Search in sources :

Example 26 with MyPriorityQueue

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

the class sparseLDA_test method printTopWord.

protected void printTopWord(int k, String topWordFile) {
    System.out.println("TopWord FilePath:" + topWordFile);
    Arrays.fill(m_sstat, 0);
    for (_Doc d : m_trainSet) {
        for (int i = 0; i < number_of_topics; i++) m_sstat[i] += m_logSpace ? Math.exp(d.m_topics[i]) : d.m_topics[i];
    }
    Utils.L1Normalization(m_sstat);
    try {
        PrintWriter topWordWriter = new PrintWriter(new File(topWordFile));
        for (int i = 0; i < topic_term_probabilty.length; i++) {
            MyPriorityQueue<_RankItem> fVector = new MyPriorityQueue<_RankItem>(k);
            for (int j = 0; j < vocabulary_size; j++) fVector.add(new _RankItem(m_corpus.getFeature(j), topic_term_probabilty[i][j]));
            topWordWriter.format("Topic %d(%.5f):\t", i, m_sstat[i]);
            for (_RankItem it : fVector) topWordWriter.format("%s(%.5f)\t", it.m_name, m_logSpace ? Math.exp(it.m_value) : it.m_value);
            topWordWriter.write("\n");
        }
        topWordWriter.close();
    } catch (Exception ex) {
        System.err.print("File Not Found");
    }
}
Also used : structures._RankItem(structures._RankItem) structures._Doc(structures._Doc) MyPriorityQueue(structures.MyPriorityQueue) File(java.io.File) FileNotFoundException(java.io.FileNotFoundException) PrintWriter(java.io.PrintWriter)

Example 27 with MyPriorityQueue

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

the class ACCTM method printTopWords.

@Override
public void printTopWords(int k, String betaFile) {
    Arrays.fill(m_sstat, 0);
    System.out.println("print top words");
    for (_Doc d : m_trainSet) {
        for (int i = 0; i < m_sstat.length; i++) {
            m_sstat[i] += m_logSpace ? Math.exp(d.m_topics[i]) : d.m_topics[i];
            if (Double.isNaN(d.m_topics[i]))
                System.out.println("nan name\t" + d.getName());
        }
    }
    Utils.L1Normalization(m_sstat);
    try {
        System.out.println("beta file");
        PrintWriter betaOut = new PrintWriter(new File(betaFile));
        for (int i = 0; i < topic_term_probabilty.length; i++) {
            MyPriorityQueue<_RankItem> fVector = new MyPriorityQueue<_RankItem>(k);
            for (int j = 0; j < vocabulary_size; j++) fVector.add(new _RankItem(m_corpus.getFeature(j), topic_term_probabilty[i][j]));
            betaOut.format("Topic %d(%.3f):\t", i, m_sstat[i]);
            for (_RankItem it : fVector) {
                betaOut.format("%s(%.3f)\t", it.m_name, m_logSpace ? Math.exp(it.m_value) : it.m_value);
                System.out.format("%s(%.3f)\t", it.m_name, m_logSpace ? Math.exp(it.m_value) : it.m_value);
            }
            betaOut.println();
            System.out.println();
        }
        betaOut.close();
    } catch (Exception ex) {
        System.err.print("File Not Found");
    }
}
Also used : structures._RankItem(structures._RankItem) structures._Doc(structures._Doc) MyPriorityQueue(structures.MyPriorityQueue) File(java.io.File) PrintWriter(java.io.PrintWriter)

Example 28 with MyPriorityQueue

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

the class ACCTM_C_test method printTopWordsDistribution.

protected void printTopWordsDistribution(int topK, String topWordFile) {
    Arrays.fill(m_sstat, 0);
    System.out.println("print top words");
    for (_Doc d : m_trainSet) {
        for (int i = 0; i < number_of_topics; i++) m_sstat[i] += m_logSpace ? Math.exp(d.m_topics[i]) : d.m_topics[i];
    }
    Utils.L1Normalization(m_sstat);
    try {
        System.out.println("top word file");
        PrintWriter betaOut = new PrintWriter(new File(topWordFile));
        for (int i = 0; i < topic_term_probabilty.length; i++) {
            MyPriorityQueue<_RankItem> fVector = new MyPriorityQueue<_RankItem>(topK);
            for (int j = 0; j < vocabulary_size; j++) fVector.add(new _RankItem(m_corpus.getFeature(j), topic_term_probabilty[i][j]));
            betaOut.format("Topic %d(%.3f):\t", i, m_sstat[i]);
            for (_RankItem it : fVector) {
                betaOut.format("%s(%.3f)\t", it.m_name, m_logSpace ? Math.exp(it.m_value) : it.m_value);
                System.out.format("%s(%.3f)\t", it.m_name, m_logSpace ? Math.exp(it.m_value) : it.m_value);
            }
            betaOut.println();
            System.out.println();
        }
        betaOut.flush();
        betaOut.close();
    } catch (Exception ex) {
        System.err.print("File Not Found");
    }
}
Also used : structures._RankItem(structures._RankItem) structures._Doc(structures._Doc) MyPriorityQueue(structures.MyPriorityQueue) File(java.io.File) FileNotFoundException(java.io.FileNotFoundException) PrintWriter(java.io.PrintWriter)

