Example usage for weka.core Instances add

List of usage examples for weka.core Instances add

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

Introduction

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

Prototype

@Override
public boolean add(Instance instance)

Source Link

Document

Adds one instance to the end of the set.

Usage

From source file:couchdb.PrepareData.java

/**
 * Metoda do zmiany danych przechowywanych w dokumentach JSON na dane
 * przechowywane w obiekcie typu Instances.
 *
 * @return Zbir danych typu Instances.//from   w  w w. j a v a 2  s. co m
 */
public Instances getDataForWeka() {
    CouchDBService cdbs = new CouchDBService();
    ArrayList<String> listOfValues = cdbs.getValues(simpleDocumentList);
    ParseJSON p = new ParseJSON();
    ArrayList<String> listOfSimpleAttributes = p.getAttributes(simpleDocumentList.get(0));
    ArrayList<String> listOfComplexAttributes = new ArrayList<>();

    FastVector listOfAttributes = getAtributes(simpleDocumentList, listOfValues);
    Instances instances = new Instances(nameData, listOfAttributes, 0);

    for (int j = 0; j < simpleDocumentList.size(); j++) {
        Instance instance = new Instance(listOfAttributes.size());
        instances.add(instance);
    }

    int k = 0;
    for (int i = 0; i < instances.numInstances(); i++) {
        Instance ins = instances.instance(i);
        for (int j = 0; j < ins.numAttributes(); j++) {
            String s = listOfValues.get(k);
            if (s.equals("nn")) {
                return null;
            }
            if (s.equals("")) {
                k++;
                j--;
                continue;
            }
            if (ins.attribute(j).type() == 0) {
                double d = 0;
                try {
                    d = Double.parseDouble(s);
                } catch (NumberFormatException ex) {
                    d = 0;
                }
                ins.setValue(j, d);
            } else {

                ins.setValue(j, s);
            }
            k++;
        }
    }

    return instances;
}

From source file:csav2.Weka_additive.java

public void createTrainingFeatureFile1(String input) throws Exception {
    String file = "Classifier\\featurefile_additive_trial1.arff";
    ArffLoader loader = new ArffLoader();

    //ATTRIBUTES/*from w w w. j a v a 2  s . co  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);

    if (new File(file).isFile()) {
        loader.setFile(new File(file));
        dataset = loader.getDataSet();
    }

    System.out.println("-----------------------------------------");
    System.out.println(input);
    System.out.println("-----------------------------------------");

    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));
        }
        dataset.add(example);
    }

    //Save dataset
    ArffSaver saver = new ArffSaver();
    saver.setInstances(dataset);
    saver.setFile(new File(file));
    saver.writeBatch();

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

    //Build classifier
    dataset.setClassIndex(1);
    Classifier classifier = new J48();
    classifier.buildClassifier(dataset);

    //Save classifier
    String file1 = "Classifier\\classifier_add_autosentiment.model";
    OutputStream os = new FileOutputStream(file1);
    ObjectOutputStream objectOutputStream = new ObjectOutputStream(os);
    objectOutputStream.writeObject(classifier);

    // Comment out if not needed
    //Read classifier back
    InputStream is = new FileInputStream(file1);
    ObjectInputStream objectInputStream = new ObjectInputStream(is);
    classifier = (Classifier) objectInputStream.readObject();
    objectInputStream.close();

    //Evaluate resample if needed
    //dataset = dataset.resample(new Random(42));
    //split to 70:30 learn and test set
    double percent = 70.0;
    int trainSize = (int) Math.round(dataset.numInstances() * percent / 100);
    int testSize = dataset.numInstances() - trainSize;
    Instances train = new Instances(dataset, 0, trainSize);
    Instances test = new Instances(dataset, trainSize, testSize);
    train.setClassIndex(1);
    test.setClassIndex(1);

    //Evaluate
    Evaluation eval = new Evaluation(dataset); //trainset
    eval.crossValidateModel(classifier, dataset, 10, new Random(1));
    System.out.println("EVALUATION:\n" + eval.toSummaryString());
    System.out.println("WEIGHTED MEASURE:\n" + eval.weightedFMeasure());
    System.out.println("WEIGHTED PRECISION:\n" + eval.weightedPrecision());
    System.out.println("WEIGHTED RECALL:\n" + eval.weightedRecall());
}

From source file:csav2.Weka_additive.java

public void createTrainingFeatureFile2(String input) throws Exception {
    String file = "Classifier\\featurefile_additive_trial2.arff";
    ArffLoader loader = new ArffLoader();

