Example usage for weka.filters.supervised.attribute Discretize setUseBetterEncoding

List of usage examples for weka.filters.supervised.attribute Discretize setUseBetterEncoding

  1. HOME
  2. Java
  3. weka
  4. weka.filters.supervised.attribute.*
  5. Discretize
  6. setUseBetterEncoding

Introduction

In this page you can find the example usage for weka.filters.supervised.attribute Discretize setUseBetterEncoding.

Prototype

public void setUseBetterEncoding(boolean useBetterEncoding)

Source Link

Document

Sets whether better encoding is to be used for MDL.

Usage

From source file:GainRatioAttributeEval1.java

License:Open Source License

/**
 * Initializes a gain ratio attribute evaluator.
 * Discretizes all attributes that are numeric.
 *
 * @param data set of instances serving as training data 
 * @throws Exception if the evaluator has not been 
 * generated successfully/*from www .  j a v a2 s  .c o m*/
 */
public void buildEvaluator(Instance data) throws Exception {

    // can evaluator handle data?
    program10 program10 = new program10();
    getCapabilities().testWithFail(program10.DataTrain());

    m_trainInstances = program10.DataTrain();
    m_classIndex = m_trainInstances.classIndex();
    m_numAttribs = m_trainInstances.numAttributes();
    m_numInstances = m_trainInstances.numInstances();
    Discretize disTransform = new Discretize();
    disTransform.setUseBetterEncoding(true);
    disTransform.setInputFormat(m_trainInstances);
    m_trainInstances = Filter.useFilter(m_trainInstances, disTransform);
    m_numClasses = m_trainInstances.attribute(m_classIndex).numValues();
}

From source file:ChiSquare.ChiSquaredAttributeEval.java

License:Open Source License

/**
 * Initializes a chi-squared attribute evaluator.
 * Discretizes all attributes that are numeric.
 *
 * @param data set of instances serving as training data 
 * @throws Exception if the evaluator has not been 
 * generated successfully//w ww .j  ava 2s .  co m
 */
public void buildEvaluator(Instances data) throws Exception {

    // can evaluator handle data?
    getCapabilities().testWithFail(data);

    int classIndex = data.classIndex();
    int numInstances = data.numInstances();

    if (!m_Binarize) {
        Discretize disTransform = new Discretize();
        disTransform.setUseBetterEncoding(true);
        disTransform.setInputFormat(data);
        data = Filter.useFilter(data, disTransform);
    } else {
        NumericToBinary binTransform = new NumericToBinary();
        binTransform.setInputFormat(data);
        data = Filter.useFilter(data, binTransform);
    }
    int numClasses = data.attribute(classIndex).numValues();

    // Reserve space and initialize counters
    double[][][] counts = new double[data.numAttributes()][][];
    for (int k = 0; k < data.numAttributes(); k++) {
        if (k != classIndex) {
            int numValues = data.attribute(k).numValues();
            counts[k] = new double[numValues + 1][numClasses + 1];
        }
    }

    // Initialize counters
    double[] temp = new double[numClasses + 1];
    for (int k = 0; k < numInstances; k++) {
        Instance inst = data.instance(k);
        if (inst.classIsMissing()) {
            temp[numClasses] += inst.weight();
        } else {
            temp[(int) inst.classValue()] += inst.weight();
        }
    }
    for (int k = 0; k < counts.length; k++) {
        if (k != classIndex) {
            for (int i = 0; i < temp.length; i++) {
                counts[k][0][i] = temp[i];
            }
        }
    }

    // Get counts
    for (int k = 0; k < numInstances; k++) {
        Instance inst = data.instance(k);
        for (int i = 0; i < inst.numValues(); i++) {
            if (inst.index(i) != classIndex) {
                if (inst.isMissingSparse(i) || inst.classIsMissing()) {
                    if (!inst.isMissingSparse(i)) {
                        counts[inst.index(i)][(int) inst.valueSparse(i)][numClasses] += inst.weight();
                        counts[inst.index(i)][0][numClasses] -= inst.weight();
                    } else if (!inst.classIsMissing()) {
                        counts[inst.index(i)][data.attribute(inst.index(i)).numValues()][(int) inst
                                .classValue()] += inst.weight();
                        counts[inst.index(i)][0][(int) inst.classValue()] -= inst.weight();
                    } else {
                        counts[inst.index(i)][data.attribute(inst.index(i)).numValues()][numClasses] += inst
                                .weight();
                        counts[inst.index(i)][0][numClasses] -= inst.weight();
                    }
                } else {
                    counts[inst.index(i)][(int) inst.valueSparse(i)][(int) inst.classValue()] += inst.weight();
                    counts[inst.index(i)][0][(int) inst.classValue()] -= inst.weight();
                }
            }
        }
    }

