Example usage for weka.core Attribute index

Introduction

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

Prototype

public finalint index() 

Source Link

Document

Returns the index of this attribute.

Usage

From source file:ID3Chi.java

License:Open Source License

/**
 * Method for building an ID3Chi tree./*from w  ww. j  a va 2 s.  c  o  m*/
 *
 * @param data
 *            the training data
 * @exception Exception
 *                if decision tree can't be built successfully
 */
private void makeTree(Instances data) throws Exception {

    // Check if no instances have reached this node.
    /*
    if (data.numInstances() == 0) {
       m_Attribute = null;
       m_ClassValue = Instance.missingValue();
       m_Distribution = new double[data.numClasses()];
       return;
    }
    /**/
    if (data.numInstances() == 0) {
        SetNullDistribution(data);
    }

    // Compute attribute with maximum information gain.
    double[] infoGains = new double[data.numAttributes()];
    Enumeration attEnum = data.enumerateAttributes();
    double entropyOfAllData = computeEntropy(data);

    while (attEnum.hasMoreElements()) {
        Attribute att = (Attribute) attEnum.nextElement();
        infoGains[att.index()] = computeInfoGain(data, att, entropyOfAllData);
    }
    m_Attribute = data.attribute(Utils.maxIndex(infoGains));

    double chiSquare = computeChiSquare(data, m_Attribute);

    int degreesOfFreedom = m_Attribute.numValues() - 1;
    ChiSquaredDistribution chi = new ChiSquaredDistribution(degreesOfFreedom);
    double threshold = chi.inverseCumulativeProbability(m_confidenceLevel);

    // Make leaf if information gain is zero.
    // Otherwise create successors.
    if (Utils.eq(infoGains[m_Attribute.index()], 0)) {
        MakeALeaf(data);
    } else {
        // Discard unknown values for selected attribute
        //data.deleteWithMissing(m_Attribute);
        Instances[] subset = splitData(data, m_Attribute);

        if (CheckIfCanApplyChiSquare(subset) && (chiSquare <= threshold)) {
            MakeALeaf(data);
            return;
        }

        m_Successors = new ID3Chi[m_Attribute.numValues()];
        for (int j = 0; j < m_Attribute.numValues(); j++) {
            m_Successors[j] = new ID3Chi(this.m_confidenceLevel);
            m_Successors[j].m_Ratio = (double) subset[j].numInstances() / (double) data.numInstances();
            m_Successors[j].makeTree(subset[j]);
        }
    }
}

---

From source file:adams.flow.sink.WekaInstanceViewer.java

License:Open Source License

/**
 * Displays the token (the panel and dialog have already been created at
 * this stage)./* w  w  w  . j  a v  a2 s .c  o m*/
 *
 * @param token   the token to display
 */
@Override
protected void display(Token token) {
    InstanceContainerManager manager;
    InstanceContainer cont;
    weka.core.Instance winst;
    weka.core.Attribute att;
    String id;
    adams.data.instance.Instance inst;

    if (token.getPayload() instanceof weka.core.Instance) {
        winst = (weka.core.Instance) token.getPayload();
        inst = new adams.data.instance.Instance();
        inst.set(winst);
        if (!m_ID.isEmpty()) {
            att = winst.dataset().attribute(m_ID);
            if (att != null) {
                if (att.isNominal() || att.isString())
                    id = winst.stringValue(att.index());
                else
                    id = "" + winst.value(att.index());
                inst.setID(id);
            }
        }
    } else {
        inst = (adams.data.instance.Instance) token.getPayload();
        if (inst.hasReport() && inst.getReport().hasValue(m_ID))
            inst.setID("" + inst.getReport().getValue(new Field(m_ID, DataType.UNKNOWN)));
    }

    manager = m_InstancePanel.getContainerManager();
    cont = manager.newContainer(inst);
    manager.startUpdate();
    manager.add(cont);

    m_Updater.update(m_InstancePanel, cont);
}

---

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

License:Open Source License

/**
 * Evaluates the experiment data./*  www  . j a va2 s  .c o  m*/
 *
 * @param data   the data to evaluate
 * @throws Exception    If something goes wrong, like loading
 *          data fails or comparison field invalid
 */
protected void evaluateExperiment(Instances data) throws Exception {
    Tester ttester;
    StringBuilder outBuff;
    int compareCol;
    int tType;
    String tmpStr;
    weka.core.Attribute att;

