Example usage for weka.filters.supervised.instance SMOTE SMOTE

Introduction

In this page you can find the example usage for weka.filters.supervised.instance SMOTE SMOTE.

Prototype

SMOTE

Source Link

Usage

From source file:gyc.SMOTEBagging.java

License:Open Source License

/**
 * /*from   ww  w  .j a  v  a2 s .c om*/
 * 100%majminSMOTE (k, a).
 * @param data
 * @param i
 * @return
 */
protected Instances randomSampling(Instances copia, int majC, int minC, int a, Random simplingRandom) {
    int[] majExamples = new int[copia.numInstances()];
    int[] minExamples = new int[copia.numInstances()];
    int majCount = 0, minCount = 0;
    // First, we copy the examples from the minority class and save the indexes of the majority
    // resample min at rate (Nmaj/Nmin)*a%
    int size = copia.attributeStats(copia.classIndex()).nominalCounts[majC] * a / 100;
    // class name
    String majClassName = copia.attribute(copia.classIndex()).value(majC);

    for (int i = 0; i < copia.numInstances(); i++) {
        if (copia.instance(i).stringValue(copia.classIndex()).equalsIgnoreCase(majClassName)) {
            // save index
            majExamples[majCount] = i;
            majCount++;
        } else {
            minExamples[minCount] = i;
            minCount++;
        }
    }

    /* random undersampling of the majority */
    Instances myDataset = new Instances(copia, 0);
    int r;
    //100%majC
    for (int i = 0; i < majCount; i++) {
        myDataset.add(copia.instance(majExamples[i]));
    }
    if (minCount == 0)
        return myDataset;
    //(Nmaj/Nmin)*a% minC
    for (int i = 0; i < size; i++) {
        r = simplingRandom.nextInt(minCount);
        myDataset.add(copia.instance(minExamples[r]));
    }
    myDataset.randomize(simplingRandom);

    if (size == 1) {
        try {
            //neighbor
            Resample filter = new Resample();
            filter.setInputFormat(myDataset);
            filter.setBiasToUniformClass(1.0);
            filter.setRandomSeed(simplingRandom.nextInt());
            myDataset = Filter.useFilter(myDataset, filter);
        } catch (Exception e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        }
    }
    if (size > 1) {
        try {
            SMOTE filter = new SMOTE();
            filter.setInputFormat(myDataset); // filter capabilities are checked here
            //data.
            double value = 100.0 * majCount / size - 100;
            //Percentage
            filter.setPercentage(value);
            //if (nMin<5) filter.setNearestNeighbors(nMin);
            filter.setRandomSeed(simplingRandom.nextInt());
            //filterSMOTESMOTE
            myDataset = Filter.useFilter(myDataset, filter);
            //t.stop();
        } catch (Exception e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        }
    }

    return myDataset;
}

---