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

Example 21 with structures._Word

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

the class ACCTM_C method initialize_probability.

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) {
            d.setTopics4Gibbs(number_of_topics, 0);
            for (_Stn stnObj : d.getSentences()) stnObj.setTopicsVct(number_of_topics);
        } else if (d instanceof _ChildDoc4BaseWithPhi) {
            ((_ChildDoc4BaseWithPhi) d).createXSpace(number_of_topics, m_gamma.length, vocabulary_size, d_beta);
            ((_ChildDoc4BaseWithPhi) d).setTopics4Gibbs(number_of_topics, 0);
            computeMu4Doc((_ChildDoc) d);
        }
        if (d instanceof _ParentDoc) {
            for (_Word w : d.getWords()) {
                word_topic_sstat[w.getTopic()][w.getIndex()]++;
                m_sstat[w.getTopic()]++;
            }
        } else if (d instanceof _ChildDoc4BaseWithPhi) {
            for (_Word w : d.getWords()) {
                int xid = w.getX();
                int tid = w.getTopic();
                int wid = w.getIndex();
                // update global
                if (xid == 0) {
                    word_topic_sstat[tid][wid]++;
                    m_sstat[tid]++;
                }
            }
        }
    }
    imposePrior();
    m_statisticsNormalized = false;
}

Example 22 with structures._Word

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

the class ACCTM_C method sampleInChildDoc.

protected void sampleInChildDoc(_Doc d) {
    _ChildDoc4BaseWithPhi cDoc = (_ChildDoc4BaseWithPhi) d;
    int wid, tid, xid;
    double normalizedProb;
    for (_Word w : cDoc.getWords()) {
        wid = w.getIndex();
        tid = w.getTopic();
        xid = w.getX();
        if (xid == 0) {
            cDoc.m_xTopicSstat[xid][tid]--;
            cDoc.m_xSstat[xid]--;
            cDoc.m_wordXStat.put(wid, cDoc.m_wordXStat.get(wid) - 1);
            if (m_collectCorpusStats) {
                word_topic_sstat[tid][wid]--;
                m_sstat[tid]--;
            }
        } else if (xid == 1) {
            cDoc.m_xTopicSstat[xid][wid]--;
            cDoc.m_xSstat[xid]--;
            cDoc.m_childWordSstat--;
        }
        normalizedProb = 0;
        double pLambdaZero = childXInDocProb(0, cDoc);
        double pLambdaOne = childXInDocProb(1, cDoc);
        for (tid = 0; tid < number_of_topics; tid++) {
            double pWordTopic = childWordByTopicProb(tid, wid);
            double pTopic = childTopicInDocProb(tid, cDoc);
            m_topicProbCache[tid] = pWordTopic * pTopic * pLambdaZero;
            normalizedProb += m_topicProbCache[tid];
        }
        double pWordTopic = childLocalWordByTopicProb(wid, cDoc);
        m_topicProbCache[tid] = pWordTopic * pLambdaOne;
        normalizedProb += m_topicProbCache[tid];
        normalizedProb *= m_rand.nextDouble();
        for (tid = 0; tid < m_topicProbCache.length; tid++) {
            normalizedProb -= m_topicProbCache[tid];
            if (normalizedProb <= 0)
                break;
        }
        if (tid == m_topicProbCache.length)
            tid--;
        if (tid < number_of_topics) {
            xid = 0;
            w.setX(xid);
            w.setTopic(tid);
            cDoc.m_xTopicSstat[xid][tid]++;
            cDoc.m_xSstat[xid]++;
            if (cDoc.m_wordXStat.containsKey(wid)) {
                cDoc.m_wordXStat.put(wid, cDoc.m_wordXStat.get(wid) + 1);
            } else {
                cDoc.m_wordXStat.put(wid, 1);
            }
            if (m_collectCorpusStats) {
                word_topic_sstat[tid][wid]++;
                m_sstat[tid]++;
            }
        } else if (tid == (number_of_topics)) {
            xid = 1;
            w.setX(xid);
            w.setTopic(tid);
            cDoc.m_xTopicSstat[xid][wid]++;
            cDoc.m_xSstat[xid]++;
            cDoc.m_childWordSstat++;
        }
    }
}

Example 23 with structures._Word

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

the class ACCTM_CZ method cal_logLikelihood_partial4Child.

