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:com.mycompany.tubesann.MyANN.java

public static Instances setNominalToBinary(Instances instances) {
    NominalToBinary ntb = new NominalToBinary();
    Instances newInstances = null;//from  w w  w. jav  a2 s . c  o m
    try {
        ntb.setInputFormat(instances);
        newInstances = new Instances(Filter.useFilter(instances, ntb));
    } catch (Exception e) {
        e.printStackTrace();
    }

    return newInstances;
}

---

From source file:com.reactivetechnologies.analytics.core.eval.AdaBoostM1WithBuiltClassifiers.java

License:Open Source License

@Override
public void buildClassifier(Instances data) throws Exception {
    /** Changed here: Using the provided classifiers */
    /** End *//* w w w . j a v a  2s. c o m*/

    // can classifier handle the data?
    getCapabilities().testWithFail(data);

    // remove instances with missing class
    data = new Instances(data);
    data.deleteWithMissingClass();

    // only class? -> build ZeroR model
    if (data.numAttributes() == 1) {
        System.err.println(
                "Cannot build model (only class attribute present in data!), " + "using ZeroR model instead!");
        m_ZeroR = new weka.classifiers.rules.ZeroR();
        m_ZeroR.buildClassifier(data);
        return;
    } else {
        m_ZeroR = null;
    }

    m_NumClasses = data.numClasses();
    if ((!m_UseResampling) && (m_Classifier instanceof WeightedInstancesHandler)) {
        buildClassifierWithWeights(data);
    } else {
        buildClassifierUsingResampling(data);
    }
}

---

From source file:com.reactivetechnologies.analytics.core.eval.BaggingWithBuiltClassifiers.java

License:Open Source License

@Override
public void buildClassifier(Instances data) throws Exception {

    // can classifier handle the data?
    getCapabilities().testWithFail(data);

    // remove instances with missing class
    data = new Instances(data);
    data.deleteWithMissingClass();/*from  w  w w.ja v a  2 s  . c  om*/

    /** Changed here: Use supplied classifier */
    //super.buildClassifier(data);
    /** End change */

    if (m_CalcOutOfBag && (m_BagSizePercent != 100)) {
        throw new IllegalArgumentException(
                "Bag size needs to be 100% if " + "out-of-bag error is to be calculated!");
    }

    int bagSize = (int) (data.numInstances() * (m_BagSizePercent / 100.0));
    Random random = new Random(m_Seed);

    boolean[][] inBag = null;
    if (m_CalcOutOfBag)
        inBag = new boolean[m_Classifiers.length][];

    for (int j = 0; j < m_Classifiers.length; j++) {
        Instances bagData = null;

        // create the in-bag dataset
        if (m_CalcOutOfBag) {
            inBag[j] = new boolean[data.numInstances()];
            bagData = data.resampleWithWeights(random, inBag[j]);
        } else {
            bagData = data.resampleWithWeights(random);
            if (bagSize < data.numInstances()) {
                bagData.randomize(random);
                Instances newBagData = new Instances(bagData, 0, bagSize);
                bagData = newBagData;
            }
        }

        /** Changed here: Use supplied classifier */
        /*if (m_Classifier instanceof Randomizable) {
          ((Randomizable) m_Classifiers[j]).setSeed(random.nextInt());
        }
                
        // build the classifier
        m_Classifiers[j].buildClassifier(bagData);*/
        /** End change */
    }

    // calc OOB error?
    if (getCalcOutOfBag()) {
        double outOfBagCount = 0.0;
        double errorSum = 0.0;
        boolean numeric = data.classAttribute().isNumeric();

        for (int i = 0; i < data.numInstances(); i++) {
            double vote;
            double[] votes;
            if (numeric)
                votes = new double[1];
            else
                votes = new double[data.numClasses()];

            // determine predictions for instance
            int voteCount = 0;
            for (int j = 0; j < m_Classifiers.length; j++) {
                if (inBag[j][i])
                    continue;

                voteCount++;
                // double pred = m_Classifiers[j].classifyInstance(data.instance(i));
                if (numeric) {
                    // votes[0] += pred;
                    votes[0] += m_Classifiers[j].classifyInstance(data.instance(i));
                } else {
                    // votes[(int) pred]++;
                    double[] newProbs = m_Classifiers[j].distributionForInstance(data.instance(i));
                    // average the probability estimates
                    for (int k = 0; k < newProbs.length; k++) {
                        votes[k] += newProbs[k];
                    }
                }
            }

            // "vote"
            if (numeric) {
                vote = votes[0];
                if (voteCount > 0) {
                    vote /= voteCount; // average
                }
            } else {
                if (Utils.eq(Utils.sum(votes), 0)) {
                } else {
                    Utils.normalize(votes);
                }
                vote = Utils.maxIndex(votes); // predicted class
            }

