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

Example 16 with structures._ParentDoc

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

the class corrLDA_Gibbs method childTopicInDocProb.

protected double childTopicInDocProb(int tid, _ChildDoc d) {
    _ParentDoc pDoc = (_ParentDoc) (d.m_parentDoc);
    double pDocTopicSum = Utils.sumOfArray(pDoc.m_sstat);
    double term = (pDoc.m_sstat[tid] + m_smoothingParam) / (pDocTopicSum + m_smoothingParam * number_of_topics);
    return term;
}

Example 17 with structures._ParentDoc

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

the class corrLDA_Gibbs method initialize_probability.

@Override
protected void initialize_probability(Collection<_Doc> collection) {
    createSpace();
    for (int i = 0; i < number_of_topics; i++) Arrays.fill(word_topic_sstat[i], d_beta);
    Arrays.fill(m_sstat, d_beta * vocabulary_size);
    for (_Doc d : collection) {
        if (d instanceof _ParentDoc) {
            for (_Stn stnObj : d.getSentences()) {
                stnObj.setTopicsVct(number_of_topics);
            }
            d.setTopics4Gibbs(number_of_topics, 0);
        } else if (d instanceof _ChildDoc) {
            ((_ChildDoc) d).setTopics4Gibbs_LDA(number_of_topics, 0);
        }
        for (_Word w : d.getWords()) {
            word_topic_sstat[w.getTopic()][w.getIndex()]++;
            m_sstat[w.getTopic()]++;
        }
    }
    imposePrior();
    m_statisticsNormalized = false;
}

Example 18 with structures._ParentDoc

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

the class corrLDA_Gibbs method calculate_log_likelihood4Parent.

protected double calculate_log_likelihood4Parent(_Doc d) {
    _ParentDoc pDoc = (_ParentDoc) d;
    double docLogLikelihood = 0;
    _SparseFeature[] fv = pDoc.getSparse();
    double docTopicSum = Utils.sumOfArray(pDoc.m_sstat);
    double alphaSum = d_alpha * number_of_topics;
    for (int j = 0; j < fv.length; j++) {
        int wid = fv[j].getIndex();
        double value = fv[j].getValue();
        double wordLogLikelihood = 0;
        for (int k = 0; k < number_of_topics; k++) {
            double wordPerTopicLikelihood = parentWordByTopicProb(k, wid) * parentTopicInDocProb(k, pDoc) / (alphaSum + docTopicSum);
            wordLogLikelihood += wordPerTopicLikelihood;
        }
        if (Math.abs(wordLogLikelihood) < 1e-10) {
            System.out.println("wordLogLikelihood\t" + wordLogLikelihood);
            wordLogLikelihood += 1e-10;
        }
        wordLogLikelihood = Math.log(wordLogLikelihood);
        docLogLikelihood += value * wordLogLikelihood;
    }
    return docLogLikelihood;
}

Example 19 with structures._ParentDoc

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

the class corrLDA_Gibbs method initTest.

protected void initTest(ArrayList<_Doc> sampleTestSet, _Doc d) {
    _ParentDoc pDoc = (_ParentDoc) d;
    for (_Stn stnObj : pDoc.getSentences()) {
        stnObj.setTopicsVct(number_of_topics);
    }
    int testLength = (int) (m_testWord4PerplexityProportion * pDoc.getTotalDocLength());
    pDoc.setTopics4GibbsTest(number_of_topics, 0, testLength);
    sampleTestSet.add(pDoc);
    for (_ChildDoc cDoc : pDoc.m_childDocs) {
        testLength = (int) (m_testWord4PerplexityProportion * cDoc.getTotalDocLength());
        cDoc.setTopics4GibbsTest(number_of_topics, 0, testLength);
        sampleTestSet.add(cDoc);
    }
}

Example 20 with structures._ParentDoc

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

the class languageModelBaseLine method generateReferenceModelWithXVal.

protected void generateReferenceModelWithXVal() {
    m_allWordFrequencyWithXVal = 0;
    for (_Doc d : m_corpus.getCollection()) {
        if (d instanceof _ParentDoc) {
            for (_SparseFeature fv : d.getSparse()) {
                int wid = fv.getIndex();
                double val = fv.getValue();
                m_allWordFrequencyWithXVal += val;
                if (m_wordSstat.containsKey(wid)) {
                    double oldVal = m_wordSstat.get(wid);
                    m_wordSstat.put(wid, oldVal + val);
                } else {
                    m_wordSstat.put(wid, val);
                }
            }
        } else {
            double docLenWithXVal = 0;
            for (_Word w : d.getWords()) {
                // double xProportion = w.getXProb();
                int wid = w.getIndex();
                double val = 0;
                if (((_ChildDoc) d).m_wordXStat.containsKey(wid)) {
                    val = ((_ChildDoc) d).m_wordXStat.get(wid);
                }
                docLenWithXVal += val;
                m_allWordFrequencyWithXVal += val;
                if (m_wordSstat.containsKey(wid)) {
                    double oldVal = m_wordSstat.get(wid);
                    m_wordSstat.put(wid, oldVal + val);
                } else {
                    m_wordSstat.put(wid, val);
                }
            }
            ((_ChildDoc) d).setChildDocLenWithXVal(docLenWithXVal);
        }
    }
    for (int wid : m_wordSstat.keySet()) {
        double val = m_wordSstat.get(wid);
        double prob = val / m_allWordFrequencyWithXVal;
        m_wordSstat.put(wid, prob);
    }
}