Example usage for weka.core Instance setDataset

List of usage examples for weka.core Instance setDataset

  1. HOME
  2. Java
  3. weka
  4. weka.core.*
  5. Instance
  6. setDataset

Introduction

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

Prototype

public void setDataset(Instances instances);

Source Link

Document

Sets the reference to the dataset.

Usage

From source file:focusedCrawler.target.classifier.WekaTargetClassifier.java

License:Open Source License

public double[] distributionForInstance(String target) throws TargetClassifierException {
    double[] result = null;
    try {// w ww.  j ava2 s. co  m
        double[] values = getValues(new Page(null, target));
        weka.core.Instance instanceWeka = new weka.core.Instance(1, values);
        instanceWeka.setDataset(instances);
        result = classifier.distributionForInstance(instanceWeka);
    } catch (Exception ex) {
        ex.printStackTrace();
        throw new TargetClassifierException(ex.getMessage());
    }
    return result;
}

From source file:focusedCrawler.target.classifier.WekaTargetClassifier.java

License:Open Source License

public double[] distributionForInstance(Page page) throws TargetClassifierException {
    double[] result = null;
    try {//from   w  ww.  j  a va 2  s .  c o m
        double[] values = getValues(page);
        weka.core.Instance instanceWeka = new weka.core.Instance(1, values);
        instanceWeka.setDataset(instances);
        result = classifier.distributionForInstance(instanceWeka);
    } catch (Exception ex) {
        ex.printStackTrace();
        throw new TargetClassifierException(ex.getMessage());
    }
    return result;
}

From source file:focusedCrawler.target.TargetClassifierImpl.java

License:Open Source License

public boolean classify(Target target) throws TargetClassifierException {
    boolean relevant = false;
    try {//from   w  w  w.  java  2 s  .  com
        double[] values = getValues(target);
        weka.core.Instance instanceWeka = new weka.core.Instance(1, values);
        instanceWeka.setDataset(instances);
        double classificationResult = classifier.classifyInstance(instanceWeka);
        if (classificationResult == 0) {
            relevant = true;
        } else {
            relevant = false;
        }
    } catch (Exception ex) {
        ex.printStackTrace();
        throw new TargetClassifierException(ex.getMessage());
    }
    return relevant;
}

From source file:focusedCrawler.target.TargetClassifierImpl.java

License:Open Source License

public double[] distributionForInstance(Target target) throws TargetClassifierException {
    double[] result = null;
    try {//w  w w  .  j a v a2 s.com
        double[] values = getValues(target);
        weka.core.Instance instanceWeka = new weka.core.Instance(1, values);
        instanceWeka.setDataset(instances);
        result = classifier.distributionForInstance(instanceWeka);
    } catch (Exception ex) {
        ex.printStackTrace();
        throw new TargetClassifierException(ex.getMessage());
    }
    return result;
}

From source file:form.ml.ClassifierTemplate.java

/**
 * make the Instance weka object from a String
 *
 * @param text the String to be converted
 * @return Instance object// w ww. j av  a2 s  .co  m
 */
private Instance makeInstance(String text) {
    Instance instance = new Instance(2);
    Attribute attribute = train.attribute("text");
    instance.setValue(attribute, attribute.addStringValue(text));
    instance.setDataset(train);
    return instance;
}

From source file:fr.loria.synalp.jtrans.phonetiseur.Classifieurs.java

License:Open Source License

/**
 * => on peut passer null au parametre Postag si on ne veut pas remplir le champ
 *///from  ww  w  . j  ava 2s  . c o  m
public AlignementGraphemesPhonemes phonetiser(String[] tGraphemes, String Postag) throws Exception {
    ArrayList<String> alGraphemes = new ArrayList<String>();
    ArrayList<String> alPhonemes = new ArrayList<String>();

    String graphemeCourant, doublePhoneme1er;
    Instance instance;
    int indiceGraphemeCourant;