    //ATTRIBUTES/*from  w w w .  java2 s . c  om*/
    Attribute attr[] = new Attribute[50];

    //numeric
    attr[0] = new Attribute("Autosentiment");
    attr[1] = new Attribute("PositiveMatch");
    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);

    if (new File(file).isFile()) {
        loader.setFile(new File(file));
        dataset = loader.getDataSet();
    }

    System.out.println("-----------------------------------------");
    System.out.println(input);
    System.out.println("-----------------------------------------");

    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));
        }
        dataset.add(example);
    }

    //Save dataset
    ArffSaver saver = new ArffSaver();
    saver.setInstances(dataset);
    saver.setFile(new File(file));
    saver.writeBatch();

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

    //Build classifier
    dataset.setClassIndex(3);
    Classifier classifier = new J48();
    classifier.buildClassifier(dataset);

    //Save classifier
    String file1 = "Classifier\\classifier_add_asAndpolarwords.model";
    OutputStream os = new FileOutputStream(file1);
    ObjectOutputStream objectOutputStream = new ObjectOutputStream(os);
    objectOutputStream.writeObject(classifier);

    // Comment out if not needed
    //Read classifier back
    InputStream is = new FileInputStream(file1);
    ObjectInputStream objectInputStream = new ObjectInputStream(is);
    classifier = (Classifier) objectInputStream.readObject();
    objectInputStream.close();

    //Evaluate resample if needed
    //dataset = dataset.resample(new Random(42));
    //split to 70:30 learn and test set
    double percent = 70.0;
    int trainSize = (int) Math.round(dataset.numInstances() * percent / 100);
    int testSize = dataset.numInstances() - trainSize;
    Instances train = new Instances(dataset, 0, trainSize);
    Instances test = new Instances(dataset, trainSize, testSize);
    train.setClassIndex(3);
    test.setClassIndex(3);

    //Evaluate
    Evaluation eval = new Evaluation(dataset); //trainset
    eval.crossValidateModel(classifier, dataset, 10, new Random(1));
    System.out.println("EVALUATION:\n" + eval.toSummaryString());
    System.out.println("WEIGHTED MEASURE:\n" + eval.weightedFMeasure());
    System.out.println("WEIGHTED PRECISION:\n" + eval.weightedPrecision());
    System.out.println("WEIGHTED RECALL:\n" + eval.weightedRecall());
}

From source file:csav2.Weka_additive.java

public void createTrainingFeatureFile3(String input) throws Exception {
    String file = "Classifier\\featurefile_additive_trial3.arff";
    ArffLoader loader = new ArffLoader();

    //ATTRIBUTES/*from  w ww  .ja  v  a 2s.  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);

    if (new File(file).isFile()) {
        loader.setFile(new File(file));
        dataset = loader.getDataSet();
    }

    System.out.println("-----------------------------------------");
    System.out.println(input);
    System.out.println("-----------------------------------------");

    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));
        }
        dataset.add(example);
    }

    //Save dataset
    ArffSaver saver = new ArffSaver();
    saver.setInstances(dataset);
    saver.setFile(new File(file));
    saver.writeBatch();

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

    //Build classifier
    dataset.setClassIndex(7);
    Classifier classifier = new J48();
    classifier.buildClassifier(dataset);

    //Save classifier
    String file1 = "Classifier\\classifier_add_asAndpolarwordsAndpos.model";
    OutputStream os = new FileOutputStream(file1);
    ObjectOutputStream objectOutputStream = new ObjectOutputStream(os);
    objectOutputStream.writeObject(classifier);

    // Comment out if not needed
    //Read classifier back
    InputStream is = new FileInputStream(file1);
    ObjectInputStream objectInputStream = new ObjectInputStream(is);
    classifier = (Classifier) objectInputStream.readObject();
    objectInputStream.close();

    //Evaluate resample if needed
    //dataset = dataset.resample(new Random(42));
    //split to 70:30 learn and test set
    double percent = 70.0;
    int trainSize = (int) Math.round(dataset.numInstances() * percent / 100);
    int testSize = dataset.numInstances() - trainSize;
    Instances train = new Instances(dataset, 0, trainSize);
    Instances test = new Instances(dataset, trainSize, testSize);
    train.setClassIndex(7);
    test.setClassIndex(7);

