Example usage for weka.core Instance 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:adams.data.instances.AbstractInstanceGenerator.java

License:Open Source License

/**
 * For adding IDs, notes, additional fields to the data.
 *
 * @param data   the input data//w  ww. j a  v a  2s.  co m
 * @param inst   the generated instance
 * @return      the processed instance
 */
protected Instance postProcessOutput(T data, Instance inst) {
    Instance result;
    double[] values;
    int index;
    Report report;

    values = inst.toDoubleArray();
    report = data.getReport();

    if (m_AddDatabaseID) {
        index = m_OutputHeader.attribute(ArffUtils.getDBIDName()).index();
        values[index] = report.getDatabaseID();
    }

    result = new DenseInstance(1.0, values);
    result.setDataset(m_OutputHeader);

    return result;
}

---

From source file:adams.flow.transformer.WekaInstanceDumper.java

License:Open Source License

/**
 * Executes the flow item.//from  w  w w  . j ava 2s.  c o m
 *
 * @return      null if everything is fine, otherwise error message
 */
@Override
protected String doExecute() {
    String result;
    Instance inst;
    Instances newHeader;
    double[] values;
    boolean append;
    ArrayList<Attribute> atts;
    int i;

    result = null;

    if (m_InputToken.getPayload() instanceof Instance) {
        inst = (Instance) m_InputToken.getPayload();
        // get header and optionally compare it to previous (to start a new
        // output file)
        newHeader = inst.dataset();
    } else {
        values = (double[]) m_InputToken.getPayload();
        // create artificial dataset header
        atts = new ArrayList<>();
        for (i = 0; i < values.length; i++)
            atts.add(new Attribute("att_" + (i + 1)));
        newHeader = new Instances(getName(), atts, 0);
        inst = new DenseInstance(1.0, values);
        inst.setDataset(newHeader);
    }

    append = true;
    if (m_Header == null) {
        m_Header = new Instances(newHeader, 0);
        if (!m_KeepExisting)
            append = false;
    } else {
        if (m_CheckHeader) {
            if (!m_Header.equalHeaders(newHeader)) {
                m_Counter++;
                m_Header = new Instances(newHeader, 0);
                append = false;
            }
        }
    }

    if (!append)
        FileUtils.delete(createFilename(inst.dataset()).getAbsolutePath());

    // buffer data and write to disk if necessary
    m_Buffer.add(inst);
    if (m_Buffer.size() >= m_BufferSize)
        result = writeToDisk(append);

    // broadcast name
    if (result == null)
        m_OutputToken = new Token(createFilename(inst.dataset()).getAbsolutePath());

    return result;
}

---

From source file:adams.flow.transformer.WekaNewInstance.java

License:Open Source License

/**
 * Executes the flow item./*  www  . j a  v a 2s  .  com*/
 *
 * @return      null if everything is fine, otherwise error message
 */
@Override
protected String doExecute() {
    String result;
    Instances data;
    Instance inst;
    Class cls;
    Constructor constr;

    result = null;

    data = (Instances) m_InputToken.getPayload();

    try {
        cls = m_InstanceClass.classValue();
        constr = cls.getConstructor(new Class[] { Integer.TYPE });
        inst = (Instance) constr.newInstance(new Object[] { data.numAttributes() });
        inst.setDataset(data);
        m_OutputToken = new Token(inst);
    } catch (Exception e) {
        result = handleException("Failed to create new instance: ", e);
    }

    return result;
}

---

From source file:adams.ml.data.WekaConverter.java

License:Open Source License

/**
 * Turns an ADAMS dataset row into a Weka Instance.
 *
 * @param data   the dataset to use as template
 * @param row      the row to convert/*w  w  w. j av a2 s  .  co  m*/
 * @return      the generated instance
 * @throws Exception   if conversion fails
 */
public static Instance toInstance(Instances data, Row row) throws Exception {
    Instance result;
    double[] values;
    int i;
    Cell cell;
    Attribute att;

    values = new double[data.numAttributes()];
    for (i = 0; i < data.numAttributes(); i++) {
        values[i] = Utils.missingValue();

        if (!row.hasCell(i))
            continue;
        cell = row.getCell(i);
        if (cell.isMissing())
            continue;

        att = data.attribute(i);
        switch (att.type()) {
        case Attribute.NUMERIC:
            values[i] = cell.toDouble();
            break;
        case Attribute.DATE:
            values[i] = cell.toAnyDateType().getTime();
            break;
        case Attribute.NOMINAL:
            values[i] = att.indexOfValue(cell.getContent());
            break;
        case Attribute.STRING:
            values[i] = att.addStringValue(cell.getContent());
            break;
        default:
            throw new Exception("Unhandled Weka attribute type: " + Attribute.typeToString(att));
        }
    }

    result = new DenseInstance(1.0, values);
    result.setDataset(data);

    return result;
}

---

From source file:ant.Game.java

private char keyFromWeka(int classifier) {

    char key = W;

