Example usage for weka.core Instances Instances

Introduction

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

Prototype

public Instances(Instances dataset)

Source Link

Document

Constructor copying all instances and references to the header information from the given set of instances.

Usage

From source file:data.generation.target.utils.PrincipalComponents.java

License:Open Source License

/**
 * Gets the transformed training data.// ww w .j a  v a  2  s  .  c o  m
 * @return the transformed training data
 * @throws Exception if transformed data can't be returned
 */
public Instances transformedData(Instances data) throws Exception {
    if (m_eigenvalues == null) {
        throw new Exception("Principal components hasn't been built yet");
    }

    Instances output = null;

    if (m_transBackToOriginal) {
        output = new Instances(m_originalSpaceFormat);
    } else {
        output = new Instances(m_transformedFormat);
    }
    for (int i = 0; i < data.numInstances(); i++) {
        Instance converted = convertInstance(data.instance(i));
        output.add(converted);
    }

    return output;
}

From source file:data.Regression.java

public int regression(String fileName) {

    String arffName = FileTransfer.transfer(fileName);

    try {//  w  ww  . jav a  2  s .c  o m
        //load data
        Instances data = new Instances(new BufferedReader(new FileReader(arffName)));
        data.setClassIndex(data.numAttributes() - 1);
        //build model
        LinearRegression model = new LinearRegression();
        model.buildClassifier(data);
        //the last instance with missing class is not used
        System.out.println(model);
        //classify the last instance
        Instance num = data.lastInstance();
        int people = (int) model.classifyInstance(num);
        System.out.println("NumOfEnrolled (" + num + "): " + people);
        return people;
    } catch (Exception e) {
        e.printStackTrace();
        System.out.println("Regression fail");
    }
    return 0;
}

From source file:data.RegressionDrop.java

public void regression() throws Exception {

    //public static void main(String[] args) throws Exception{

    //load data//from  ww w .j  a v  a2  s  . c  om
    Instances data = new Instances(new BufferedReader(new FileReader("NumOfDroppedByYear.arff")));
    data.setClassIndex(data.numAttributes() - 1);
    //build model
    LinearRegression model = new LinearRegression();
    model.buildClassifier(data);
    //the last instance with missing class is not used
    System.out.println(model);
    //classify the last instance
    Instance num = data.lastInstance();
    int people = (int) model.classifyInstance(num);
    System.out.println("NumOfDropped (" + num + "): " + people);
}

From source file:dataHandlers.DataClusterHandler.java

public void buildGraph(String filePath) {

    LOGGER.log(Level.WARNING, "May throw exception for poorly formated data files");
    try {//from   ww w. j  a v a2s.  c o  m
        userPoints = new Instances(getDataFile(filePath));
        int numberOfClusters = clusterCount(userPoints);
        int maxSeedAmount = seedAmount(userPoints);
        initiateClusters(maxSeedAmount, numberOfClusters);
        if (clusterInitiated) {
            LOGGER.log(Level.WARNING, "May throw exeption for instances type");
            try {
                dataGraph.buildClusterer(userPoints);
                saveClusterInforamtion();
                LOGGER.log(Level.INFO, "Clustering was completed");
            } catch (Exception e) {
                LOGGER.log(Level.SEVERE, "Error@ClusterProcess_initiateCluster", e);
            }
        }

    } catch (IOException e) {
        LOGGER.log(Level.SEVERE, "Error@ClusterProcess_initiateCluster", e);
    }

}

From source file:DataMiningLogHistoriKIRI.ArffIO.java

public Instances readArff(String name) throws IOException {
    Instances data;/*from w ww .  ja  v a  2 s  .c o m*/
    data = new Instances(new BufferedReader(new FileReader("temp.arff")));
    data.setClassIndex(data.numAttributes() - 1);
    return data;
}

From source file:DataMining_FP.interfaz.java

public static void inicializando_weka() {
    //Inicializando los objetos de weka
    try {//w ww  . j ava2  s. com
        reader = new BufferedReader(new FileReader("WISDM_ar_v1.1_transformed.arff"));
        data = new Instances(reader);
        reader.close();