Example 29 with MyPriorityQueue

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

the class DCMCorrLDA method printTopWords.

public void printTopWords(int k, String betaFile) {
    try {
        PrintWriter topWordWriter = new PrintWriter(new File(betaFile));
        for (int i = 0; i < m_beta.length; i++) {
            MyPriorityQueue<_RankItem> fVector = new MyPriorityQueue<_RankItem>(k);
            for (int j = 0; j < vocabulary_size; j++) fVector.add(new _RankItem(m_corpus.getFeature(j), m_beta[i][j]));
            topWordWriter.format("Topic %d(%.5f):\t", i, m_sstat[i]);
            for (_RankItem it : fVector) topWordWriter.format("%s(%.5f)\t", it.m_name, m_logSpace ? Math.exp(it.m_value) : it.m_value);
            topWordWriter.write("\n");
        }
        topWordWriter.close();
    } catch (Exception ex) {
        System.err.print("File Not Found");
    }
}
Also used : structures._RankItem(structures._RankItem) MyPriorityQueue(structures.MyPriorityQueue) File(java.io.File) PrintWriter(java.io.PrintWriter)

Example 30 with MyPriorityQueue

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

the class DCMCorrLDA_test method printWordTopicDistribution.

protected void printWordTopicDistribution(_Doc d, File wordTopicDistributionFolder, int k) {
    _ParentDoc4DCM pDoc = (_ParentDoc4DCM) d;
    String wordTopicDistributionFile = pDoc.getName() + ".txt";
    try {
        PrintWriter pw = new PrintWriter(new File(wordTopicDistributionFolder, wordTopicDistributionFile));
        for (int i = 0; i < number_of_topics; i++) {
            MyPriorityQueue<_RankItem> fVector = new MyPriorityQueue<_RankItem>(k);
            for (int v = 0; v < vocabulary_size; v++) {
                String featureName = m_corpus.getFeature(v);
                double wordProb = pDoc.m_wordTopic_prob[i][v];
                _RankItem ri = new _RankItem(featureName, wordProb);
                fVector.add(ri);
            }
            pw.format("Topic %d(%.5f):\t", i, pDoc.m_topics[i]);
            for (_RankItem it : fVector) pw.format("%s(%.5f)\t", it.m_name, m_logSpace ? Math.exp(it.m_value) : it.m_value);
            pw.write("\n");
        }
        pw.flush();
        pw.close();
    } catch (FileNotFoundException e) {
        e.printStackTrace();
    }
}
Also used : structures._RankItem(structures._RankItem) MyPriorityQueue(structures.MyPriorityQueue) structures._ParentDoc4DCM(structures._ParentDoc4DCM) FileNotFoundException(java.io.FileNotFoundException) File(java.io.File) PrintWriter(java.io.PrintWriter)

Aggregations

MyPriorityQueue (structures.MyPriorityQueue)39 structures._RankItem (structures._RankItem)39 File (java.io.File)27 PrintWriter (java.io.PrintWriter)27 structures._Doc (structures._Doc)25 FileNotFoundException (java.io.FileNotFoundException)20 structures._ParentDoc4DCM (structures._ParentDoc4DCM)3 IOException (java.io.IOException)2 structures._Doc4DCMLDA (structures._Doc4DCMLDA)2 structures._Review (structures._Review)2 SparseDoubleMatrix2D (cern.colt.matrix.tdouble.impl.SparseDoubleMatrix2D)1 ArrayList (java.util.ArrayList)1 structures._HDPThetaStar (structures._HDPThetaStar)1 structures._Node (structures._Node)1 structures._QUPair (structures._QUPair)1 structures._Query (structures._Query)1 structures._SparseFeature (structures._SparseFeature)1 structures._Stn (structures._Stn)1 structures._thetaStar (structures._thetaStar)1