// change it into proportion rather than the last sample
@Override
protected double cal_logLikelihood_partial4Child(_Doc d) {
    _ChildDoc4BaseWithPhi cDoc = (_ChildDoc4BaseWithPhi) d;
    double docLogLikelihood = 0.0;
    double gammaLen = Utils.sumOfArray(m_gamma);
    double cDocXSum = Utils.sumOfArray(cDoc.m_xSstat);
    for (_Word w : cDoc.getTestWords()) {
        int wid = w.getIndex();
        double wordLogLikelihood = 0;
        for (int k = 0; k < number_of_topics; k++) {
            double term1 = childWordByTopicProb(k, wid);
            double term2 = childTopicInDoc(k, cDoc);
            double term3 = childXInDocProb(0, cDoc) / (cDocXSum + gammaLen);
            double wordPerTopicLikelihood = term1 * term2 * term3;
            wordLogLikelihood += wordPerTopicLikelihood;
        }
        double wordPerTopicLikelihood = childLocalWordByTopicProb(wid, cDoc) * childXInDocProb(1, cDoc) / (cDocXSum + gammaLen);
        wordLogLikelihood += wordPerTopicLikelihood;
        if (Math.abs(wordLogLikelihood) < 1e-10) {
            System.out.println("wordLoglikelihood\t" + wordLogLikelihood);
            wordLogLikelihood += 1e-10;
        }
        wordLogLikelihood = Math.log(wordLogLikelihood);
        docLogLikelihood += wordLogLikelihood;
    }
    return docLogLikelihood;
}

Example 24 with structures._Word

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

the class ACCTM_CZLR method xProb4Word.

public double xProb4Word(int xid, _Word w, _ChildDoc cDoc) {
    double result = 0;
    _ParentDoc pDoc = cDoc.m_parentDoc;
    double temp1 = pDoc.m_featureWeight.length;
    double temp2 = w.getFeatures().length;
    result = Utils.dotProduct(pDoc.m_featureWeight, w.getFeatures());
    if (xid == 1)
        result = 1 / (1 + Math.exp(-result));
    else
        result = 1 / (1 + Math.exp(result));
    return result;
}

Example 25 with structures._Word

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

the class ACCTM_CZLR method sampleInChildDoc.

@Override
public void sampleInChildDoc(_Doc d) {
    _ChildDoc4BaseWithPhi cDoc = (_ChildDoc4BaseWithPhi) d;
    int wid, tid, xid;
    double normalizedProb;
    for (_Word w : cDoc.getWords()) {
        wid = w.getIndex();
        tid = w.getTopic();
        xid = w.getX();
        if (xid == 0) {
            cDoc.m_xTopicSstat[xid][tid]--;
            cDoc.m_xSstat[xid]--;
            cDoc.m_wordXStat.put(wid, cDoc.m_wordXStat.get(wid) - 1);
            if (m_collectCorpusStats) {
                word_topic_sstat[tid][wid]--;
                m_sstat[tid]--;
            }
        } else if (xid == 1) {
            cDoc.m_xTopicSstat[xid][wid]--;
            cDoc.m_xSstat[xid]--;
            cDoc.m_childWordSstat--;
        }
        normalizedProb = 0;
        double pLambdaZero = xProb4Word(0, w, cDoc);
        double pLambdaOne = xProb4Word(1, w, cDoc);
        for (tid = 0; tid < number_of_topics; tid++) {
            double pWordTopic = childWordByTopicProb(tid, wid);
            double pTopic = childTopicInDocProb(tid, cDoc);
            m_topicProbCache[tid] = pWordTopic * pTopic * pLambdaZero;
            normalizedProb += m_topicProbCache[tid];
        }
        double pWordTopic = childLocalWordByTopicProb(wid, cDoc);
        m_topicProbCache[tid] = pWordTopic * pLambdaOne;
        normalizedProb += m_topicProbCache[tid];
        normalizedProb *= m_rand.nextDouble();
        for (tid = 0; tid < m_topicProbCache.length; tid++) {
            normalizedProb -= m_topicProbCache[tid];
            if (normalizedProb <= 0)
                break;
        }
        if (tid == m_topicProbCache.length)
            tid--;
        if (tid < number_of_topics) {
            xid = 0;
            w.setX(xid);
            w.setTopic(tid);
            cDoc.m_xTopicSstat[xid][tid]++;
            cDoc.m_xSstat[xid]++;
            if (cDoc.m_wordXStat.containsKey(wid)) {
                cDoc.m_wordXStat.put(wid, cDoc.m_wordXStat.get(wid) + 1);
            } else {
                cDoc.m_wordXStat.put(wid, 1);
            }
            if (m_collectCorpusStats) {
                word_topic_sstat[tid][wid]++;
                m_sstat[tid]++;
            }
        } else if (tid == (number_of_topics)) {
            xid = 1;
            w.setX(xid);
            w.setTopic(tid);
            cDoc.m_xTopicSstat[xid][wid]++;
            cDoc.m_xSstat[xid]++;
            cDoc.m_childWordSstat++;
        }
    }
}