    // distribute missing counts if required
    if (m_missing_merge) {

        for (int k = 0; k < data.numAttributes(); k++) {
            if (k != classIndex) {
                int numValues = data.attribute(k).numValues();

                // Compute marginals
                double[] rowSums = new double[numValues];
                double[] columnSums = new double[numClasses];
                double sum = 0;
                for (int i = 0; i < numValues; i++) {
                    for (int j = 0; j < numClasses; j++) {
                        rowSums[i] += counts[k][i][j];
                        columnSums[j] += counts[k][i][j];
                    }
                    sum += rowSums[i];
                }

                if (Utils.gr(sum, 0)) {
                    double[][] additions = new double[numValues][numClasses];

                    // Compute what needs to be added to each row
                    for (int i = 0; i < numValues; i++) {
                        for (int j = 0; j < numClasses; j++) {
                            additions[i][j] = (rowSums[i] / sum) * counts[k][numValues][j];
                        }
                    }

                    // Compute what needs to be added to each column
                    for (int i = 0; i < numClasses; i++) {
                        for (int j = 0; j < numValues; j++) {
                            additions[j][i] += (columnSums[i] / sum) * counts[k][j][numClasses];
                        }
                    }

                    // Compute what needs to be added to each cell
                    for (int i = 0; i < numClasses; i++) {
                        for (int j = 0; j < numValues; j++) {
                            additions[j][i] += (counts[k][j][i] / sum) * counts[k][numValues][numClasses];
                        }
                    }

                    // Make new contingency table
                    double[][] newTable = new double[numValues][numClasses];
                    for (int i = 0; i < numValues; i++) {
                        for (int j = 0; j < numClasses; j++) {
                            newTable[i][j] = counts[k][i][j] + additions[i][j];
                        }
                    }
                    counts[k] = newTable;
                }
            }
        }
    }

    // Compute chi-squared values
    m_ChiSquareds = new double[data.numAttributes()];
    for (int i = 0; i < data.numAttributes(); i++) {
        if (i != classIndex) {
            m_ChiSquareds[i] = ContingencyTables.chiVal(ContingencyTables.reduceMatrix(counts[i]), false);
        }
    }
}

From source file:edu.columbia.cs.ltrie.sampling.queries.generation.ChiSquaredWithYatesCorrectionAttributeEval.java

License:Open Source License

/**
 * Initializes a chi-squared attribute evaluator.
 * Discretizes all attributes that are numeric.
 *
 * @param data set of instances serving as training data 
 * @throws Exception if the evaluator has not been 
 * generated successfully//  w  w w .j  av a2s  .  co m
 */
public void buildEvaluator(Instances data) throws Exception {

    // can evaluator handle data?
    getCapabilities().testWithFail(data);

    int classIndex = data.classIndex();
    int numInstances = data.numInstances();

    if (!m_Binarize) {
        Discretize disTransform = new Discretize();
        disTransform.setUseBetterEncoding(true);
        disTransform.setInputFormat(data);
        data = Filter.useFilter(data, disTransform);
    } else {
        NumericToBinary binTransform = new NumericToBinary();
        binTransform.setInputFormat(data);
        data = Filter.useFilter(data, binTransform);
    }
    int numClasses = data.attribute(classIndex).numValues();

    // Reserve space and initialize counters
    double[][][] counts = new double[data.numAttributes()][][];
    for (int k = 0; k < data.numAttributes(); k++) {
        if (k != classIndex) {
            int numValues = data.attribute(k).numValues();
            counts[k] = new double[numValues + 1][numClasses + 1];
        }
    }

    // Initialize counters
    double[] temp = new double[numClasses + 1];
    for (int k = 0; k < numInstances; k++) {
        Instance inst = data.instance(k);
        if (inst.classIsMissing()) {
            temp[numClasses] += inst.weight();
        } else {
            temp[(int) inst.classValue()] += inst.weight();
        }
    }
    for (int k = 0; k < counts.length; k++) {
        if (k != classIndex) {
            for (int i = 0; i < temp.length; i++) {
                counts[k][0][i] = temp[i];
            }
        }
    }

