Example usage for weka.filters.unsupervised.instance Resample Resample

Introduction

In this page you can find the example usage for weka.filters.unsupervised.instance Resample Resample.

Prototype

Resample

Source Link

Usage

From source file:com.relationalcloud.partitioning.explanation.ExplanationHandler.java

License:Open Source License

/**
 * Applies sample training to reduce the input Instances to a specified size.
 * /*w ww . j  ava 2s.co m*/
 * @param classifier_sampling_threshold
 * @param newData1
 * @return
 * @throws Exception
 */
public static Instances sampleTraining(Double classifier_sampling_threshold, Instances newData1)
        throws Exception {
    String[] options;
    Instances newData;
    if (newData1.numInstances() > classifier_sampling_threshold) {
        double percentage = (double) 100 * ((double) classifier_sampling_threshold)
                / ((double) newData1.numInstances());

        Resample r = new Resample();

        options = new String[4];
        options[0] = "-C";
        options[1] = "last";
        options[2] = "-Z";
        options[3] = "" + percentage;

        r.setOptions(options);
        r.setInputFormat(newData1);
        newData = Filter.useFilter(newData1, r);

    } else {
        newData = newData1;
    }

    return newData;
}

---

From source file:hero.unstable.util.classification.wekaData.java

public void setData(String dataPath, double percentageClaseControl, int classIdx) {
    // Load data/*from  w ww. j  a va2 s  .  c om*/
    //Instances data = IO.csvToInstances(dataPath);
    ConverterUtils.DataSource source = null;
    try {
        source = new ConverterUtils.DataSource(dataPath);
        dataOriginal = source.getDataSet();
    } catch (Exception ex) {
        logger.info(ClusteringBinaryPD.class.getName());
        ex.printStackTrace();
    }

    // Set first column as CLASS
    dataOriginal.setClassIndex(classIdx);
    //logger.info("Data correctly loaded from " + dataPath);
    //logger.info("Data filtered: Class is the FIRST column");
    //logger.info("Number of attributes: " + data.numAttributes() );
    //logger.info("Number of instances: " + data.numInstances() );
    // Get TRAINING and TEST sets:
    Resample splitter = new Resample();
    try {
        splitter.setInvertSelection(false);
        splitter.setNoReplacement(true);
        splitter.setSampleSizePercent(percentageClaseControl);
        splitter.setInputFormat(dataOriginal);
        dataTraining = Filter.useFilter(dataOriginal, splitter);

        splitter = new Resample();
        splitter.setInvertSelection(true);
        splitter.setNoReplacement(true);
        splitter.setSampleSizePercent(percentageClaseControl);
        splitter.setInputFormat(dataOriginal);
        dataTest = Filter.useFilter(dataOriginal, splitter);
    } catch (Exception ex) {
        Logger.getLogger(ClusteringBinaryPD.class.getName()).log(Level.SEVERE, null, ex);
    }
}

---

From source file:lu.lippmann.cdb.lab.beta.shih.Shih2010.java

License:Open Source License

public Shih2010(Instances instances, boolean ignoreClass, boolean needsToResample, double theta) {
    try {/*from   w w w.j av  a2  s  .  com*/
        this.instances = instances;
        this.theta = theta;
        this.resample = needsToResample;
        if (needsToResample) {
            final Resample rs = new Resample();
            if (this.instances.numInstances() > MAX_INSTANCES_TAKEN) {
                rs.setInputFormat(instances);
                rs.setSampleSizePercent(MAX_INSTANCES_TAKEN * 100.0 / this.instances.numInstances());
                this.instances = Filter.useFilter(instances, rs);
            }
        }

        //System.out.println("Size = " + this.instances.numInstances());

        this.mapDomain = new HashMap<Integer, Set<String>>();

        if (ignoreClass) {
            this.instances.setClassIndex(-1);
        }

        //Save index of nominal & categorial attributes
        //Build a map i-DOM -> Attribute index
        this.idxsC = new ArrayList<Integer>();
        this.idxsN = new ArrayList<Integer>();
        int nn = 0;

        for (int i = 0; i < instances.numAttributes(); i++) {
            if (!instances.attribute(i).isNumeric())
                mapDomain.put(i, new HashSet<String>());
        }

        //Create map index & domain
        this.mapIndex = new HashMap<Integer, Map<String, Integer>>();
        int mapIdx = 0;
        for (int i = 0; i < instances.numAttributes(); i++) {
            Attribute attribute = instances.attribute(i);
            if (!attribute.isNumeric()) {
                idxsC.add(i); //i-th attribute is nominal
                final Map<String, Integer> mapIndexAttribute = new HashMap<String, Integer>();
                mapIndex.put(i, mapIndexAttribute);
                Enumeration<?> en = attribute.enumerateValues();
                while (en.hasMoreElements()) {
                    String catVal = en.nextElement().toString();
                    boolean created = mapDomain.get(i).add(catVal);
                    if (created) {
                        mapIndexAttribute.put(catVal, mapIdx++);
                    }
                }
                nn += mapDomain.get(i).size(); //count total nominal values
            } else {
                idxsN.add(i);
            }
        }

        this.n = nn;
        this.base = new ArrayList<TupleSI>();
        this.noBase = new ArrayList<TupleSI>();
        this.M = new int[n][n];
        this.D = new double[n][n];
        this.F = new HashMap<TupleSI, Double>();
        this.computeBase();
        this.computeMatrixMDF();
    } catch (Exception e) {
        e.printStackTrace();
    }

}

---