Example usage for weka.estimators NormalEstimator NormalEstimator

Introduction

In this page you can find the example usage for weka.estimators NormalEstimator NormalEstimator.

Prototype

public NormalEstimator(double precision) 

Source Link

Document

Constructor that takes a precision argument.

Usage

From source file:cn.edu.xjtu.dbmine.source.NaiveBayes.java

License:Open Source License

/**
 * Generates the classifier.//  ww  w  .  ja  v  a  2s  .  co  m
 *
 * @param instances set of instances serving as training data 
 * @exception Exception if the classifier has not been generated 
 * successfully
 */
public void buildClassifier(Instances instances) throws Exception {

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

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

    m_NumClasses = instances.numClasses();

    // Copy the instances
    m_Instances = new Instances(instances);

    // Discretize instances if required
    if (m_UseDiscretization) {
        m_Disc = new weka.filters.supervised.attribute.Discretize();
        m_Disc.setInputFormat(m_Instances);
        m_Instances = weka.filters.Filter.useFilter(m_Instances, m_Disc);
    } else {
        m_Disc = null;
    }

    // Reserve space for the distributions
    m_Distributions = new Estimator[m_Instances.numAttributes() - 1][m_Instances.numClasses()];
    m_ClassDistribution = new DiscreteEstimator(m_Instances.numClasses(), true);
    int attIndex = 0;
    Enumeration enu = m_Instances.enumerateAttributes();
    while (enu.hasMoreElements()) {
        Attribute attribute = (Attribute) enu.nextElement();

        // If the attribute is numeric, determine the estimator 
        // numeric precision from differences between adjacent values
        double numPrecision = DEFAULT_NUM_PRECISION;
        if (attribute.type() == Attribute.NUMERIC) {
            m_Instances.sort(attribute);
            if ((m_Instances.numInstances() > 0) && !m_Instances.instance(0).isMissing(attribute)) {
                double lastVal = m_Instances.instance(0).value(attribute);
                double currentVal, deltaSum = 0;
                int distinct = 0;
                for (int i = 1; i < m_Instances.numInstances(); i++) {
                    Instance currentInst = m_Instances.instance(i);
                    if (currentInst.isMissing(attribute)) {
                        break;
                    }
                    currentVal = currentInst.value(attribute);
                    if (currentVal != lastVal) {
                        deltaSum += currentVal - lastVal;
                        lastVal = currentVal;
                        distinct++;
                    }
                }
                if (distinct > 0) {
                    numPrecision = deltaSum / distinct;
                }
            }
        }

        for (int j = 0; j < m_Instances.numClasses(); j++) {
            switch (attribute.type()) {
            case Attribute.NUMERIC:
                if (m_UseKernelEstimator) {
                    m_Distributions[attIndex][j] = new KernelEstimator(numPrecision);
                } else {
                    m_Distributions[attIndex][j] = new NormalEstimator(numPrecision);
                }
                break;
            case Attribute.NOMINAL:
                m_Distributions[attIndex][j] = new DiscreteEstimator(attribute.numValues(), true);
                break;
            default:
                throw new Exception("Attribute type unknown to NaiveBayes");
            }
        }
        attIndex++;
    }

    // Compute counts
    Enumeration enumInsts = m_Instances.enumerateInstances();
    while (enumInsts.hasMoreElements()) {
        Instance instance = (Instance) enumInsts.nextElement();
        updateClassifier(instance);
    }

    // Save space
    m_Instances = new Instances(m_Instances, 0);
}

---

From source file:main.NaiveBayes.java

License:Open Source License

/**
 * Generates the classifier.//from  ww w .j  av a 2s.  c  o  m
 * 
 * @param instances set of instances serving as training data
 * @exception Exception if the classifier has not been generated successfully
 */
@Override
public void buildClassifier(Instances instances) throws Exception {

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

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

    m_NumClasses = instances.numClasses();

    // Copy the instances
    m_Instances = new Instances(instances);

    // Discretize instances if required
    if (m_UseDiscretization) {
        m_Disc = new weka.filters.supervised.attribute.Discretize();
        m_Disc.setInputFormat(m_Instances);
        m_Instances = weka.filters.Filter.useFilter(m_Instances, m_Disc);
    } else {
        m_Disc = null;
    }

    // Reserve space for the distributions
    m_Distributions = new Estimator[m_Instances.numAttributes() - 1][m_Instances.numClasses()];
    m_ClassDistribution = new DiscreteEstimator(m_Instances.numClasses(), true);
    int attIndex = 0;
    Enumeration<Attribute> enu = m_Instances.enumerateAttributes();
    while (enu.hasMoreElements()) {
        Attribute attribute = enu.nextElement();

        // If the attribute is numeric, determine the estimator
        // numeric precision from differences between adjacent values
        double numPrecision = DEFAULT_NUM_PRECISION;
        if (attribute.type() == Attribute.NUMERIC) {
            m_Instances.sort(attribute);
            if ((m_Instances.numInstances() > 0) && !m_Instances.instance(0).isMissing(attribute)) {
                double lastVal = m_Instances.instance(0).value(attribute);
                double currentVal, deltaSum = 0;
                int distinct = 0;
                for (int i = 1; i < m_Instances.numInstances(); i++) {
                    Instance currentInst = m_Instances.instance(i);
                    if (currentInst.isMissing(attribute)) {
                        break;
                    }
                    currentVal = currentInst.value(attribute);
                    if (currentVal != lastVal) {
                        deltaSum += currentVal - lastVal;
                        lastVal = currentVal;
                        distinct++;
                    }
                }
                if (distinct > 0) {
                    numPrecision = deltaSum / distinct;
                }
            }
        }

        for (int j = 0; j < m_Instances.numClasses(); j++) {
            switch (attribute.type()) {
            case Attribute.NUMERIC:
                if (m_UseKernelEstimator) {
                    m_Distributions[attIndex][j] = new KernelEstimator(numPrecision);
                } else {
                    m_Distributions[attIndex][j] = new NormalEstimator(numPrecision);
                }
                break;
            case Attribute.NOMINAL:
                m_Distributions[attIndex][j] = new DiscreteEstimator(attribute.numValues(), true);
                break;
            default:
                throw new Exception("Attribute type unknown to NaiveBayes");
            }
        }
        attIndex++;
    }

    // Compute counts
    Enumeration<Instance> enumInsts = m_Instances.enumerateInstances();
    while (enumInsts.hasMoreElements()) {
        Instance instance = enumInsts.nextElement();
        updateClassifier(instance);
    }

    // Save space
    m_Instances = new Instances(m_Instances, 0);
}

---