    Instance i = new Instance(m_ant.getNumAttributes() + 1);
    i.setDataset(m_data);
    for (int j = 0; j < i.numAttributes() - 1; ++j) {
        i.setValue(new Attribute(Integer.toString(j), j), see(j));
    }/*from w  ww  .j a  v  a2 s .  c om*/

    i.setClassValue(1);
    double p = -1;
    try {
        p = m_wrapper10x1.classifyInstance(i);
    } catch (Exception ex) {
        Logger.getLogger(Game.class.getName()).log(Level.SEVERE, null, ex);
    }

    switch ((int) p) {
    case 0:
        key = W;
        break;
    case 1:
        key = A;
        break;
    case 2:
        key = S;
        break;
    case 3:
        key = D;
        break;
    default:
        System.err.println("Unexpected classifier output!");
        break;
    }

    return key;
}

---

From source file:aprendizadodemaquina.classificadores.ClassificadorDT.java

License:Open Source License

/**
 * Retorna a classificao de uma instncia de relao.
 * //from  w  ww .j a v a 2 s  . c  o m
 * @param instance Instncia de relao criada pelo objeto featurizador
 * @return Classe predita pelo classificador para a instncia fornecida
 */
public String classificar(Instance instance) {
    //System.out.println( "DEBUG: Classificando instncia " + instance );
    instance.setDataset(dadosTreinamento);
    try {
        double pred = classificador.classifyInstance(instance);
        return dadosTreinamento.classAttribute().value((int) pred);
    } catch (Exception ex) {
        Logger.getLogger("ARS logger").log(Level.SEVERE, null, ex);
    }
    return "none";
}

---

From source file:at.aictopic1.sentimentanalysis.machinelearning.impl.TwitterClassifer.java

public Integer classify(Tweet[] tweets) {
    // TEST//from  w w  w. j  a v  a  2  s.co  m

    // Generate two tweet examples
    Tweet exOne = new Tweet("This is good and fantastic");
    exOne.setPreprocessedText("This is good and fantastic");
    Tweet exTwo = new Tweet("Horribly, terribly bad and more");
    exTwo.setPreprocessedText("Horribly, terribly bad and more");
    Tweet exThree = new Tweet(
            "I want to update lj and read my friends list, but I\\'m groggy and sick and blargh.");
    exThree.setPreprocessedText(
            "I want to update lj and read my friends list, but I\\'m groggy and sick and blargh.");
    Tweet exFour = new Tweet("bad hate worst sick");
    exFour.setPreprocessedText("bad hate worst sick");
    tweets = new Tweet[] { exOne, exTwo, exThree, exFour };
    // TEST

    // Load model
    //        loadModel();
    // Convert Tweet to Instance type 
    // Get String Data
    // Create attributes for the Instances set
    Attribute twitter_id = new Attribute("twitter_id");
    //        Attribute body = new Attribute("body");

    FastVector classVal = new FastVector(2);
    classVal.addElement("pos");
    classVal.addElement("neg");

    Attribute class_attr = new Attribute("class_attr", classVal);

    // Add them to a list
    FastVector attrVector = new FastVector(3);
    //        attrVector.addElement(twitter_id);
    //        attrVector.addElement(new Attribute("body", (FastVector) null));
    //        attrVector.addElement(class_attr);

    // Get the number of tweets and then create predictSet
    int numTweets = tweets.length;
    Enumeration structAttrs = dataStructure.enumerateAttributes();

    //        ArrayList<Attribute> attrList = new ArrayList<Attribute>(dataStructure.numAttributes());
    while (structAttrs.hasMoreElements()) {
        attrVector.addElement((Attribute) structAttrs.nextElement());
    }
    Instances predictSet = new Instances("predictInstances", attrVector, numTweets);
    //        Instances predictSet = new Instances(dataStructure);
    predictSet.setClassIndex(2);

    // init prediction
    double prediction = -1;

    System.out.println("PredictSet matches source structure: " + predictSet.equalHeaders(dataStructure));

    System.out.println("PredSet struct: " + predictSet.attribute(0));
    System.out.println("PredSet struct: " + predictSet.attribute(1));
    System.out.println("PredSet struct: " + predictSet.attribute(2));
    // Array to return predictions 
    //double[] tweetsClassified = new double[2][numTweets];
    //List<Integer, Double> tweetsClass = new ArrayList<Integer, Double>(numTweets);
    for (int i = 0; i < numTweets; i++) {
        String content = (String) tweets[i].getPreprocessedText();