    // Get counts
    for (int k = 0; k < numInstances; k++) {
        Instance inst = data.instance(k);
        for (int i = 0; i < inst.numValues(); i++) {
            if (inst.index(i) != classIndex) {
                if (inst.isMissingSparse(i) || inst.classIsMissing()) {
                    if (!inst.isMissingSparse(i)) {
                        counts[inst.index(i)][(int) inst.valueSparse(i)][numClasses] += inst.weight();
                        counts[inst.index(i)][0][numClasses] -= inst.weight();
                    } else if (!inst.classIsMissing()) {
                        counts[inst.index(i)][data.attribute(inst.index(i)).numValues()][(int) inst
                                .classValue()] += inst.weight();
                        counts[inst.index(i)][0][(int) inst.classValue()] -= inst.weight();
                    } else {
                        counts[inst.index(i)][data.attribute(inst.index(i)).numValues()][numClasses] += inst
                                .weight();
                        counts[inst.index(i)][0][numClasses] -= inst.weight();
                    }
                } else {
                    counts[inst.index(i)][(int) inst.valueSparse(i)][(int) inst.classValue()] += inst.weight();
                    counts[inst.index(i)][0][(int) inst.classValue()] -= inst.weight();
                }
            }
        }
    }

    // distribute missing counts if required
    if (m_missing_merge) {

        for (int k = 0; k < data.numAttributes(); k++) {
            if (k != classIndex) {
                int numValues = data.attribute(k).numValues();

                // Compute marginals
                double[] rowSums = new double[numValues];
                double[] columnSums = new double[numClasses];
                double sum = 0;
                for (int i = 0; i < numValues; i++) {
                    for (int j = 0; j < numClasses; j++) {
                        rowSums[i] += counts[k][i][j];
                        columnSums[j] += counts[k][i][j];
                    }
                    sum += rowSums[i];
                }

                if (Utils.gr(sum, 0)) {
                    double[][] additions = new double[numValues][numClasses];

                    // Compute what needs to be added to each row
                    for (int i = 0; i < numValues; i++) {
                        for (int j = 0; j < numClasses; j++) {
                            additions[i][j] = (rowSums[i] / sum) * counts[k][numValues][j];
                        }
                    }

                    // Compute what needs to be added to each column
                    for (int i = 0; i < numClasses; i++) {
                        for (int j = 0; j < numValues; j++) {
                            additions[j][i] += (columnSums[i] / sum) * counts[k][j][numClasses];
                        }
                    }

                    // Compute what needs to be added to each cell
                    for (int i = 0; i < numClasses; i++) {
                        for (int j = 0; j < numValues; j++) {
                            additions[j][i] += (counts[k][j][i] / sum) * counts[k][numValues][numClasses];
                        }
                    }

                    // Make new contingency table
                    double[][] newTable = new double[numValues][numClasses];
                    for (int i = 0; i < numValues; i++) {
                        for (int j = 0; j < numClasses; j++) {
                            newTable[i][j] = counts[k][i][j] + additions[i][j];
                        }
                    }
                    counts[k] = newTable;
                }
            }
        }
    }

    // Compute chi-squared values
    m_ChiSquareds = new double[data.numAttributes()];
    for (int i = 0; i < data.numAttributes(); i++) {
        if (i != classIndex) {
            m_ChiSquareds[i] = chiVal(ContingencyTables.reduceMatrix(counts[i]));
        }
    }
}

From source file:feature.InfoGainEval.java

License:Open Source License

/**
 * Initializes an information gain attribute evaluator. Discretizes all
 * attributes that are numeric./*from   w  w  w. j a  v a2 s  .  com*/
 *
 * @param data
 *            set of instances serving as training data
 * @throws Exception
 *             if the evaluator has not been generated successfully
 */
public double computeInfoGain(Instances data, int att) throws Exception {

    // can evaluator handle data?
    getCapabilities().testWithFail(data);

    int classIndex = data.classIndex();
    int numInstances = data.numInstances();

    if (!m_Binarize) {
        Discretize disTransform = new Discretize();
        disTransform.setUseBetterEncoding(true);
        disTransform.setInputFormat(data);
        data = Filter.useFilter(data, disTransform);
    } else {
        NumericToBinary binTransform = new NumericToBinary();
        binTransform.setInputFormat(data);
        data = Filter.useFilter(data, binTransform);
    }
    int numClasses = data.attribute(classIndex).numValues();

    // Reserve space and initialize counters
    double[][][] counts = new double[data.numAttributes()][][];
    for (int k = 0; k < data.numAttributes(); k++) {
        if (k != classIndex) {
            int numValues = data.attribute(k).numValues();
            counts[k] = new double[numValues + 1][numClasses + 1];
        }
    }