            // error for instance
            outOfBagCount += data.instance(i).weight();
            if (numeric) {
                errorSum += StrictMath.abs(vote - data.instance(i).classValue()) * data.instance(i).weight();
            } else {
                if (vote != data.instance(i).classValue())
                    errorSum += data.instance(i).weight();
            }
        }

        m_OutOfBagError = errorSum / outOfBagCount;
    } else {
        m_OutOfBagError = 0;
    }
}

---

From source file:com.reactivetechnologies.analytics.core.eval.StackingWithBuiltClassifiers.java

License:Open Source License

/**
 * Buildclassifier selects a classifier from the set of classifiers
 * by minimising error on the training data.
 *
 * @param data the training data to be used for generating the
 * boosted classifier./*from   ww  w  .j av  a  2  s  .c  o  m*/
 * @throws Exception if the classifier could not be built successfully
 */
@Override
public void buildClassifier(Instances data) throws Exception {

    if (m_MetaClassifier == null) {
        throw new IllegalArgumentException("No meta classifier has been set");
    }

    // can classifier handle the data?
    getCapabilities().testWithFail(data);

    // remove instances with missing class
    Instances newData = new Instances(data);
    m_BaseFormat = new Instances(data, 0);
    newData.deleteWithMissingClass();

    Random random = new Random(m_Seed);
    newData.randomize(random);
    if (newData.classAttribute().isNominal()) {
        newData.stratify(m_NumFolds);
    }

    // Create meta level
    generateMetaLevel(newData, random);

    /** Changed here */
    // DO NOT Rebuilt all the base classifiers on the full training data
    /*for (int i = 0; i < m_Classifiers.length; i++) {
      getClassifier(i).buildClassifier(newData);
    }*/
    /** End change */
}

---

From source file:com.reactivetechnologies.analytics.core.eval.VotingWithBuiltClassifiers.java

License:Open Source License

/**
 * Buildclassifier selects a classifier from the set of classifiers
 * by minimising error on the training data.
 *
 * @param data the training data to be used for generating the
 * boosted classifier.//from   w  w  w  .  j  a  v  a  2s .c o m
 * @throws Exception if the classifier could not be built successfully
 */
@Override
public void buildClassifier(Instances data) throws Exception {

    // can classifier handle the data?
    getCapabilities().testWithFail(data);

    // remove instances with missing class
    Instances newData = new Instances(data);
    newData.deleteWithMissingClass();

    m_Random = new Random(getSeed());

    /** Changed here */
    /*for (int i = 0; i < m_Classifiers.length; i++) {
      getClassifier(i).buildClassifier(newData);
    }*/
    /** End change */
}

---

From source file:com.reactivetechnologies.analytics.core.IncrementalClassifierBean.java

License:Open Source License

/**
 * Builds an intermediary classifier based on training data available
 * @throws Exception// w  w w .j ava 2 s  .  c o  m
 */
private synchronized void updateClassifier() throws Exception {
    Set<Entry<Integer, Dataset>> entries = hzService.instanceEntrySet();
    if (!entries.isEmpty()) {
        Instances data = null;
        for (Entry<Integer, Dataset> entry : entries) {
            data = new Instances(getAsInstances(entry.getValue()));

        }
        buildClassifier(data);
        hzService.clearInstanceMap();

        log.info("[updateClassifier] Incremental classifier build complete");
    }
    instanceCount.compareAndSet(instanceBatchSize, 0);
}

---

From source file:com.sliit.views.DataVisualizerPanel.java

void getScatterPlot() {
    try {//from   w w w  . j  a  v  a2  s . com
        Reader r = new BufferedReader(new FileReader(datasetPathText.getText()));
        Instances inst = new Instances(r);
        final ScatterPlotMatrix scatterPlotMatrix = new ScatterPlotMatrix();
        scatterPlotMatrix.setInstances(inst);

        scatterplotpanel.removeAll();
        scatterplotpanel.add(scatterPlotMatrix, "scatterplotpanel", 0);
        scatterplotpanel.revalidate();

    } catch (Exception ex) {
        ex.printStackTrace();
        System.err.println(ex.getMessage());
    }
}

---

From source file:com.sliit.views.DataVisualizerPanel.java

void getRocCurve() {
    try {/*from www  .ja v  a2 s.com*/
        Instances data;
        data = new Instances(new BufferedReader(new FileReader(datasetPathText.getText())));
        data.setClassIndex(data.numAttributes() - 1);

        // train classifier
        Classifier cl = new NaiveBayes();
        Evaluation eval = new Evaluation(data);
        eval.crossValidateModel(cl, data, 10, new Random(1));

        // generate curve
        ThresholdCurve tc = new ThresholdCurve();
        int classIndex = 0;
        Instances result = tc.getCurve(eval.predictions(), classIndex);