    //Evaluate
    Evaluation eval = new Evaluation(dataset); //trainset
    eval.crossValidateModel(classifier, dataset, 10, new Random(1));
    System.out.println("EVALUATION:\n" + eval.toSummaryString());
    System.out.println("WEIGHTED MEASURE:\n" + eval.weightedFMeasure());
    System.out.println("WEIGHTED PRECISION:\n" + eval.weightedPrecision());
    System.out.println("WEIGHTED RECALL:\n" + eval.weightedRecall());
}

From source file:csav2.Weka_additive.java

public void createTrainingFeatureFile4(String input) throws Exception {
    String file = "Classifier\\featurefile_additive_trial4.arff";
    ArffLoader loader = new ArffLoader();

    //ATTRIBUTES/*from  w w  w  .  j  av a  2  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");

    //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);

    if (new File(file).isFile()) {
        loader.setFile(new File(file));
        dataset = loader.getDataSet();
    }

    System.out.println("-----------------------------------------");
    System.out.println(input);
    System.out.println("-----------------------------------------");

    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));
        }
        dataset.add(example);
    }

    //Save dataset
    ArffSaver saver = new ArffSaver();
    saver.setInstances(dataset);
    saver.setFile(new File(file));
    saver.writeBatch();

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

    //Build classifier
    dataset.setClassIndex(10);
    Classifier classifier = new J48();
    classifier.buildClassifier(dataset);

    //Save classifier
    String file1 = "Classifier\\classifier_asAndpolarwordsAndposAnddep.model";
    OutputStream os = new FileOutputStream(file1);
    ObjectOutputStream objectOutputStream = new ObjectOutputStream(os);
    objectOutputStream.writeObject(classifier);

    // Comment out if not needed
    //Read classifier back
    InputStream is = new FileInputStream(file1);
    ObjectInputStream objectInputStream = new ObjectInputStream(is);
    classifier = (Classifier) objectInputStream.readObject();
    objectInputStream.close();

    //Evaluate resample if needed
    //dataset = dataset.resample(new Random(42));
    //split to 70:30 learn and test set
    double percent = 70.0;
    int trainSize = (int) Math.round(dataset.numInstances() * percent / 100);
    int testSize = dataset.numInstances() - trainSize;
    Instances train = new Instances(dataset, 0, trainSize);
    Instances test = new Instances(dataset, trainSize, testSize);
    train.setClassIndex(10);
    test.setClassIndex(10);

    //Evaluate
    Evaluation eval = new Evaluation(dataset); //trainset
    eval.crossValidateModel(classifier, dataset, 10, new Random(1));
    System.out.println("EVALUATION:\n" + eval.toSummaryString());
    System.out.println("WEIGHTED MEASURE:\n" + eval.weightedFMeasure());
    System.out.println("WEIGHTED PRECISION:\n" + eval.weightedPrecision());
    System.out.println("WEIGHTED RECALL:\n" + eval.weightedRecall());
}

From source file:csav2.Weka_additive.java

public void createTrainingFeatureFile5(String input) throws Exception {
    String file = "Classifier\\featurefile_additive_trial5.arff";
    ArffLoader loader = new ArffLoader();

    //ATTRIBUTES//from  w  ww.j ava2 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");
    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);

    if (new File(file).isFile()) {
        loader.setFile(new File(file));
        dataset = loader.getDataSet();
    }

    System.out.println("-----------------------------------------");
    System.out.println(input);
    System.out.println("-----------------------------------------");

    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));
        }
        dataset.add(example);
    }

    //Save dataset
    ArffSaver saver = new ArffSaver();
    saver.setInstances(dataset);
    saver.setFile(new File(file));
    saver.writeBatch();

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

    //Build classifier
    dataset.setClassIndex(12);
    Classifier classifier = new J48();
    classifier.buildClassifier(dataset);

    //Save classifier
    String file1 = "Classifier\\classifier_add_asAndpolarwordsAndposAnddepAndbl.model";
    OutputStream os = new FileOutputStream(file1);
    ObjectOutputStream objectOutputStream = new ObjectOutputStream(os);
    objectOutputStream.writeObject(classifier);

    // Comment out if not needed
    //Read classifier back
    InputStream is = new FileInputStream(file1);
    ObjectInputStream objectInputStream = new ObjectInputStream(is);
    classifier = (Classifier) objectInputStream.readObject();
    objectInputStream.close();

