count += 1;
        if (prediction[0] > prediction[1]) {
            if (prediction[0] > prediction[2]) {
                val = "p: " + Double.toString((double) Math.round((prediction[0]) * 1000) / 1000);
            } else {
                val = "o: " + Double.toString((double) Math.round((prediction[2]) * 1000) / 1000);
            }
        } else {
            if (prediction[1] > prediction[2]) {
                val = "n: " + Double.toString((double) Math.round((prediction[1]) * 1000) / 1000);
            } else {
                val = "o: " + Double.toString((double) Math.round((prediction[2]) * 1000) / 1000);
            }
        }
        optest += op.nextToken() + "\t" + val + "\n";
    }
    rw.writeToFile(optest, "Answers_additive_Test5", "txt");
}