    for (int i = 0; i < tGraphemes.length; i++) {
        // Est-ce-que le grapheme i est un simple ou double phoneme ?
        instance = new Instance(11);
        instance.setDataset(instancesSimpleOuDoublePhoneme);
        setval(instance, 0, tGraphemes[i]);
        setval(instance, 1, (i >= 1) ? tGraphemes[i - 1] : Configuration.GRAPHEME_DEBUT_DE_MOT_VECTEUR);
        setval(instance, 2, (i >= 2) ? tGraphemes[i - 2] : Configuration.GRAPHEME_DEBUT_DE_MOT_VECTEUR);
        setval(instance, 3, (i >= 3) ? tGraphemes[i - 3] : Configuration.GRAPHEME_DEBUT_DE_MOT_VECTEUR);
        setval(instance, 4, (i >= 4) ? tGraphemes[i - 4] : Configuration.GRAPHEME_DEBUT_DE_MOT_VECTEUR);
        setval(instance, 5,
                (i < tGraphemes.length - 1) ? tGraphemes[i + 1] : Configuration.GRAPHEME_FIN_DE_MOT_VECTEUR);
        setval(instance, 6,
                (i < tGraphemes.length - 2) ? tGraphemes[i + 2] : Configuration.GRAPHEME_FIN_DE_MOT_VECTEUR);
        setval(instance, 7,
                (i < tGraphemes.length - 3) ? tGraphemes[i + 3] : Configuration.GRAPHEME_FIN_DE_MOT_VECTEUR);
        setval(instance, 8,
                (i < tGraphemes.length - 4) ? tGraphemes[i + 4] : Configuration.GRAPHEME_FIN_DE_MOT_VECTEUR);
        if (Postag != null) {
            setval(instance, 9, Postag);
        }
        instance = appliquerFiltreAUneInstance(filtreSimpleOuDoublePhoneme, instance,
                instancesSimpleOuDoublePhoneme);

        if (resultatClassifieur(instance, classifieurSimpleOuDoublePhoneme, instancesSimpleOuDoublePhoneme)
                .equals(Configuration.VALEUR_SORTIE_VECTEUR_SIMPLE_PHONEME)) {
            // Cas d'un simple phoneme
            graphemeCourant = tGraphemes[i];
            indiceGraphemeCourant = lexique.getIndiceFromGrapheme(graphemeCourant);
            if (indiceGraphemeCourant < 0) {
                System.err.println("unknown grapheme " + graphemeCourant);
                continue;
            }
            instance = new Instance(11);
            instance.setDataset(tInstancesSimplePhoneme[indiceGraphemeCourant]);
            setval(instance, 0, tGraphemes[i]);
            setval(instance, 1, (i >= 1) ? tGraphemes[i - 1] : Configuration.GRAPHEME_DEBUT_DE_MOT_VECTEUR);
            setval(instance, 2, (i >= 2) ? tGraphemes[i - 2] : Configuration.GRAPHEME_DEBUT_DE_MOT_VECTEUR);
            setval(instance, 3, (i >= 3) ? tGraphemes[i - 3] : Configuration.GRAPHEME_DEBUT_DE_MOT_VECTEUR);
            setval(instance, 4, (i >= 4) ? tGraphemes[i - 4] : Configuration.GRAPHEME_DEBUT_DE_MOT_VECTEUR);
            setval(instance, 5, (i < tGraphemes.length - 1) ? tGraphemes[i + 1]
                    : Configuration.GRAPHEME_FIN_DE_MOT_VECTEUR);
            setval(instance, 6, (i < tGraphemes.length - 2) ? tGraphemes[i + 2]
                    : Configuration.GRAPHEME_FIN_DE_MOT_VECTEUR);
            setval(instance, 7, (i < tGraphemes.length - 3) ? tGraphemes[i + 3]
                    : Configuration.GRAPHEME_FIN_DE_MOT_VECTEUR);
            setval(instance, 8, (i < tGraphemes.length - 4) ? tGraphemes[i + 4]
                    : Configuration.GRAPHEME_FIN_DE_MOT_VECTEUR);
            if (Postag != null) {
                setval(instance, 9, Postag);
            }
            instance = appliquerFiltreAUneInstance(filtreSimplePhoneme, instance,
                    tInstancesSimplePhoneme[indiceGraphemeCourant]);