    //Evaluate resample if needed
    //dataset = dataset.resample(new Random(42));
    //split to 70:30 learn and test set
    double percent = 70.0;
    int trainSize = (int) Math.round(dataset.numInstances() * percent / 100);
    int testSize = dataset.numInstances() - trainSize;
    Instances train = new Instances(dataset, 0, trainSize);
    Instances test = new Instances(dataset, trainSize, testSize);
    train.setClassIndex(12);
    test.setClassIndex(12);

    //Evaluate
    Evaluation eval = new Evaluation(dataset); //trainset
    eval.crossValidateModel(classifier, dataset, 10, new Random(1));
    System.out.println("EVALUATION:\n" + eval.toSummaryString());
    System.out.println("WEIGHTED MEASURE:\n" + eval.weightedFMeasure());
    System.out.println("WEIGHTED PRECISION:\n" + eval.weightedPrecision());
    System.out.println("WEIGHTED RECALL:\n" + eval.weightedRecall());
}

From source file:csav2.Weka_additive.java

public void createTrainingFeatureFile6(String input) throws Exception {
    String file = "Classifier\\featurefile_additive_trial6.arff";
    ArffLoader loader = new ArffLoader();

    //ATTRIBUTES//from  w  w  w  . j  a  v  a  2s . c  om
    Attribute attr[] = new Attribute[50];

    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");
    attr[12] = new Attribute("VSPositive");
    attr[13] = new Attribute("VSNegative");

    //class
    FastVector classValue = new FastVector(3);
    classValue.addElement("p");
    classValue.addElement("n");
    classValue.addElement("o");
    attr[14] = 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]);
    attrs.addElement(attr[13]);
    attrs.addElement(attr[14]);

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

    if (new File(file).isFile()) {
        loader.setFile(new File(file));
        dataset = loader.getDataSet();
    }

    System.out.println("-----------------------------------------");
    System.out.println(input);
    System.out.println("-----------------------------------------");

    StringTokenizer tokenizer = new StringTokenizer(input);

    while (tokenizer.hasMoreTokens()) {
        Instance example = new Instance(15);
        for (int j = 0; j < 15; j++) {
            String st = tokenizer.nextToken();
            System.out.println(j + " " + st);
            if (j == 0)
                example.setValue(attr[j], Float.parseFloat(st));
            else if (j == 14)
                example.setValue(attr[j], st);
            else
                example.setValue(attr[j], Integer.parseInt(st));
        }
        dataset.add(example);
    }

    //Save dataset
    ArffSaver saver = new ArffSaver();
    saver.setInstances(dataset);
    saver.setFile(new File(file));
    saver.writeBatch();

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

    //Build classifier
    dataset.setClassIndex(14);
    Classifier classifier = new J48();
    classifier.buildClassifier(dataset);

    //Save classifier
    String file1 = "Classifier\\classifier_add_asAndpolarwordsAndposAnddepAndblAndvs.model";
    OutputStream os = new FileOutputStream(file1);
    ObjectOutputStream objectOutputStream = new ObjectOutputStream(os);
    objectOutputStream.writeObject(classifier);

    // Comment out if not needed
    //Read classifier back
    InputStream is = new FileInputStream(file1);
    ObjectInputStream objectInputStream = new ObjectInputStream(is);
    classifier = (Classifier) objectInputStream.readObject();
    objectInputStream.close();

    //Evaluate resample if needed
    //dataset = dataset.resample(new Random(42));
    //split to 70:30 learn and test set
    double percent = 70.0;
    int trainSize = (int) Math.round(dataset.numInstances() * percent / 100);
    int testSize = dataset.numInstances() - trainSize;
    Instances train = new Instances(dataset, 0, trainSize);
    Instances test = new Instances(dataset, trainSize, testSize);
    train.setClassIndex(14);
    test.setClassIndex(14);

    //Evaluate
    Evaluation eval = new Evaluation(dataset); //trainset
    eval.crossValidateModel(classifier, dataset, 10, new Random(1));
    System.out.println("EVALUATION:\n" + eval.toSummaryString());
    System.out.println("WEIGHTED MEASURE:\n" + eval.weightedFMeasure());
    System.out.println("WEIGHTED PRECISION:\n" + eval.weightedPrecision());
    System.out.println("WEIGHTED RECALL:\n" + eval.weightedRecall());
}

From source file:csav2.Weka_additive.java

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

    //ATTRIBUTES//from  ww  w. ja  va 2 s .c om
    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//from  w ww. ja v  a2  s.  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 .j a v  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");

    //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");
}