    // Initialize counters
    double[] temp = new double[numClasses + 1];
    for (int k = 0; k < numInstances; k++) {
        Instance inst = data.instance(k);
        if (inst.classIsMissing()) {
            temp[numClasses] += inst.weight();
        } else {
            temp[(int) inst.classValue()] += inst.weight();
        }
    }
    for (int k = 0; k < counts.length; k++) {
        if (k != classIndex) {
            for (int i = 0; i < temp.length; i++) {
                counts[k][0][i] = temp[i];
            }
        }
    }

    // Get counts
    for (int k = 0; k < numInstances; k++) {
        Instance inst = data.instance(k);
        for (int i = 0; i < inst.numValues(); i++) {
            if (inst.index(i) != classIndex) {
                if (inst.isMissingSparse(i) || inst.classIsMissing()) {
                    if (!inst.isMissingSparse(i)) {
                        counts[inst.index(i)][(int) inst.valueSparse(i)][numClasses] += inst.weight();
                        counts[inst.index(i)][0][numClasses] -= inst.weight();
                    } else if (!inst.classIsMissing()) {
                        counts[inst.index(i)][data.attribute(inst.index(i)).numValues()][(int) inst
                                .classValue()] += inst.weight();
                        counts[inst.index(i)][0][(int) inst.classValue()] -= inst.weight();
                    } else {
                        counts[inst.index(i)][data.attribute(inst.index(i)).numValues()][numClasses] += inst
                                .weight();
                        counts[inst.index(i)][0][numClasses] -= inst.weight();
                    }
                } else {
                    counts[inst.index(i)][(int) inst.valueSparse(i)][(int) inst.classValue()] += inst.weight();
                    counts[inst.index(i)][0][(int) inst.classValue()] -= inst.weight();
                }
            }
        }
    }

    // distribute missing counts if required
    if (m_missing_merge) {

        for (int k = 0; k < data.numAttributes(); k++) {
            if (k != classIndex) {
                int numValues = data.attribute(k).numValues();

                // Compute marginals
                double[] rowSums = new double[numValues];
                double[] columnSums = new double[numClasses];
                double sum = 0;
                for (int i = 0; i < numValues; i++) {
                    for (int j = 0; j < numClasses; j++) {
                        rowSums[i] += counts[k][i][j];
                        columnSums[j] += counts[k][i][j];
                    }
                    sum += rowSums[i];
                }

                if (Utils.gr(sum, 0)) {
                    double[][] additions = new double[numValues][numClasses];

                    // Compute what needs to be added to each row
                    for (int i = 0; i < numValues; i++) {
                        for (int j = 0; j < numClasses; j++) {
                            additions[i][j] = (rowSums[i] / sum) * counts[k][numValues][j];
                        }
                    }

                    // Compute what needs to be added to each column
                    for (int i = 0; i < numClasses; i++) {
                        for (int j = 0; j < numValues; j++) {
                            additions[j][i] += (columnSums[i] / sum) * counts[k][j][numClasses];
                        }
                    }

                    // Compute what needs to be added to each cell
                    for (int i = 0; i < numClasses; i++) {
                        for (int j = 0; j < numValues; j++) {
                            additions[j][i] += (counts[k][j][i] / sum) * counts[k][numValues][numClasses];
                        }
                    }

                    // Make new contingency table
                    double[][] newTable = new double[numValues][numClasses];
                    for (int i = 0; i < numValues; i++) {
                        for (int j = 0; j < numClasses; j++) {
                            newTable[i][j] = counts[k][i][j] + additions[i][j];
                        }
                    }
                    counts[k] = newTable;
                }
            }
        }
    }

    // Compute info gains
    m_InfoGains = new double[data.numAttributes()];
    m_InfoGains[att] = (ContingencyTables.entropyOverColumns(counts[att])
            - ContingencyTables.entropyConditionedOnRows(counts[att]));

    return m_InfoGains[att];
}

From source file:feature.InfoGainEval.java

License:Open Source License

public void buildEvaluator(Instances data) throws Exception {

    // can evaluator handle data?
    getCapabilities().testWithFail(data);

    int classIndex = data.classIndex();
    int numInstances = data.numInstances();

    if (!m_Binarize) {
        Discretize disTransform = new Discretize();
        disTransform.setUseBetterEncoding(true);
        disTransform.setInputFormat(data);
        data = Filter.useFilter(data, disTransform);
    } else {/*from   w  ww  . ja  va 2 s .  c  o  m*/
        NumericToBinary binTransform = new NumericToBinary();
        binTransform.setInputFormat(data);
        data = Filter.useFilter(data, binTransform);
    }
    int numClasses = data.attribute(classIndex).numValues();

