Examples with structures._ChildDoc4BaseWithPhi_Hard structures._ChildDoc4BaseWithPhi_Hard used on opensource projects

Example 1 with structures._ChildDoc4BaseWithPhi_Hard

use of structures._ChildDoc4BaseWithPhi_Hard in project IR_Base by Linda-sunshine.

the class ParentChildAnalyzer method loadChildDoc.

public void loadChildDoc(String fileName) {
    if (fileName == null || fileName.isEmpty())
        return;
    JSONObject json = LoadJSON(fileName);
    String content = Utils.getJSONValue(json, "content");
    String name = Utils.getJSONValue(json, "name");
    String parent = Utils.getJSONValue(json, "parent");
    String title = Utils.getJSONValue(json, "title");
    // 
    // _ChildDoc4BaseWithPhi d = new _ChildDoc4BaseWithPhi(m_corpus.getSize(),
    // name, "", content, 0);
    // _ChildDoc4BaseWithPhi_Hard d = new _ChildDoc4BaseWithPhi_Hard(m_corpus.getSize(), name, "", content, 0) ;
    // _ChildDoc4ChildPhi d = new _ChildDoc4ChildPhi(m_corpus.getSize(),
    // name,
    // "", content, 0);
    // _ChildDoc4TwoPhi d = new _ChildDoc4TwoPhi(m_corpus.getSize(), name, "", content, 0);
    // _ChildDoc4ThreePhi d = new _ChildDoc4ThreePhi(m_corpus.getSize(), name,
    // "", content, 0);
    // _ChildDoc4OneTopicProportion d = new _ChildDoc4OneTopicProportion(m_corpus.getSize(), name, "", content, 0);
    _ChildDoc d = new _ChildDoc(m_corpus.getSize(), name, "", content, 0);
    if (parentHashMap.containsKey(parent)) {
        if (AnalyzeDoc(d)) {
            // this is a valid child document
            // if (parentHashMap.containsKey(parent)) {
            _ParentDoc pDoc = parentHashMap.get(parent);
            d.setParentDoc(pDoc);
            pDoc.addChildDoc(d);
        } else {
        // System.err.format("filtering comments %s!\n", parent);
        }
    } else {
    // System.err.format("[Warning]Missing parent document %s!\n", parent);
    }
}

Example 2 with structures._ChildDoc4BaseWithPhi_Hard

use of structures._ChildDoc4BaseWithPhi_Hard in project IR_Base by Linda-sunshine.

the class ACCTM_CHard 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) {
            d.setTopics4Gibbs(number_of_topics, 0);
            for (_Stn stnObj : d.getSentences()) stnObj.setTopic(number_of_topics);
        } else if (d instanceof _ChildDoc4BaseWithPhi) {
            ((_ChildDoc4BaseWithPhi_Hard) d).createXSpace(number_of_topics, m_gamma.length, vocabulary_size, d_beta);
            ((_ChildDoc4BaseWithPhi_Hard) 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 3 with structures._ChildDoc4BaseWithPhi_Hard

use of structures._ChildDoc4BaseWithPhi_Hard in project IR_Base by Linda-sunshine.

the class ACCTM_CHard method initTest.

@Override
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 * d.getTotalDocLength());
    testLength = 0;
    pDoc.setTopics4GibbsTest(number_of_topics, 0, testLength);
    sampleTestSet.add(pDoc);
    pDoc.createSparseVct4Infer();
    for (_ChildDoc cDoc : pDoc.m_childDocs) {
        testLength = (int) (m_testWord4PerplexityProportion * cDoc.getTotalDocLength());
        ((_ChildDoc4BaseWithPhi_Hard) cDoc).createXSpace(number_of_topics, m_gamma.length, vocabulary_size, d_beta);
        ((_ChildDoc4BaseWithPhi_Hard) cDoc).setTopics4GibbsTest(number_of_topics, 0, testLength);
        sampleTestSet.add(cDoc);
        cDoc.createSparseVct4Infer();
        computeTestMu4Doc(cDoc);
    }
}

Example 4 with structures._ChildDoc4BaseWithPhi_Hard

use of structures._ChildDoc4BaseWithPhi_Hard in project IR_Base by Linda-sunshine.

the class ACCTM_CHard method cal_logLikelihood_partial4Child.

@Override
protected double cal_logLikelihood_partial4Child(_Doc d) {
    _ChildDoc4BaseWithPhi_Hard cDoc = (_ChildDoc4BaseWithPhi_Hard) 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;
        if (Utils.indexOf(cDoc.m_parentDoc.getSparse(), wid) != -1) {
            for (int k = 0; k < number_of_topics; k++) {
                double wordPerTopicLikelihood = childWordByTopicProb(k, wid) * childTopicInDocProb(k, cDoc);
                wordLogLikelihood += wordPerTopicLikelihood;
            }
        } else {
            for (int k = 0; k < number_of_topics; k++) {
                double wordPerTopicLikelihood = childWordByTopicProb(k, wid) * childTopicInDocProb(k, cDoc) * childXInDocProb(0, cDoc) / (cDocXSum + gammaLen);
                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;
}