Examples with structures._SparseFeature structures._SparseFeature used on opensource projects

Example 56 with structures._SparseFeature

use of structures._SparseFeature in project IR_Base by Linda-sunshine.

the class ACCTM_C_test method generateLanguageModel.

protected void generateLanguageModel() {
    double totalWord = 0;
    for (_Doc d : m_corpus.getCollection()) {
        if (d instanceof _ParentDoc)
            continue;
        _SparseFeature[] fv = d.getSparse();
        for (int i = 0; i < fv.length; i++) {
            int wid = fv[i].getIndex();
            double val = fv[i].getValue();
            totalWord += val;
            if (m_wordSstat.containsKey(wid)) {
                double oldVal = m_wordSstat.get(wid);
                m_wordSstat.put(wid, oldVal + val);
            } else {
                m_wordSstat.put(wid, val);
            }
        }
    }
    for (int wid : m_wordSstat.keySet()) {
        double val = m_wordSstat.get(wid);
        double prob = val / totalWord;
        m_wordSstat.put(wid, prob);
    }
}

Example 57 with structures._SparseFeature

use of structures._SparseFeature in project IR_Base by Linda-sunshine.

the class ACCTM_C_test method printParentPhi.

protected void printParentPhi(_Doc d, File phiFolder) {
    _ParentDoc pDoc = (_ParentDoc) d;
    String parentPhiFileName = pDoc.getName() + ".txt";
    _SparseFeature[] fv = pDoc.getSparse();
    try {
        PrintWriter parentPW = new PrintWriter(new File(phiFolder, parentPhiFileName));
        for (int n = 0; n < fv.length; n++) {
            int index = fv[n].getIndex();
            String featureName = m_corpus.getFeature(index);
            parentPW.print(featureName + ":\t");
            for (int k = 0; k < number_of_topics; k++) parentPW.print(pDoc.m_phi[n][k] + "\t");
            parentPW.println();
        }
        parentPW.flush();
        parentPW.close();
    } catch (Exception ex) {
        ex.printStackTrace();
    }
}

Example 58 with structures._SparseFeature

use of structures._SparseFeature in project IR_Base by Linda-sunshine.

the class AspectAnalyzer method collectStats.

void collectStats(_Doc d) {
    int aspectID, wordID;
    for (_Stn s : d.getSentences()) {
        if ((aspectID = s.getTopic()) > -1) {
            // if it is annotated
            for (_SparseFeature f : s.getFv()) {
                wordID = f.getIndex();
                m_featureStat.get(m_featureNames.get(wordID)).addOneDF(aspectID);
            }
            m_aspectDist[aspectID]++;
        }
    }
}

Example 59 with structures._SparseFeature

use of structures._SparseFeature in project IR_Base by Linda-sunshine.

the class IndividualSVM method createLibLinearFV.

public Feature[] createLibLinearFV(_Review r, int userIndex) {
    int fIndex;
    double fValue;
    _SparseFeature fv;
    _SparseFeature[] fvs = r.getSparse();
    Feature[] node;
    if (m_bias)
        node = new Feature[fvs.length + 1];
    else
        node = new Feature[fvs.length];
    for (int i = 0; i < fvs.length; i++) {
        fv = fvs[i];
        // liblinear's feature index starts from one
        fIndex = fv.getIndex() + 1;
        fValue = fv.getValue();
        // Construct the user part of the training instance.
        node[i] = new FeatureNode(fIndex, fValue);
    }
    if (// add the bias term
    m_bias)
        // user model's bias
        node[fvs.length] = new FeatureNode(m_featureSize + 1, 1.0);
    return node;
}

Example 60 with structures._SparseFeature

use of structures._SparseFeature in project IR_Base by Linda-sunshine.

the class LogisticRegression method calcFuncGradient.

// This function is used to calculate the value and gradient with the new beta.
protected double calcFuncGradient(Collection<_Doc> trainSet) {
    double gValue = 0, fValue = 0;
    double Pij = 0, logPij = 0;
    // Add the L2 regularization.
    double L2 = 0, b;
    for (int i = 0; i < m_beta.length; i++) {
        b = m_beta[i];
        m_g[i] = 2 * m_lambda * b;
        L2 += b * b;
    }
    // The computation complexity is n*classNo.
    int Yi;
    _SparseFeature[] fv;
    double weight;
    for (_Doc doc : trainSet) {
        Yi = doc.getYLabel();
        fv = doc.getSparse();
        weight = doc.getWeight();
        // compute P(Y=j|X=xi)
        calcPosterior(fv, m_cache);
        for (int j = 0; j < m_classNo; j++) {
            Pij = m_cache[j];
            logPij = Math.log(Pij);
            if (Yi == j) {
                gValue = Pij - 1.0;
                fValue += logPij * weight;
            } else
                gValue = Pij;
            // weight might be different for different documents
            gValue *= weight;
            int offset = j * (m_featureSize + 1);
            m_g[offset] += gValue;
            // (Yij - Pij) * Xi
            for (_SparseFeature sf : fv) m_g[offset + sf.getIndex() + 1] += gValue * sf.getValue();
        }
    }
    // LBFGS is used to calculate the minimum value while we are trying to calculate the maximum likelihood.
    return m_lambda * L2 - fValue;
}