            alGraphemes.add(graphemeCourant);
            alPhonemes.add(resultatClassifieur(instance, tClassifieurSimplePhoneme[indiceGraphemeCourant],
                    tInstancesSimplePhoneme[indiceGraphemeCourant]));
        } else {
            // Cas d'un double phoneme
            // Double phoneme 1
            instance = new Instance(11);
            instance.setDataset(instancesDoublePhoneme1er);
            setval(instance, 0, tGraphemes[i]);
            setval(instance, 1, (i >= 1) ? tGraphemes[i - 1] : Configuration.GRAPHEME_DEBUT_DE_MOT_VECTEUR);
            setval(instance, 2, (i >= 2) ? tGraphemes[i - 2] : Configuration.GRAPHEME_DEBUT_DE_MOT_VECTEUR);
            setval(instance, 3, (i >= 3) ? tGraphemes[i - 3] : Configuration.GRAPHEME_DEBUT_DE_MOT_VECTEUR);
            setval(instance, 4, (i >= 4) ? tGraphemes[i - 4] : Configuration.GRAPHEME_DEBUT_DE_MOT_VECTEUR);
            setval(instance, 5, (i < tGraphemes.length - 1) ? tGraphemes[i + 1]
                    : Configuration.GRAPHEME_FIN_DE_MOT_VECTEUR);
            setval(instance, 6, (i < tGraphemes.length - 2) ? tGraphemes[i + 2]
                    : Configuration.GRAPHEME_FIN_DE_MOT_VECTEUR);
            setval(instance, 7, (i < tGraphemes.length - 3) ? tGraphemes[i + 3]
                    : Configuration.GRAPHEME_FIN_DE_MOT_VECTEUR);
            setval(instance, 8, (i < tGraphemes.length - 4) ? tGraphemes[i + 4]
                    : Configuration.GRAPHEME_FIN_DE_MOT_VECTEUR);
            if (Postag != null) {
                setval(instance, 9, Postag);
            }
            instance = appliquerFiltreAUneInstance(filtreDoublePhoneme1er, instance, instancesDoublePhoneme1er);

            doublePhoneme1er = resultatClassifieur(instance, classifieurDoublePhoneme1er,
                    instancesDoublePhoneme1er);

            alGraphemes.add(tGraphemes[i]);
            alPhonemes.add(doublePhoneme1er);

            // Double phoneme 2
            instance = new Instance(12);
            instance.setDataset(instancesDoublePhoneme2eme);
            setval(instance, 0, tGraphemes[i]);
            setval(instance, 1, doublePhoneme1er);
            setval(instance, 2, (i >= 1) ? tGraphemes[i - 1] : Configuration.GRAPHEME_DEBUT_DE_MOT_VECTEUR);
            setval(instance, 3, (i >= 2) ? tGraphemes[i - 2] : Configuration.GRAPHEME_DEBUT_DE_MOT_VECTEUR);
            setval(instance, 4, (i >= 3) ? tGraphemes[i - 3] : Configuration.GRAPHEME_DEBUT_DE_MOT_VECTEUR);
            setval(instance, 5, (i >= 4) ? tGraphemes[i - 4] : Configuration.GRAPHEME_DEBUT_DE_MOT_VECTEUR);
            setval(instance, 6, (i < tGraphemes.length - 1) ? tGraphemes[i + 1]
                    : Configuration.GRAPHEME_FIN_DE_MOT_VECTEUR);
            setval(instance, 7, (i < tGraphemes.length - 2) ? tGraphemes[i + 2]
                    : Configuration.GRAPHEME_FIN_DE_MOT_VECTEUR);
            setval(instance, 8, (i < tGraphemes.length - 3) ? tGraphemes[i + 3]
                    : Configuration.GRAPHEME_FIN_DE_MOT_VECTEUR);
            setval(instance, 9, (i < tGraphemes.length - 4) ? tGraphemes[i + 4]
                    : Configuration.GRAPHEME_FIN_DE_MOT_VECTEUR);
            if (Postag != null) {
                setval(instance, 10, Postag);
            }
            instance = appliquerFiltreAUneInstance(filtreDoublePhoneme2eme, instance,
                    instancesDoublePhoneme2eme);

            alGraphemes.add(Configuration.STRING_DE_REMPLACEMENT_GRAPHEME_VIDE);
            alPhonemes.add(
                    resultatClassifieur(instance, classifieurDoublePhoneme2eme, instancesDoublePhoneme2eme));
        }
    }

    return new AlignementGraphemesPhonemes(alGraphemes, alPhonemes);
}

From source file:GClass.EvaluationInternal.java

License:Open Source License

/**
 * Prints the predictions for the given dataset into a String variable.
 *//*  w w  w .j  a v a  2 s .  c om*/
protected static String printClassifications(Classifier classifier, Instances train, String testFileName,
        int classIndex, Range attributesToOutput) throws Exception {