        System.out.println("Tweet content: " + content);

        //            attrList
        Instance tweetInstance = new Instance(predictSet.numAttributes());

        tweetInstance.setDataset(predictSet);

        tweetInstance.setValue(predictSet.attribute(0), i);
        tweetInstance.setValue(predictSet.attribute(1), content);
        tweetInstance.setClassMissing();

        predictSet.add(tweetInstance);

        try {
            // Apply string filter
            StringToWordVector filter = new StringToWordVector();

            filter.setInputFormat(predictSet);
            Instances filteredPredictSet = Filter.useFilter(predictSet, filter);

            // Apply model
            prediction = trainedModel.classifyInstance(filteredPredictSet.instance(i));
            filteredPredictSet.instance(i).setClassValue(prediction);
            System.out.println("Classification: " + filteredPredictSet.instance(i).toString());
            System.out.println("Prediction: " + prediction);

        } catch (Exception ex) {
            Logger.getLogger(TwitterClassifer.class.getName()).log(Level.SEVERE, null, ex);
        }
    }

    return 0;
}

---

From source file:at.tuflowgraphy.semanticapps.semdroid.DalvikBaseAnalyzer.java

License:Apache License

protected void addLastXWekaInstances(Instances instances, int numberOfInstances, List<Object> linkedObjects) {
    // TODO: use ResultEntry instead of List<Object>
    if (numberOfInstances <= 0) {
        return;//from   www .  j  a v  a2  s .  c  om
    }
    List<DActivationPatternPackage> dActivationPatternPackages = mAnalysisChain.getFinalLayers().get(0)
            .getResultAnalysisPackage().getActivationPatternPackages();
    int counter = 0;
    for (DActivationPatternPackage dActivationPatternPackage : dActivationPatternPackages) {
        DActivationPattern activationPatternTemp = dActivationPatternPackage.getActivationPatterns().get(0);
        if (counter > 0) {
            throw new RuntimeException("More than one DActivationPatternPackage found!");
        }
        counter++;

        for (int i = numberOfInstances - 1; i >= 0; i--) {
            DActivationPattern activationPattern = dActivationPatternPackage.getActivationPatterns()
                    .get(dActivationPatternPackage.getActivationPatterns().size() - 1 - i);
            Instance instance = new Instance(activationPatternTemp.getRawPattern().length + 1);

            for (int j = 0; j < activationPattern.getRawPattern().length; j++) {
                instance.setValue(j, activationPattern.getRawPattern()[j]);
            }
            instances.add(instance);
            instance.setDataset(instances);

            if (linkedObjects != null) {
                DBasicMetaData d = activationPattern.getMetaData();
                if (d instanceof DObjectLinkMetaData) {
                    Object o = ((DObjectLinkMetaData) d).getLinkedObject();
                    linkedObjects.add(o);
                } else {
                    throw new IllegalArgumentException(
                            "Wrong metadata type attached! Must be DObjectLinkMetaData!");
                }
            }
        }

    }
}

---

From source file:at.tuflowgraphy.semanticapps.semdroid.DalvikBaseAnalyzer.java

License:Apache License

public Instances getWekaInstances() {
    Instances instances = null;/* w w w. j  a  v  a2s .  c  om*/
    List<DActivationPatternPackage> dActivationPatternPackages = mAnalysisChain.getFinalLayers().get(0)
            .getResultAnalysisPackage().getActivationPatternPackages();
    int counter = 0;
    for (DActivationPatternPackage dActivationPatternPackage : dActivationPatternPackages) {
        if (counter > 0) {
            throw new RuntimeException("More than one DActivationPatternPackage found!");
        }
        counter++;
        DActivationPattern activationPatternTemp = dActivationPatternPackage.getActivationPatterns().get(0);
        FastVector fvWekaAttributes = new FastVector(activationPatternTemp.getRawPattern().length);
        for (int j = 0; j < activationPatternTemp.getRawPattern().length; j++) {
            Attribute attribute = new Attribute(j + "");
            fvWekaAttributes.addElement(attribute);
        }

        Set<String> labelSet = getLabelSet(dActivationPatternPackage);

        FastVector classValues = new FastVector(labelSet.size());
        for (String label : labelSet) {
            classValues.addElement(label);
        }