    // Reserve space and initialize counters
    double[][][] counts = new double[data.numAttributes()][][];
    for (int k = 0; k < data.numAttributes(); k++) {
        if (k != classIndex) {
            int numValues = data.attribute(k).numValues();
            counts[k] = new double[numValues + 1][numClasses + 1];
        }
    }

    // Initialize counters
    double[] temp = new double[numClasses + 1];
    for (int k = 0; k < numInstances; k++) {
        Instance inst = data.instance(k);
        if (inst.classIsMissing()) {
            temp[numClasses] += inst.weight();
        } else {
            temp[(int) inst.classValue()] += inst.weight();
        }
    }
    for (int k = 0; k < counts.length; k++) {
        if (k != classIndex) {
            for (int i = 0; i < temp.length; i++) {
                counts[k][0][i] = temp[i];
            }
        }
    }

    // Get counts
    for (int k = 0; k < numInstances; k++) {
        Instance inst = data.instance(k);
        for (int i = 0; i < inst.numValues(); i++) {
            if (inst.index(i) != classIndex) {
                if (inst.isMissingSparse(i) || inst.classIsMissing()) {
                    if (!inst.isMissingSparse(i)) {
                        counts[inst.index(i)][(int) inst.valueSparse(i)][numClasses] += inst.weight();
                        counts[inst.index(i)][0][numClasses] -= inst.weight();
                    } else if (!inst.classIsMissing()) {
                        counts[inst.index(i)][data.attribute(inst.index(i)).numValues()][(int) inst
                                .classValue()] += inst.weight();
                        counts[inst.index(i)][0][(int) inst.classValue()] -= inst.weight();
                    } else {
                        counts[inst.index(i)][data.attribute(inst.index(i)).numValues()][numClasses] += inst
                                .weight();
                        counts[inst.index(i)][0][numClasses] -= inst.weight();
                    }
                } else {
                    counts[inst.index(i)][(int) inst.valueSparse(i)][(int) inst.classValue()] += inst.weight();
                    counts[inst.index(i)][0][(int) inst.classValue()] -= inst.weight();
                }
            }
        }
    }

    // distribute missing counts if required
    if (m_missing_merge) {

        for (int k = 0; k < data.numAttributes(); k++) {
            if (k != classIndex) {
                int numValues = data.attribute(k).numValues();

                // Compute marginals
                double[] rowSums = new double[numValues];
                double[] columnSums = new double[numClasses];
                double sum = 0;
                for (int i = 0; i < numValues; i++) {
                    for (int j = 0; j < numClasses; j++) {
                        rowSums[i] += counts[k][i][j];
                        columnSums[j] += counts[k][i][j];
                    }
                    sum += rowSums[i];
                }

                if (Utils.gr(sum, 0)) {
                    double[][] additions = new double[numValues][numClasses];

                    // Compute what needs to be added to each row
                    for (int i = 0; i < numValues; i++) {
                        for (int j = 0; j < numClasses; j++) {
                            additions[i][j] = (rowSums[i] / sum) * counts[k][numValues][j];
                        }
                    }

                    // Compute what needs to be added to each column
                    for (int i = 0; i < numClasses; i++) {
                        for (int j = 0; j < numValues; j++) {
                            additions[j][i] += (columnSums[i] / sum) * counts[k][j][numClasses];
                        }
                    }

                    // Compute what needs to be added to each cell
                    for (int i = 0; i < numClasses; i++) {
                        for (int j = 0; j < numValues; j++) {
                            additions[j][i] += (counts[k][j][i] / sum) * counts[k][numValues][numClasses];
                        }
                    }

                    // Make new contingency table
                    double[][] newTable = new double[numValues][numClasses];
                    for (int i = 0; i < numValues; i++) {
                        for (int j = 0; j < numClasses; j++) {
                            newTable[i][j] = counts[k][i][j] + additions[i][j];
                        }
                    }
                    counts[k] = newTable;
                }
            }
        }
    }

    // Compute info gains
    m_InfoGains = new double[data.numAttributes()];
    for (int i = 0; i < data.numAttributes(); i++) {
        if (i != classIndex) {
            m_InfoGains[i] = (ContingencyTables.entropyOverColumns(counts[i])
                    - ContingencyTables.entropyConditionedOnRows(counts[i]));
        }
    }
}