    StringBuffer text = new StringBuffer();
    if (testFileName.length() != 0) {
        BufferedReader testReader = null;
        try {
            testReader = new BufferedReader(new FileReader(testFileName));
        } catch (Exception e) {
            throw new Exception("Can't open file " + e.getMessage() + '.');
        }
        Instances test = new Instances(testReader, 1);
        if (classIndex != -1) {
            test.setClassIndex(classIndex - 1);
        } else {
            test.setClassIndex(test.numAttributes() - 1);
        }
        int i = 0;
        while (test.readInstance(testReader)) {
            Instance instance = test.instance(0);
            Instance withMissing = (Instance) instance.copy();
            withMissing.setDataset(test);
            double predValue = ((Classifier) classifier).classifyInstance(withMissing);
            if (test.classAttribute().isNumeric()) {
                if (Instance.isMissingValue(predValue)) {
                    text.append(i + " missing ");
                } else {
                    text.append(i + " " + predValue + " ");
                }
                if (instance.classIsMissing()) {
                    text.append("missing");
                } else {
                    text.append(instance.classValue());
                }
                text.append(" " + attributeValuesString(withMissing, attributesToOutput) + "\n");
            } else {
                if (Instance.isMissingValue(predValue)) {
                    text.append(i + " missing ");
                } else {
                    text.append(i + " " + test.classAttribute().value((int) predValue) + " ");
                }
                if (Instance.isMissingValue(predValue)) {
                    text.append("missing ");
                } else {
                    text.append(classifier.distributionForInstance(withMissing)[(int) predValue] + " ");
                }
                text.append(instance.toString(instance.classIndex()) + " "
                        + attributeValuesString(withMissing, attributesToOutput) + "\n");
            }
            test.delete(0);
            i++;
        }
        testReader.close();
    }
    return text.toString();
}

From source file:gnusmail.filters.FilterManager.java

License:Open Source License

/**
 * Extracts Attributes for a given message. A connection is opened and
 * closed for each mail, as the number of open folders is limited (and we
 * cannot predict it, since we are iterating over the mails
 * chronologically):w/*from w  ww  .  ja  v  a  2  s.c om*/
 * 
 */
public Instance makeInstance(Document document) {
    if (dataset == null) {
        Logger.getLogger(FilterManager.class.getName()).log(Level.SEVERE, "Dataset is null");
        return null;
    }
    Instance inst = new DenseInstance(dataset.numAttributes());
    inst.setDataset(dataset);
    for (Filter filter : filterList) {
        filter.updateInstance(inst, document);
    }

    return inst;
}

From source file:gr.ntua.ece.cslab.panic.core.models.AbstractWekaModel.java

License:Apache License

/**
 * Converts an input space point to a Weka instance.
 * @param point//  www  .  j a v a 2s  .co  m
 * @return 
 */
public static Instance convertPointToInstance(InputSpacePoint point, OutputSpacePoint outputPoint) {
    Instance inst = new Instance(point.numberDimensions() + outputPoint.numberDimensions());
    int index = 0;
    for (String k : point.getKeysAsCollection()) {
        Attribute att = new Attribute(k, index++);
        inst.setValue(att, point.getValue(k));
    }
    for (Entry<String, Double> e : outputPoint.getOutputPoints().entrySet()) {
        if (e.getValue() == null) {
            inst.setMissing(index++);
        } else {
            Attribute att = new Attribute(e.getKey(), index++);
            inst.setValue(att, e.getValue());
        }
    }

    //assign instance to dataset
    FastVector att = new FastVector(point.numberDimensions() + 1);
    for (String s : point.getKeysAsCollection())
        att.addElement(new Attribute(s, index++));
    for (String k : outputPoint.getOutputPoints().keySet()) {
        att.addElement(new Attribute(k, index++));
    }

    Instances dataset = new Instances("instances", att, point.numberDimensions() + 1);
    dataset.setClassIndex(dataset.numAttributes() - 1);
    inst.setDataset(dataset);
    return inst;
}

From source file:gr.ntua.ece.cslab.panic.core.models.AbstractWekaModel.java

License:Apache License

public static Instance convertPointToInstance(InputSpacePoint point) {
    Instance inst = new Instance(point.numberDimensions() + 1);
    int index = 0;
    for (String k : point.getKeysAsCollection()) {
        Attribute att = new Attribute(k, index++);
        inst.setValue(att, point.getValue(k));
    }/*from   www .j  av  a 2 s.co m*/
    inst.setMissing(index);

    //assign instance to dataset
    FastVector att = new FastVector(point.numberDimensions() + 1);
    for (String s : point.getKeysAsCollection())
        att.addElement(new Attribute(s, index++));
    att.addElement(new Attribute("objective", index++));

    Instances dataset = new Instances("instances", att, point.numberDimensions() + 1);
    dataset.setClassIndex(dataset.numAttributes() - 1);
    inst.setDataset(dataset);
    return inst;
}