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

Example 11 with structures._ChildDoc

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

the class LDAGibbs4AC_test method debugOutput.

public void debugOutput(String filePrefix) {
    File topicFolder = new File(filePrefix + "topicAssignment");
    if (!topicFolder.exists()) {
        System.out.println("creating directory" + topicFolder);
        topicFolder.mkdir();
    }
    File childTopKStnFolder = new File(filePrefix + "topKStn");
    if (!childTopKStnFolder.exists()) {
        System.out.println("creating top K stn directory\t" + childTopKStnFolder);
        childTopKStnFolder.mkdir();
    }
    File stnTopKChildFolder = new File(filePrefix + "topKChild");
    if (!stnTopKChildFolder.exists()) {
        System.out.println("creating top K child directory\t" + stnTopKChildFolder);
        stnTopKChildFolder.mkdir();
    }
    int topKStn = 10;
    int topKChild = 10;
    for (_Doc d : m_trainSet) {
        if (d instanceof _ParentDoc) {
            printParentTopicAssignment(d, topicFolder);
        } else if (d instanceof _ChildDoc) {
            printChildTopicAssignment(d, topicFolder);
        }
    // if(d instanceof _ParentDoc){
    // printTopKChild4Stn(topKChild, (_ParentDoc)d, stnTopKChildFolder);
    // printTopKStn4Child(topKStn, (_ParentDoc)d, childTopKStnFolder);
    // }
    }
    String parentParameterFile = filePrefix + "parentParameter.txt";
    String childParameterFile = filePrefix + "childParameter.txt";
    printParameter(parentParameterFile, childParameterFile, m_trainSet);
    // printTestParameter4Spam(filePrefix);
    String similarityFile = filePrefix + "topicSimilarity.txt";
    discoverSpecificComments(similarityFile);
    printEntropy(filePrefix);
    printTopKChild4Parent(filePrefix, topKChild);
    printTopKChild4Stn(filePrefix, topKChild);
    printTopKChild4StnWithHybrid(filePrefix, topKChild);
    printTopKChild4StnWithHybridPro(filePrefix, topKChild);
    printTopKStn4Child(filePrefix, topKStn);
}

Example 12 with structures._ChildDoc

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

the class LDAGibbs4AC_test method rankChild4StnByHybrid.

protected HashMap<String, Double> rankChild4StnByHybrid(_Stn stnObj, _ParentDoc pDoc) {
    HashMap<String, Double> childLikelihoodMap = new HashMap<String, Double>();
    double smoothingMu = m_LM.m_smoothingMu;
    for (_ChildDoc cDoc : pDoc.m_childDocs) {
        double cDocLen = cDoc.getTotalDocLength();
        _SparseFeature[] fv = cDoc.getSparse();
        double stnLogLikelihood = 0;
        double alphaDoc = smoothingMu / (smoothingMu + cDocLen);
        _SparseFeature[] sv = stnObj.getFv();
        for (_SparseFeature svWord : sv) {
            double featureLikelihood = 0;
            int wid = svWord.getIndex();
            double stnVal = svWord.getValue();
            int featureIndex = Utils.indexOf(fv, wid);
            double docVal = 0;
            if (featureIndex != -1) {
                docVal = fv[featureIndex].getValue();
            }
            double LMLikelihood = (1 - alphaDoc) * docVal / (cDocLen);
            LMLikelihood += alphaDoc * m_LM.getReferenceProb(wid);
            double TMLikelihood = 0;
            for (int k = 0; k < number_of_topics; k++) {
                // double likelihoodPerTopic =
                // topic_term_probabilty[k][wid];
                // System.out.println("likelihoodPerTopic1-----\t"+likelihoodPerTopic);
                // 
                // likelihoodPerTopic *= cDoc.m_topics[k];
                // System.out.println("likelihoodPerTopic2-----\t"+likelihoodPerTopic);
                TMLikelihood += (word_topic_sstat[k][wid] / m_sstat[k]) * (topicInDocProb(k, cDoc) / (d_alpha * number_of_topics + cDocLen));
            // TMLikelihood +=
            // topic_term_probabilty[k][wid]*cDoc.m_topics[k];
            // System.out.println("TMLikelihood\t"+TMLikelihood);
            }
            featureLikelihood = m_tau * LMLikelihood + (1 - m_tau) * TMLikelihood;
            // featureLikelihood = TMLikelihood;
            featureLikelihood = Math.log(featureLikelihood);
            stnLogLikelihood += stnVal * featureLikelihood;
        }
        childLikelihoodMap.put(cDoc.getName(), stnLogLikelihood);
    }
    return childLikelihoodMap;
}

Example 13 with structures._ChildDoc

use of structures._ChildDoc 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 14 with structures._ChildDoc

use of structures._ChildDoc 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 15 with structures._ChildDoc

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

the class corrLDA_Gibbs method sampleInChildDoc.

protected void sampleInChildDoc(_Doc d) {
    _ChildDoc cDoc = (_ChildDoc) d;
    int wid, tid;
    double normalizedProb = 0;
    for (_Word w : cDoc.getWords()) {
        wid = w.getIndex();
        tid = w.getTopic();
        cDoc.m_sstat[tid]--;
        if (m_collectCorpusStats) {
            word_topic_sstat[tid][wid]--;
            m_sstat[tid]--;
        }
        normalizedProb = 0;
        for (tid = 0; tid < number_of_topics; tid++) {
            double pWordTopic = childWordByTopicProb(tid, wid);
            double pTopicDoc = childTopicInDocProb(tid, cDoc);
            m_topicProbCache[tid] = pWordTopic * pTopicDoc;
            normalizedProb += m_topicProbCache[tid];
        }
        normalizedProb *= m_rand.nextDouble();
        for (tid = 0; tid < number_of_topics; tid++) {
            normalizedProb -= m_topicProbCache[tid];
            if (normalizedProb < 0)
                break;
        }
        if (tid == number_of_topics)
            tid--;
        w.setTopic(tid);
        cDoc.m_sstat[tid]++;
        if (m_collectCorpusStats) {
            word_topic_sstat[tid][wid]++;
            m_sstat[tid]++;
        }
    }
}