        Attribute classAttribute = new Attribute("Class", classValues);
        fvWekaAttributes.addElement(classAttribute);

        instances = new Instances(mAnalysisConfig.getApplicationAnalysisName(), fvWekaAttributes,
                dActivationPatternPackage.getActivationPatterns().size());
        instances.setClassIndex(instances.numAttributes() - 1);

        for (int i = 0; i < dActivationPatternPackage.getActivationPatterns().size(); i++) {
            DActivationPattern activationPattern = dActivationPatternPackage.getActivationPatterns().get(i);
            Instance instance = new Instance(fvWekaAttributes.size());

            for (int j = 0; j < activationPattern.getRawPattern().length; j++) {
                instance.setValue((Attribute) fvWekaAttributes.elementAt(j),
                        activationPattern.getRawPattern()[j]);
            }

            instance.setDataset(instances);

            DSimpleStringMetaData metadata = (DSimpleStringMetaData) activationPattern.getMetaData();
            List<String> keys = metadata.getMetaDataKeys();
            for (int k = 0; k < keys.size(); k++) {
                if (keys.get(k).equals(DalvikInputPlugin.TAG_LABEL)) {
                    String label = metadata.getMetaDataEntries().get(k);
                    instance.setClassValue(label);
                    break;
                }
            }

            instances.add(instance);
        }

    }
    return instances;
}

---

From source file:at.tuflowgraphy.semanticapps.semdroid.utils.ArffHelper.java

License:Apache License

public Instances getWekaInstances(AnalysisChain analysisChain, String name) {
    Instances instances = null;/*from   w w  w  . java  2  s .c o  m*/
    List<DActivationPatternPackage> dActivationPatternPackages = analysisChain.getFinalLayers().get(0)
            .getResultAnalysisPackage().getActivationPatternPackages();
    int counter = 0;
    for (DActivationPatternPackage dActivationPatternPackage : dActivationPatternPackages) {
        if (counter > 0) {
            //                String resultFileName = arffFile.getName();
            //                String newName = resultFileName.split("_")[0];
            //                int index = resultFileName.indexOf("_");
            //                newName += "-MISSING-" + counter + "-"
            //                        + resultFileName.substring(index);
            //                arffFileToWriteTo = new File(arffFile.getParentFile(), newName);
            System.err.println("ERROR: Multiple activation pattern packages found! Should not happen...");
        }
        counter++;
        DActivationPattern activationPatternTemp = dActivationPatternPackage.getActivationPatterns().get(0);
        FastVector fvWekaAttributes = new FastVector(activationPatternTemp.getRawPattern().length);
        for (int j = 0; j < activationPatternTemp.getRawPattern().length; j++) {
            Attribute attribute = new Attribute(j + "");
            fvWekaAttributes.addElement(attribute);
        }

        Set<String> labelSet = getLabelSet(dActivationPatternPackage);

        FastVector classValues = new FastVector(labelSet.size());
        for (String label : labelSet) {
            classValues.addElement(label);
        }

        Attribute classAttribute = new Attribute("Class", classValues);
        fvWekaAttributes.addElement(classAttribute);

        instances = new Instances(name, fvWekaAttributes,
                dActivationPatternPackage.getActivationPatterns().size());
        instances.setClassIndex(instances.numAttributes() - 1);

        for (int i = 0; i < dActivationPatternPackage.getActivationPatterns().size(); i++) {
            DActivationPattern activationPattern = dActivationPatternPackage.getActivationPatterns().get(i);
            Instance instance = new Instance(fvWekaAttributes.size());

            for (int j = 0; j < activationPattern.getRawPattern().length; j++) {
                instance.setValue((Attribute) fvWekaAttributes.elementAt(j),
                        activationPattern.getRawPattern()[j]);
            }

            instance.setDataset(instances);

            DSimpleStringMetaData metadata = (DSimpleStringMetaData) activationPattern.getMetaData();
            List<String> keys = metadata.getMetaDataKeys();
            for (int k = 0; k < keys.size(); k++) {
                if (keys.get(k).equals(DalvikInputPlugin.TAG_LABEL)) {
                    String label = metadata.getMetaDataEntries().get(k);

                    // TODO: dynamically add new labels to instances so that getLabelSet for-loop is not required

                    // System.out.println(label);
                    // if(!labelSet.contains(label)) {
                    // labelSet.add(label);
                    // // classValues.addElement(label);
                    // classAttribute.addStringValue(label);
                    // instances.attribute(instances.classIndex()).addValue(label);
                    // System.out.println("ADDED " + label);
                    // }
                    instance.setClassValue(label);
                    // TODO: only first class value used
                    break;
                }
            }
            instances.add(instance);
        }

    }
    return instances;
}

---

• «
• 1
• 2
• 3
• 4
• 5
• 6
• 7
• 8
• 9
• 10
• 11
• 12
• 13
• 14
• 15
• 16
• 17
• 18
• 19
• 20
• 21
• 22
• 23
• 24
• 25
• 26
• 27
• 28
• 29
• 30
• 31
• 32
• 33
• 34
• »