        // especificando el atributo de clase
        data.setClassIndex(data.numAttributes() - 1);

        String[] options = new String[1];
        options[0] = "-U"; // unpruned tree
        tree = new J48(); // new instance of tree
        tree.setOptions(options); // set the options
        tree.buildClassifier(data); // build classifier
    } catch (Exception e) {
        System.out.println("Error inicializando los objetos de weka");
    }
    System.out.println("Weka inicio bien");
}

From source file:de.citec.sc.matoll.classifiers.WEKAclassifier.java

public void train(List<Provenance> provenances, Set<String> pattern_lookup, Set<String> pos_lookup)
        throws IOException {
    String path = "matoll" + Language.toString() + ".arff";
    writeVectors(provenances, path, pattern_lookup, pos_lookup);
    Instances inst = new Instances(new BufferedReader(new FileReader(path)));
    inst.setClassIndex(inst.numAttributes() - 1);
    try {//from  www. ja v  a  2  s  . c o  m
        cls.buildClassifier(inst);
        // serialize model
        ObjectOutputStream oos = new ObjectOutputStream(new FileOutputStream(path.replace(".arff", ".model")));
        oos.writeObject(cls);
        oos.flush();
        oos.close();
    } catch (Exception e) {
        // TODO Auto-generated catch block
        e.printStackTrace();
    }
}

From source file:de.lmu.ifi.dbs.knowing.core.model.internal.InstancesSerializationService.java

License:Apache License

@Override
protected Object decodeFromString(String value) {
    StringReader reader = new StringReader(value);
    try {/*from ww  w  . j  a  v  a 2 s. c o m*/
        return new Instances(reader);
    } catch (IOException e) {
        e.printStackTrace();
        return null;
    }
}

From source file:de.tudarmstadt.ukp.alignment.framework.combined.WekaMachineLearning.java

License:Apache License

/**
 *
 * This method applies a serialized WEKA model file to an unlabeld .arff file for classification
 *
 *
 * @param input_arff the annotated gold standard in an .arff file
 * @param model output file for the model
 * @param output output file for evaluation of trained classifier (10-fold cross validation)
 * @throws Exception/*from   w w w  .  j a v  a 2s.  com*/
 */

public static void applyModelToUnlabeledArff(String input_arff, String model, String output) throws Exception {
    DataSource source = new DataSource(input_arff);
    Instances unlabeled = source.getDataSet();
    if (unlabeled.classIndex() == -1) {
        unlabeled.setClassIndex(unlabeled.numAttributes() - 1);
    }

    Remove rm = new Remove();
    rm.setAttributeIndices("1"); // remove ID  attribute

    ObjectInputStream ois = new ObjectInputStream(new FileInputStream(model));
    Classifier cls = (Classifier) ois.readObject();
    ois.close();
    // create copy
    Instances labeled = new Instances(unlabeled);

    // label instances
    for (int i = 0; i < unlabeled.numInstances(); i++) {
        double clsLabel = cls.classifyInstance(unlabeled.instance(i));
        labeled.instance(i).setClassValue(clsLabel);
    }
    // save labeled data
    BufferedWriter writer = new BufferedWriter(new FileWriter(output));
    writer.write(labeled.toString());
    writer.newLine();
    writer.flush();
    writer.close();

}

From source file:de.tudarmstadt.ukp.dkpro.spelling.experiments.hoo2012.featureextraction.AllFeaturesExtractor.java

License:Apache License

private Instances getInstances(File instancesFile) throws FileNotFoundException, IOException {
    Instances trainData = null;//from w w w  .  j  av  a2 s . c o m
    Reader reader;
    if (instancesFile.getAbsolutePath().endsWith(".gz")) {
        reader = new BufferedReader(
                new InputStreamReader(new GZIPInputStream(new FileInputStream(instancesFile))));
    } else {
        reader = new BufferedReader(new FileReader(instancesFile));
    }

    try {
        trainData = new Instances(reader);
        trainData.setClassIndex(trainData.numAttributes() - 1);
    } finally {
        reader.close();
    }

    return trainData;
}