    // setup testing algorithm
    ttester = getTester(data);

    // evaluate experiment
    tmpStr = m_ComparisonField.getField();
    att = data.attribute(tmpStr);
    if (att == null)
        throw new Exception("Cannot find comparison field '" + tmpStr + "' in data!");
    compareCol = att.index();
    tType = m_TestBase;
    outBuff = new StringBuilder();
    if (m_OutputHeader) {
        outBuff.append(ttester.header(compareCol));
        outBuff.append("\n");
    }
    try {
        if (tType < ttester.getNumResultsets())
            outBuff.append(ttester.multiResultsetFull(tType, compareCol));
        else if (tType == ttester.getNumResultsets())
            outBuff.append(ttester.multiResultsetSummary(compareCol));
        else
            outBuff.append(ttester.multiResultsetRanking(compareCol));
        outBuff.append("\n");
    } catch (Exception ex) {
        outBuff.append(ex.getMessage() + "\n");
    }

    // broadcast evaluation
    m_OutputToken = new Token(outBuff.toString());
}

---

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

License:Open Source License

/**
 * Returns whether the specified column is a class attribute.
 *
 * @param name   they name of the column to query
 * @return      true if column a class attribute
 *//*from  w  w  w .  jav a 2 s  .c  om*/
@Override
public boolean isClassAttributeByName(String name) {
    Attribute att;

    att = m_Data.attribute(name);
    return (att != null) && (att.index() == m_Data.classIndex());
}

---

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

License:Open Source License

/**
 * Sets the class attribute status for a column.
 *
 * @param name   the name of the column to set the class attribute status for
 * @param isClass   if true then the column will be flagged as class
 *          attribute, otherwise the flag will get removed
 * @return      true if successfully updated
 *//*from  ww w .  j a v a 2s  . c  om*/
@Override
public boolean setClassAttributeByName(String name, boolean isClass) {
    Attribute att;

    att = m_Data.attribute(name);
    return (att != null) && setClassAttribute(att.index(), isClass);
}

---

From source file:app.RunApp.java

License:Open Source License

/**
 * Action when table attributes clicked with left mouse
 * //from  ww w.  j  ava  2s  .c om
 * @param evt Event
 */
private void tableAttributesLeftMouseClicked(java.awt.event.MouseEvent evt) {//GEN-FIRST:event_tableAttributesLeftMouseClicked
    if (tabsAttributes.getSelectedIndex() == 0) {
        int selected = tableAttributesLeft.getSelectedRow();

        String attr = tableAttributesLeft.getValueAt(selected, 0).toString();

        Instances instances = dataset.getDataSet();

        Attribute currentAttr = instances.attribute(attr);

        double[] attributeValues = instances.attributeToDoubleArray(currentAttr.index());

        HeapSort.sort(attributeValues);

        attributesBoxDiagram2.getChart().setTitle(currentAttr.name());

        attributesBoxDiagram2.getChart().getXYPlot().clearAnnotations();

        ChartUtils.updateXYChart(attributesBoxDiagram2, HeapSort.getSortedArray());
    }
}

---

From source file:asap.PostProcess.java

private void formatPredictions(Instances instances, double[] predictions, String[] columnNames,
        int predictionsColumnIndex, String predictionsColumnName, String columnSeparator, String outputFilename,
        boolean writeColumnsHeaderLine) {
    PerformanceCounters.startTimer("formatPredictions");