        // plot curve
        ThresholdVisualizePanel vmc = new ThresholdVisualizePanel();
        vmc.setROCString("(Area under ROC = " + Utils.doubleToString(tc.getROCArea(result), 4) + ")");
        vmc.setName(result.relationName());
        PlotData2D tempd = new PlotData2D(result);
        tempd.setPlotName(result.relationName());
        tempd.addInstanceNumberAttribute();
        // specify which points are connected
        boolean[] cp = new boolean[result.numInstances()];
        for (int n = 1; n < cp.length; n++) {
            cp[n] = true;
        }
        tempd.setConnectPoints(cp);
        // add plot
        vmc.addPlot(tempd);

        // display curve
        String plotName = vmc.getName();
        final javax.swing.JFrame jf = new javax.swing.JFrame("Weka Classifier Visualize: " + plotName);
        jf.setSize(500, 400);
        jf.getContentPane().setLayout(new BorderLayout());
        jf.getContentPane().add(vmc, BorderLayout.CENTER);
        jf.addWindowListener(new java.awt.event.WindowAdapter() {
            public void windowClosing(java.awt.event.WindowEvent e) {
                jf.dispose();
            }
        });
        jf.setVisible(true);
    } catch (IOException ex) {
        Logger.getLogger(DataVisualizerPanel.class.getName()).log(Level.SEVERE, null, ex);
    } catch (Exception ex) {
        Logger.getLogger(DataVisualizerPanel.class.getName()).log(Level.SEVERE, null, ex);
    }
}

---

From source file:com.sliit.views.KNNView.java

void getRocCurve() {
    try {/*from   w  ww  .  j av a2s . com*/
        Instances data;
        data = new Instances(new BufferedReader(new java.io.FileReader(PredictorPanel.modalText.getText())));
        data.setClassIndex(data.numAttributes() - 1);

        // train classifier
        Classifier cl = new NaiveBayes();
        Evaluation eval = new Evaluation(data);
        eval.crossValidateModel(cl, data, 10, new Random(1));

        // generate curve
        ThresholdCurve tc = new ThresholdCurve();
        int classIndex = 0;
        Instances result = tc.getCurve(eval.predictions(), classIndex);

        // plot curve
        ThresholdVisualizePanel vmc = new ThresholdVisualizePanel();
        vmc.setROCString("(Area under ROC = " + Utils.doubleToString(tc.getROCArea(result), 4) + ")");
        vmc.setName(result.relationName());
        PlotData2D tempd = new PlotData2D(result);
        tempd.setPlotName(result.relationName());
        tempd.addInstanceNumberAttribute();
        // specify which points are connected
        boolean[] cp = new boolean[result.numInstances()];
        for (int n = 1; n < cp.length; n++) {
            cp[n] = true;
        }
        tempd.setConnectPoints(cp);
        // add plot
        vmc.addPlot(tempd);

        rocPanel.removeAll();
        rocPanel.add(vmc, "vmc", 0);
        rocPanel.revalidate();

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

---

From source file:com.sliit.views.SVMView.java

/**
 * draw ROC curve//from  w  w  w . ja v a2s .c o  m
 */
void getRocCurve() {
    try {
        Instances data;
        data = new Instances(new BufferedReader(new FileReader(PredictorPanel.modalText.getText())));
        data.setClassIndex(data.numAttributes() - 1);

        //train classifier
        Classifier cl = new NaiveBayes();
        Evaluation eval = new Evaluation(data);
        eval.crossValidateModel(cl, data, 10, new Random(1));

        // generate curve
        ThresholdCurve tc = new ThresholdCurve();
        int classIndex = 0;
        Instances result = tc.getCurve(eval.predictions(), classIndex);

        // plot curve
        ThresholdVisualizePanel vmc = new ThresholdVisualizePanel();
        vmc.setROCString("(Area under ROC = " + Utils.doubleToString(tc.getROCArea(result), 4) + ")");
        vmc.setName(result.relationName());
        PlotData2D tempd = new PlotData2D(result);
        tempd.setPlotName(result.relationName());
        tempd.addInstanceNumberAttribute();
        // specify which points are connected
        boolean[] cp = new boolean[result.numInstances()];
        for (int n = 1; n < cp.length; n++) {
            cp[n] = true;
        }
        tempd.setConnectPoints(cp);
        // add plot
        vmc.addPlot(tempd);

        //            rocPanel.removeAll();
        //            rocPanel.add(vmc, "vmc", 0);
        //            rocPanel.revalidate();
    } catch (IOException ex) {
        Logger.getLogger(DataVisualizerPanel.class.getName()).log(Level.SEVERE, null, ex);
    } catch (Exception ex) {
        Logger.getLogger(DataVisualizerPanel.class.getName()).log(Level.SEVERE, null, ex);
    }
}

---

• «
• 1
• 2
• 3
• 4
• 5
• 6
• 7
• 8
• 9
• 10
• 11
• 12
• 13
• 14
• 15
• 16
• 17
• 18
• 19
• 20
• 21
• 22
• 23
• 24
• »