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

Example 61 with structures._Word

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

the class LDAGibbs4AC method cal_logLikelihood_partial4Parent.

protected double cal_logLikelihood_partial4Parent(_Doc d) {
    double docLogLikelihood = 0.0;
    for (_Word w : d.getTestWords()) {
        int wid = w.getIndex();
        double wordLogLikelihood = 0;
        for (int k = 0; k < number_of_topics; k++) {
            double wordPerTopicLikelihood = d.m_topics[k] * topic_term_probabilty[k][wid];
            wordLogLikelihood += wordPerTopicLikelihood;
        }
        docLogLikelihood += Math.log(wordLogLikelihood);
    }
    return docLogLikelihood;
}

Example 62 with structures._Word

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

the class LDAGibbs4AC_test method printParentTopicAssignment.

protected void printParentTopicAssignment(_Doc d, File topicFolder) {
    // System.out.println("printing topic assignment parent documents");
    String topicAssignmentFile = d.getName() + ".txt";
    try {
        PrintWriter pw = new PrintWriter(new File(topicFolder, topicAssignmentFile));
        for (_Stn stnObj : d.getSentences()) {
            pw.print(stnObj.getIndex() + "\t");
            for (_Word w : stnObj.getWords()) {
                int index = w.getIndex();
                int topic = w.getTopic();
                String featureName = m_corpus.getFeature(index);
                // System.out.println("test\t"+featureName+"\tdocName\t"+d.getName());
                pw.print(featureName + ":" + topic + "\t");
            }
            pw.println();
        }
        pw.flush();
        pw.close();
    } catch (FileNotFoundException e) {
        // TODO Auto-generated catch block
        e.printStackTrace();
    }
}

Example 63 with structures._Word

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

the class LDAGibbs4AC_test method printChildTopicAssignment.

protected void printChildTopicAssignment(_Doc d, File topicFolder) {
    // System.out.println("printing topic assignment parent documents");
    String topicAssignmentFile = d.getName() + ".txt";
    try {
        PrintWriter pw = new PrintWriter(new File(topicFolder, topicAssignmentFile));
        for (_Word w : d.getWords()) {
            int index = w.getIndex();
            int topic = w.getTopic();
            String featureName = m_corpus.getFeature(index);
            pw.print(featureName + ":" + topic + "\t");
        }
        pw.flush();
        pw.close();
    } catch (FileNotFoundException e) {
        // TODO Auto-generated catch block
        e.printStackTrace();
    }
}

Example 64 with structures._Word

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

the class LDAGibbs4AC_test method rankChild4StnByLikelihood.

// stn is a query, retrieve comment by likelihood
protected HashMap<String, Double> rankChild4StnByLikelihood(_Stn stnObj, _ParentDoc pDoc) {
    HashMap<String, Double> childLikelihoodMap = new HashMap<String, Double>();
    for (_ChildDoc cDoc : pDoc.m_childDocs) {
        int cDocLen = cDoc.getTotalDocLength();
        double stnLogLikelihood = 0;
        for (_Word w : stnObj.getWords()) {
            double wordLikelihood = 0;
            int wid = w.getIndex();
            for (int k = 0; k < number_of_topics; k++) {
                wordLikelihood += (word_topic_sstat[k][wid] / m_sstat[k]) * (topicInDocProb(k, cDoc) / (d_alpha * number_of_topics + cDocLen));
            // wordLikelihood +=
            // topic_term_probabilty[k][wid]*cDoc.m_topics[k];
            }
            stnLogLikelihood += Math.log(wordLikelihood);
        }
        childLikelihoodMap.put(cDoc.getName(), stnLogLikelihood);
    }
    return childLikelihoodMap;
}

Example 65 with structures._Word

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

the class corrLDA_Gibbs method cal_logLikelihood_partial4Child.

protected double cal_logLikelihood_partial4Child(_Doc d) {
    // _ChildDoc4BaseWithPhi cDoc = (_ChildDoc4BaseWithPhi)d;
    double docLogLikelihood = 0.0;
    for (_Word w : d.getTestWords()) {
        int wid = w.getIndex();
        double wordLogLikelihood = 0;
        for (int k = 0; k < number_of_topics; k++) {
            double term1 = d.m_topics[k];
            double term2 = topic_term_probabilty[k][wid];
            // double term1 = childWordByTopicProb(k, wid);
            // double term2 = childTopicInDoc(k, d);
            double wordPerTopicLikelihood = term1 * term2;
            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;
}