Examples with structures._ParentDoc4DCM structures._ParentDoc4DCM used on opensource projects

Example 1 with structures._ParentDoc4DCM

use of structures._ParentDoc4DCM in project IR_Base by Linda-sunshine.

the class DCMLDA4AC_test method printWordTopicDistribution.

protected void printWordTopicDistribution(_Doc d, File wordTopicDistributionFolder, int k) {
    _ParentDoc4DCM pDoc = (_ParentDoc4DCM) d;
    String wordTopicDistributionFile = pDoc.getName() + ".txt";
    try {
        PrintWriter pw = new PrintWriter(new File(wordTopicDistributionFolder, wordTopicDistributionFile));
        for (int i = 0; i < number_of_topics; i++) {
            MyPriorityQueue<_RankItem> fVector = new MyPriorityQueue<_RankItem>(k);
            for (int v = 0; v < vocabulary_size; v++) {
                String featureName = m_corpus.getFeature(v);
                double wordProb = pDoc.m_wordTopic_prob[i][v];
                _RankItem ri = new _RankItem(featureName, wordProb);
                fVector.add(ri);
            }
            pw.format("Topic %d(%.5f):\t", i, d.m_topics[i]);
            for (_RankItem it : fVector) pw.format("%s(%.5f)\t", it.m_name, m_logSpace ? Math.exp(it.m_value) : it.m_value);
            pw.write("\n");
        }
        pw.flush();
        pw.close();
    } catch (FileNotFoundException e) {
        e.printStackTrace();
    }
}

Example 2 with structures._ParentDoc4DCM

use of structures._ParentDoc4DCM in project IR_Base by Linda-sunshine.

the class weightedCorrespondenceModel method updateZeta4Child.

public void updateZeta4Child(_ParentDoc4DCM pDoc) {
    double totalGamma4Parent = Utils.sumOfArray(pDoc.m_sstat);
    for (_ChildDoc cDoc : pDoc.m_childDocs) {
        double totalPi4Child = Utils.sumOfArray(cDoc.m_sstat);
        double gammaPiInnerProd = Utils.dotProduct(pDoc.m_sstat, cDoc.m_sstat);
        cDoc.m_zeta = gammaPiInnerProd / (totalGamma4Parent * totalPi4Child);
    }
}

Example 3 with structures._ParentDoc4DCM

use of structures._ParentDoc4DCM in project IR_Base by Linda-sunshine.

the class weightedCorrespondenceModel method gammaFuncGradientVal.

public double gammaFuncGradientVal(_ParentDoc4DCM pDoc, double[] gamma, double[] gammaGradient) {
    Arrays.fill(gammaGradient, 0);
    double funcVal = 0;
    double[] expGamma = new double[number_of_topics];
    double expGammaSum = 0;
    for (int k = 0; k < number_of_topics; k++) {
        expGamma[k] = Math.exp(gamma[k]);
        expGammaSum += expGamma[k];
    }
    funcVal -= Utils.lgamma(expGammaSum);
    double constantGradient = 0;
    for (int k = 0; k < number_of_topics; k++) {
        constantGradient += (m_alpha[k] - expGamma[k]) * Utils.trigamma(expGammaSum);
    }
    for (int k = 0; k < number_of_topics; k++) {
        gammaGradient[k] = (m_alpha[k] - expGamma[k]) * Utils.trigamma(expGamma[k]);
        funcVal += (m_alpha[k] - expGamma[k]) * (Utils.digamma(expGamma[k]) - Utils.digamma(expGammaSum));
        funcVal += Utils.lgamma(expGamma[k]);
    }
    _SparseFeature[] fvs = pDoc.getSparse();
    for (int n = 0; n < fvs.length; n++) {
        int wID = fvs[n].getIndex();
        double wVal = fvs[n].getValue();
        for (int k = 0; k < number_of_topics; k++) {
            funcVal += pDoc.m_phi[n][k] * wVal * (Utils.digamma(expGamma[k]) - Utils.digamma(expGammaSum));
            gammaGradient[k] += pDoc.m_phi[n][k] * wVal * Utils.trigamma(expGamma[k]);
            constantGradient += pDoc.m_phi[n][k] * wVal * Utils.trigamma(expGammaSum);
        // gammaGradient[k] -= pDoc.m_phi[n][k]*wVal*Utils.trigamma(expGammaSum);
        }
    }
    for (_ChildDoc cDoc : pDoc.m_childDocs) {
        double piSum = Utils.sumOfArray(cDoc.m_sstat);
        _SparseFeature[] cDocFvs = cDoc.getSparse();
        for (int n = 0; n < cDocFvs.length; n++) {
            int wID = cDocFvs[n].getIndex();
            double wVal = cDocFvs[n].getValue();
            for (int k = 0; k < number_of_topics; k++) {
                funcVal += cDoc.m_phi[n][k] * wVal * (Utils.digamma(expGamma[k]) - Utils.digamma(expGammaSum));
                funcVal -= cDoc.m_phi[n][k] * wVal * (Utils.dotProduct(cDoc.m_sstat, expGamma)) / (piSum * expGammaSum * cDoc.m_zeta);
                gammaGradient[k] += cDoc.m_phi[n][k] * wVal * Utils.trigamma(expGamma[k]);
                constantGradient += cDoc.m_phi[n][k] * wVal * Utils.trigamma(expGammaSum);
                // gammaGradient[k] -= cDoc.m_phi[n][k]*wVal*Utils.trigamma(expGammaSum);
                double temp = cDoc.m_sstat[k] * expGammaSum - Utils.dotProduct(cDoc.m_sstat, expGamma);
                gammaGradient[k] -= cDoc.m_phi[n][k] * wVal * temp / (piSum * expGammaSum * expGammaSum * cDoc.m_zeta);
            }
        }
    }
    for (int k = 0; k < number_of_topics; k++) {
        gammaGradient[k] -= constantGradient;
        gammaGradient[k] *= expGamma[k];
        gammaGradient[k] = 0 - gammaGradient[k];
    }
    return -funcVal;
}