    System.out.println("Formatting predictions to file " + outputFilename + "...");
    File outputFile = new File(outputFilename);
    PrintWriter writer;//w  w w .  j a v a 2s. c om

    try {
        outputFile.getParentFile().mkdirs();
        outputFile.createNewFile();
        writer = new PrintWriter(outputFile, "UTF-8");
    } catch (IOException ex) {
        Logger.getLogger(PostProcess.class.getName()).log(Level.SEVERE, null, ex);
        return;
    }

    StringBuilder sb = new StringBuilder();
    DecimalFormat df = new DecimalFormat("#.#", new DecimalFormatSymbols(Locale.US));
    df.setMaximumFractionDigits(3);

    int i = -1;
    if (!writeColumnsHeaderLine) {
        i = 0;
    }
    for (; i < instances.numInstances(); i++) {
        sb.delete(0, sb.length());

        for (int j = 0; j < columnNames.length; j++) {
            if (j > 0) {
                sb.append(columnSeparator);
            }

            if (j == predictionsColumnIndex) {
                if (i < 0) {
                    sb.append(predictionsColumnName);
                } else {
                    sb.append(df.format(predictions[i]));
                }
                sb.append(columnSeparator);
            }
            if (i < 0) {
                sb.append(columnNames[j]);
            } else {
                if (columnNames[j].toLowerCase().contains("id")) {
                    Attribute attribute = instances.attribute(columnNames[j]);
                    if (attribute != null) {
                        sb.append((int) instances.instance(i).value(attribute.index()));
                    } else {
                        sb.append(0);
                    }
                } else {
                    Attribute attribute = instances.attribute(columnNames[j]);
                    if (attribute != null) {
                        sb.append(instances.instance(i).value(attribute.index()));
                    } else {
                        sb.append(df.format(0d));
                    }
                }
            }
        }

        if (columnNames.length == predictionsColumnIndex) {
            sb.append(columnSeparator);
            if (i < 0) {
                sb.append(predictionsColumnName);
            } else {
                sb.append(df.format(predictions[i]));
            }
        }

        writer.println(sb);
    }
    writer.flush();
    writer.close();
    System.out.println("\tdone.");
    PerformanceCounters.stopTimer("formatPredictions");
}

---

From source file:ca.uottawa.balie.WekaLearner.java

License:Open Source License

/**
 * Creates a new classification algorithm.
 * //from   www  . j a  va2s . c  om
 * @param pi_Attributes         Array of attributes
 * @param pi_ClassAttributes   Class attribute
 */
public WekaLearner(WekaAttribute[] pi_Attributes, String[] pi_ClassAttributes) {
    m_ClassAttributes = pi_ClassAttributes;
    m_AttributeLabels = new String[pi_Attributes.length];

    // Create the Weka Attributes
    m_WekaAttributes = new FastVector(pi_Attributes.length + 1);
    for (int i = 0; i != pi_Attributes.length; ++i) {
        if (pi_Attributes[i].Label().equals(CLASS_LABEL)) {
            throw new Error("Attribute cannot be named \"Class\" (reserved)");
        }
        m_AttributeLabels[i] = pi_Attributes[i].Label();
        if (pi_Attributes[i].IsNumeric()) {
            Attribute anAttribute = new Attribute(pi_Attributes[i].Label());
            m_WekaAttributes.addElement(anAttribute);
        } else {
            Attribute anAttribute = new Attribute(pi_Attributes[i].Label(), pi_Attributes[i].Values());
            m_WekaAttributes.addElement(anAttribute);
        }
    }

    // Create The class attribute 
    FastVector fvClass = new FastVector(pi_ClassAttributes.length);
    for (int i = 0; i != pi_ClassAttributes.length; ++i) {
        fvClass.addElement(pi_ClassAttributes[i]);
    }
    Attribute aClass = new Attribute(CLASS_LABEL, fvClass);

    m_WekaAttributes.addElement(aClass);

    m_TrainingSet = new Instances("", m_WekaAttributes, 0);
    m_TrainingSet.setClassIndex(aClass.index());

    m_TestingSet = new Instances("", m_WekaAttributes, 0);
    m_TestingSet.setClassIndex(aClass.index());

