Examples of NGramTfDf

Examples of uk.ac.cam.ch.wwmm.ptc.experimental.ngramtfdf.NGramTfDf

51
52
53
54
55
56
57
58
59
60
61
62
63
  public static void tfIdfAnalyseCluster(Map<Integer,Float> cluster, IndexReader ir) throws Exception {
    List<File> clusterFiles = new ArrayList<File>();
    for(Integer i : cluster.keySet()) {
      clusterFiles.add(new File(ir.document(i).getField("filename").stringValue().replaceAll("markedup", "source")));
    }
    NGramTfDf ngtd = NGramTfDf.analyseFiles(clusterFiles);
    ngtd.calculateNGrams();
    Bag<String> tf = ngtd.getDfBag(1);
    tf.discardInfrequent(2);
    Map<String,Double> tfIdf = new HashMap<String,Double>();
    int numDocs = ir.numDocs();
    IndexSearcher is = new IndexSearcher(ir);
    for(String s : tf.getSet()) {
View Full Code Here

Examples of uk.ac.cam.ch.wwmm.ptc.experimental.ngramtfdf.NGramTfDf

103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
            onts.add(termArray[j]);
          }       
        }       
      }
    }
    NGramTfDf ngtd = NGramTfDf.analyseFiles(clusterFiles);
    ngtd.calculateNGrams();
    Bag<String> df = ngtd.getDfBag(1);
    df.discardInfrequent(2);
    Map<String,Double> scores = new HashMap<String,Double>();
    int numDocs = ir.numDocs();
    int clusterSize = cluster.size();
    double scaleFactor = clusterSize * 1.0 / numDocs;
    IndexSearcher is = new IndexSearcher(ir);
    for(String s : df.getSet()) {
      //System.out.println(s);
      int docFreq = 0;
      Query q;
      if(s.matches("\\S+")) {
        TermQuery tq = new TermQuery(new Term("txt", s));
        q = tq;
        //docFreq = ir.docFreq(new Term("txt", s));
      } else {
        PhraseQuery pq = new PhraseQuery();
        for(String ss : StringTools.arrayToList(s.split("\\s+"))) pq.add(new Term("txt", ss));
        q = pq;
      }
      VectorCollector vc = new VectorCollector();
      is.search(q, vc);
      docFreq = vc.getResultsVector().size();
      double score;
      double expected = scaleFactor * docFreq;
      double excess = df.getCount(s) - expected;
      score = excess / clusterSize;       
      if(score > threshold) scores.put(s, score);
    }
    Stemmer st = new Stemmer(new EnglishStemmer());
    Map<String,List<String>> stems = st.wordsToStems(df.getSet());
    for(String stem : stems.keySet()) {
      List<String> words = stems.get(stem);
      if(words.size() > 1) {
        BooleanQuery bq = new BooleanQuery(true);
        for(String word : words) {
          bq.add(new BooleanClause(new TermQuery(new Term("txt", word)), Occur.SHOULD));
        }
        VectorCollector vc = new VectorCollector();
        is.search(bq, vc);
        double expected = scaleFactor * vc.getResultsVector().size();
        int overlap = overlapDocs(vc.getResultsVector(), cluster);
        double excess = overlap - expected;
        double score = excess / clusterSize;
        if(score > threshold) {
          df.add(stems.get(stem).toString(), overlap);
          scores.put(stems.get(stem).toString(), score);
        }
      }
    }
    Map<String,List<String>> termStems = ngtd.ngramsByStem();
    for(String stem : termStems.keySet()) {
      List<String> multiWords = termStems.get(stem);
      if(multiWords.size() > 1) {
        BooleanQuery bq = new BooleanQuery(true);
        for(String multiWord : multiWords) {
View Full Code Here

Examples of uk.ac.cam.ch.wwmm.ptc.experimental.ngramtfdf.NGramTfDf

295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
    }
    Stemmer st = new Stemmer(new EnglishStemmer());
    Map<String,List<String>> stems = st.wordsToStems(dfs.getSet());

    dfs.discardInfrequent(2);
    NGramTfDf ngtd = NGramTfDf.analyseFiles(clusterFiles);
    ngtd.calculateNGrams();
    Bag<String> bs = ngtd.getDfBag(2);
    bs.discardInfrequent(2);
    Map<String,List<String>> termStems = ngtd.ngramsByStem();

    Map<String,Double> scores = new HashMap<String,Double>();
    Map<String,Integer> overlaps = new HashMap<String,Integer>();
    IndexSearcher is = new IndexSearcher(ir);
    int docTotal = ir.numDocs();
View Full Code Here
TOP
Copyright © 2018 www.massapi.com. All rights reserved.
All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.