Example 4 with structures._ParentDoc4DCM

use of structures._ParentDoc4DCM in project IR_Base by Linda-sunshine.

the class weightedCorrespondenceModel method calculate_E_step.

@Override
public double calculate_E_step(_Doc d) {
    if (d instanceof _ChildDoc)
        return 0;
    _ParentDoc4DCM pDoc = (_ParentDoc4DCM) d;
    double last = 1;
    if (m_varConverge > 0)
        last = calculate_log_likelihood(pDoc);
    double current = last, converge, logSum, wVal;
    int iter = 0, wID;
    do {
        updateEta4Parent(pDoc);
        updateGamma4Parent(pDoc);
        // updateLambda(pDoc);
        updatePi4Child(pDoc);
        updateZeta4Child(pDoc);
        updateEta4Child(pDoc);
        updateLambda(pDoc);
        if (m_varConverge > 0) {
            current = calculate_log_likelihood(pDoc);
            converge = Math.abs((current - last) / last);
            last = current;
            if (converge < m_varConverge)
                break;
        }
    } while (++iter < m_varMaxIter);
    collectStats(pDoc);
    return current;
}

Example 5 with structures._ParentDoc4DCM

use of structures._ParentDoc4DCM in project IR_Base by Linda-sunshine.

the class weightedCorrespondenceModel method updateLambda.

public void updateLambda(_ParentDoc4DCM pDoc) {
    _SparseFeature[] fvs = pDoc.getSparse();
    int totalWord = 0;
    double totalLambda = 0;
    for (int k = 0; k < number_of_topics; k++) for (int v = 0; v < vocabulary_size; v++) pDoc.m_lambda_stat[k][v] = m_beta[k][v];
    for (int n = 0; n < fvs.length; n++) {
        int wID = fvs[n].getIndex();
        double wVal = fvs[n].getValue();
        totalWord += wVal;
        double phiSum = Utils.sumOfArray(pDoc.m_phi[n]);
        if (Math.abs(phiSum - 1) > 1) {
            System.out.println("inequal to 1\t" + n + phiSum);
        }
        for (int k = 0; k < number_of_topics; k++) {
            pDoc.m_lambda_stat[k][wID] += wVal * pDoc.m_phi[n][k];
            if (Double.isNaN(pDoc.m_lambda_stat[k][wID])) {
                System.out.println("nan error article\t" + n + " " + wID);
            }
        }
    }
    for (_ChildDoc cDoc : pDoc.m_childDocs) {
        _SparseFeature[] cFvs = cDoc.getSparse();
        for (int n = 0; n < cFvs.length; n++) {
            int wID = cFvs[n].getIndex();
            double wVal = cFvs[n].getValue();
            totalWord += wVal;
            double phiSum = Utils.sumOfArray(cDoc.m_phi[n]);
            if (Math.abs(phiSum - 1) > 1) {
                System.out.println("inequal to 1\t" + n + phiSum);
                for (int k = 0; k < number_of_topics; k++) {
                    System.out.println("\t\t" + cDoc.m_phi[n][k]);
                }
            }
            for (int k = 0; k < number_of_topics; k++) {
                pDoc.m_lambda_stat[k][wID] += wVal * cDoc.m_phi[n][k];
                if (Double.isNaN(pDoc.m_lambda_stat[k][wID])) {
                    System.out.println("nan error comment\t" + n + " " + wID);
                }
            }
        }
    }
    for (int k = 0; k < number_of_topics; k++) {
        pDoc.m_lambda_topicStat[k] = Utils.sumOfArray(pDoc.m_lambda_stat[k]);
        totalLambda += pDoc.m_lambda_topicStat[k];
    }
// System.out.println("total Words in this doc\t"+pDoc.getName()+"\t"+totalWord+"\t"+totalLambda);
}