    // create an empty confusion matrix.. will be populated at evaluation time
    m_ConfusionMatrix = new double[0][0];
    m_bDoubleOnly = false;
}

---

From source file:cerebro.Id3.java

License:Open Source License

/**
 * Method for building an Id3 tree./*from w ww  .  j av a  2  s .  c  o  m*/
 *
 * @param data the training data
 * @exception Exception if decision tree can't be built successfully
 */
private void makeTree(Instances data) throws Exception {

    // Check if no instances have reached this node.
    if (data.numInstances() == 0) {
        m_Attribute = null;
        m_ClassValue = Instance.missingValue();
        m_Distribution = new double[data.numClasses()];
        return;
    }

    // Compute attribute with maximum information gain.
    double[] infoGains = new double[data.numAttributes()];
    Enumeration attEnum = data.enumerateAttributes();
    while (attEnum.hasMoreElements()) {
        Attribute att = (Attribute) attEnum.nextElement();
        infoGains[att.index()] = computeInfoGain(data, att);
    }
    m_Attribute = data.attribute(Utils.maxIndex(infoGains));

    // Make leaf if information gain is zero.
    // Otherwise create successors.
    if (Utils.eq(infoGains[m_Attribute.index()], 0)) {
        m_Attribute = null;
        m_Distribution = new double[data.numClasses()];
        Enumeration instEnum = data.enumerateInstances();
        while (instEnum.hasMoreElements()) {
            Instance inst = (Instance) instEnum.nextElement();
            m_Distribution[(int) inst.classValue()]++;
        }
        Utils.normalize(m_Distribution);
        m_ClassValue = Utils.maxIndex(m_Distribution);
        m_ClassAttribute = data.classAttribute();
    } else {
        Instances[] splitData = splitData(data, m_Attribute);
        m_Successors = new Id3[m_Attribute.numValues()];
        for (int j = 0; j < m_Attribute.numValues(); j++) {
            m_Successors[j] = new Id3();
            m_Successors[j].makeTree(splitData[j]);
        }
    }
}

---

From source file:cezeri.utils.FactoryInstance.java

public static Instances getSubsetData(Instances data, String[] attList) {
    Instances temp = new Instances(data);
    for (int i = 0; i < data.numAttributes(); i++) {
        if (!temp.attribute(0).equals(temp.classAttribute())) {
            temp.deleteAttributeAt(0);/*w ww  .ja va 2s  .co m*/
        }
    }
    double[][] m = new double[attList.length + 1][data.numInstances()];
    for (int i = 0; i < attList.length; i++) {
        int n = attList.length - 1 - i;
        String str = attList[n];
        Attribute t = data.attribute(str);
        double[] d = data.attributeToDoubleArray(t.index());
        m[n] = d;
        temp.insertAttributeAt(t, 0);
    }
    m[attList.length] = data.attributeToDoubleArray(data.classIndex());
    m = CMatrix.getInstance(m).transpose().get2DArrayDouble();

    FastVector att = new FastVector();
    for (int i = 0; i < temp.numAttributes(); i++) {
        att.addElement(temp.attribute(i));
    }
    Instances ret = new Instances(temp.relationName(), att, m.length);
    for (int i = 0; i < m.length; i++) {
        Instance ins = new Instance(m[0].length);
        for (int j = 0; j < m[0].length; j++) {
            ins.setValue(j, m[i][j]);
        }
        ret.add(ins);
    }
    ret.setClassIndex(temp.classIndex());

    return ret;
}

---

• «
• 1
• 2
• 3
• 4
• 5
• 6
• 7
• 8
• »