Example usage for weka.core Instance numValues

Introduction

In this page you can find the example usage for weka.core Instance numValues.

Prototype

public int numValues();

Source Link

Document

Returns the number of values present in a sparse representation.

Usage

From source file:pk.lums.edu.sma.processing.ml.DBSCAN.EuclideanDataObject.java

License:Open Source License

/**
 * Compares two DataObjects in respect to their attribute-values
 * /*from www. j  a  v  a2 s. co  m*/
 * @param dataObject
 *            The DataObject, that is compared with this.dataObject; now
 *            assumed to be of the same type and with the same structure
 * @return Returns true, if the DataObjects correspond in each value, else
 *         returns false
 */
public boolean equals(DataObject dataObject) {
    if (this == dataObject)
        return true;

    Instance firstInstance = getInstance();
    Instance secondInstance = dataObject.getInstance();
    int firstNumValues = firstInstance.numValues();
    int secondNumValues = secondInstance.numValues();
    int numAttributes = firstInstance.numAttributes();

    int firstI, secondI;
    for (int p1 = 0, p2 = 0; p1 < firstNumValues || p2 < secondNumValues;) {
        if (p1 >= firstNumValues) {
            firstI = numAttributes;
        } else {
            firstI = firstInstance.index(p1);
        }

        if (p2 >= secondNumValues) {
            secondI = numAttributes;
        } else {
            secondI = secondInstance.index(p2);
        }

        if (firstI == secondI) {
            if (firstInstance.valueSparse(p1) != secondInstance.valueSparse(p2)) {
                return false;
            }
            p1++;
            p2++;
        } else if (firstI > secondI) {
            if (0 != secondInstance.valueSparse(p2)) {
                return false;
            }
            p2++;
        } else {
            if (0 != firstInstance.valueSparse(p1)) {
                return false;
            }
            p1++;
        }
    }
    return true;
}

From source file:pk.lums.edu.sma.processing.ml.DBSCAN.EuclideanDataObject.java

License:Open Source License

/**
 * Calculates the euclidian-distance between dataObject and this.dataObject
 * //from   w w  w. j a  va  2s.  c  o m
 * @param dataObject
 *            The DataObject, that is used for distance-calculation with
 *            this.dataObject; now assumed to be of the same type and with
 *            the same structure
 * @return double-value The euclidian-distance between dataObject and
 *         this.dataObject
 */
public double distance(DataObject dataObject) {
    double dist = 0.0;

    Instance firstInstance = getInstance();
    Instance secondInstance = dataObject.getInstance();
    int firstNumValues = firstInstance.numValues();
    int secondNumValues = secondInstance.numValues();
    int numAttributes = firstInstance.numAttributes();

    int firstI, secondI;
    for (int p1 = 0, p2 = 0; p1 < firstNumValues || p2 < secondNumValues;) {
        if (p1 >= firstNumValues) {
            firstI = numAttributes;
        } else {
            firstI = firstInstance.index(p1);
        }

        if (p2 >= secondNumValues) {
            secondI = numAttributes;
        } else {
            secondI = secondInstance.index(p2);
        }

        double cDistance = 0;
        if (firstI == secondI) {
            cDistance = computeDistance(firstI, firstInstance.valueSparse(p1), secondInstance.valueSparse(p2));
            p1++;
            p2++;
        } else if (firstI > secondI) {
            cDistance = computeDistance(secondI, 0, secondInstance.valueSparse(p2));
            p2++;
        } else {
            cDistance = computeDistance(firstI, firstInstance.valueSparse(p1), 0);
            p1++;
        }
        dist += cDistance * cDistance;
    }
    return Math.sqrt(dist);
}

From source file:pk.lums.edu.sma.processing.ml.DBSCAN.ManhattanDataObject.java

License:Open Source License

/**
 * Calculates the manhattan-distance between dataObject and this.dataObject
 * //from  ww  w  .  j a  va  2s  . c o  m
 * @param dataObject
 *            The DataObject, that is used for distance-calculation with
 *            this.dataObject now assumed to be of the same type and with
 *            the same structure
 * @return double-value The manhattan-distance between dataObject and
 *         this.dataObject NaN, if the computation could not be performed
 */
public double distance(DataObject dataObject) {
    double dist = 0.0;

    Instance firstInstance = getInstance();
    Instance secondInstance = dataObject.getInstance();
    int firstNumValues = firstInstance.numValues();
    int secondNumValues = secondInstance.numValues();
    int numAttributes = firstInstance.numAttributes();

    int firstI, secondI;
    for (int p1 = 0, p2 = 0; p1 < firstNumValues || p2 < secondNumValues;) {
        if (p1 >= firstNumValues) {
            firstI = numAttributes;
        } else {
            firstI = firstInstance.index(p1);
        }

        if (p2 >= secondNumValues) {
            secondI = numAttributes;
        } else {
            secondI = secondInstance.index(p2);
        }

        double cDistance = 0;
        if (firstI == secondI) {
            cDistance = computeDistance(firstI, firstInstance.valueSparse(p1), secondInstance.valueSparse(p2));
            p1++;
            p2++;
        } else if (firstI > secondI) {
            cDistance = computeDistance(secondI, 0, secondInstance.valueSparse(p2));
            p2++;
        } else {
            cDistance = computeDistance(firstI, firstInstance.valueSparse(p1), 0);
            p1++;
        }
        dist += Math.abs(cDistance);
    }
    return dist;
}

From source file:xlong.urlclassify.others.SPegasos.java

License:Open Source License

/**
 * Updates the classifier with the given instance.
 *
 * @param instance the new training instance to include in the model 
 * @exception Exception if the instance could not be incorporated in
 * the model.//from  ww  w . ja v  a  2s .c o m
 */
public void updateClassifier(Instance instance) throws Exception {
    if (!instance.classIsMissing()) {

        double learningRate = 1.0 / (m_lambda * m_t);
        //double scale = 1.0 - learningRate * m_lambda;
        double scale = 1.0 - 1.0 / m_t;
        double y = (instance.classValue() == 0) ? -1 : 1;
        double wx = dotProd(instance, m_weights, instance.classIndex());
        double z = y * (wx + m_weights[m_weights.length - 1]);

        for (int j = 0; j < m_weights.length - 1; j++) {
            if (j != instance.classIndex()) {
                m_weights[j] *= scale;
            }
        }

        if (m_loss == LOGLOSS || (z < 1)) {
            double loss = dloss(z);
            int n1 = instance.numValues();
            for (int p1 = 0; p1 < n1; p1++) {
                int indS = instance.index(p1);
                if (indS != instance.classIndex() && !instance.isMissingSparse(p1)) {
                    double m = learningRate * loss * (instance.valueSparse(p1) * y);
                    m_weights[indS] += m;
                }
            }

            // update the bias
            m_weights[m_weights.length - 1] += learningRate * loss * y;
        }

        double norm = 0;
        for (int k = 0; k < m_weights.length - 1; k++) {
            if (k != instance.classIndex()) {
                norm += (m_weights[k] * m_weights[k]);
            }
        }

        double scale2 = Math.min(1.0, (1.0 / (m_lambda * norm)));
        if (scale2 < 1.0) {
            scale2 = Math.sqrt(scale2);
            for (int j = 0; j < m_weights.length - 1; j++) {
                if (j != instance.classIndex()) {
                    m_weights[j] *= scale2;
                }
            }
        }
        m_t++;
    }
}