Package uk.ac.cam.ch.wwmm.oscar3.recogniser.document

Examples of uk.ac.cam.ch.wwmm.oscar3.recogniser.document.ProcessingDocument

79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
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
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
      System.out.println(s + "\t" + tfIdf.get(s));
    } 
  }
 
  public static Map<String,Double> excessAnalyseCluster(Map<Integer,Float> cluster, IndexReader ir, double threshold, boolean enriched) throws Exception {
    LuceneChemicalIndex lci = new LuceneIndexerSearcher(false).getLci();
    Set<String> inchis = new HashSet<String>();
    Set<String> onts = new HashSet<String>();
   
    List<File> clusterFiles = new ArrayList<File>();
    for(Integer i : cluster.keySet()) {
      clusterFiles.add(new File(ir.document(i).getField("filename").stringValue().replaceAll("markedup", "source")));
      if(enriched) {
        TermFreqVector tvf = ir.getTermFreqVector(i, "InChI");
        if(tvf != null) {
          String [] termArray = tvf.getTerms();
          for(int j=0;j<termArray.length;j++) {
            inchis.add(termArray[j]);
          }       
        }
        tvf = ir.getTermFreqVector(i, "Ontology");
        if(tvf != null) {
          String [] termArray = tvf.getTerms();
          for(int j=0;j<termArray.length;j++) {
            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) {
          PhraseQuery pq = new PhraseQuery();
          for(String ss : StringTools.arrayToList(multiWord.split("\\s+"))) pq.add(new Term("txt", ss));
          bq.add(new BooleanClause(pq, 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(termStems.get(stem).toString(), overlap);
          scores.put(termStems.get(stem).toString(), score);
        }
      }
    }
    if(enriched) {
      for(String inchi : inchis) {
        Term luceneTerm = new Term("InChI", inchi);
        Query q = new TermQuery(luceneTerm);
        VectorCollector vc = new VectorCollector();
        is.search(q, vc);
        double expected = scaleFactor * vc.getResultsVector().size();
        int overlap = overlapDocs(vc.getResultsVector(), cluster);
        if(overlap < 2) continue;
        double excess = overlap - expected;
        double score = excess / clusterSize;
       
        if(score > threshold) {
          String s = "InChi: " + lci.getName(lci.hitsByInChI(inchi));
          scores.put(s, score);
          df.add(s, overlap);           
        }
      }
     
View Full Code Here
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
    return scores;
  }

 
  public static void analyseCluster(Map<Integer,Float> cluster, IndexReader ir, DocVectorSimilarity similarity, double threshold) throws Exception {
    LuceneChemicalIndex lci = new LuceneIndexerSearcher(false).getLci();
    List<File> clusterFiles = new ArrayList<File>();
    Bag<String> dfs = new Bag<String>();
    Set<String> inchis = new HashSet<String>();
    Set<String> onts = new HashSet<String>();
    for(Integer i : cluster.keySet()) {
      cluster.put(i, 1.0f);
      TermFreqVector tvf = ir.getTermFreqVector(i, "txt");
      String [] termArray = tvf.getTerms();
      for(int j=0;j<termArray.length;j++) {
        dfs.add(termArray[j]);
      }
      if(false) {
        tvf = ir.getTermFreqVector(i, "InChI");
        if(tvf != null) {
          termArray = tvf.getTerms();
          for(int j=0;j<termArray.length;j++) {
            inchis.add(termArray[j]);
          }       
        }
        tvf = ir.getTermFreqVector(i, "Ontology");
        if(tvf != null) {
          termArray = tvf.getTerms();
          for(int j=0;j<termArray.length;j++) {
            onts.add(termArray[j]);
          }       
        }       
      }
     

      clusterFiles.add(new File(ir.document(i).getField("filename").stringValue().replaceAll("markedup", "source")));
    }
    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();
    for(String term : dfs.getSet()) {
      if(TermSets.getClosedClass().contains(term) || term.matches("[^A-Za-z]+")) continue;
      Term luceneTerm = new Term("txt", term);
      Query q = new TermQuery(luceneTerm);
      VectorCollector vc = new VectorCollector();
      is.search(q, vc);
      double score = similarity.similarity(cluster, vc.getResultsVector());
      if(score > threshold) {
        int overlap = overlapDocs(vc.getResultsVector(), cluster);
        if(overlap > 1) {
          scores.put(term, score);
          overlaps.put(term, overlap);           
        }
      }
    }
    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 score = similarity.similarity(cluster, vc.getResultsVector());
        if(score > threshold) {
          String s = words.toString();
          int overlap = overlapDocs(vc.getResultsVector(), cluster);
          if(overlap > 1) {
            scores.put(s, score);
            overlaps.put(s, overlap);           
          }
        }
      }
    }
    for(String stem : termStems.keySet()) {
      List<String> multiWords = termStems.get(stem);
      if(multiWords.size() > 1) {
        BooleanQuery bq = new BooleanQuery(true);
        for(String multiWord : multiWords) {
          PhraseQuery pq = new PhraseQuery();
          for(String ss : StringTools.arrayToList(multiWord.split("\\s+"))) pq.add(new Term("txt", ss));
          bq.add(new BooleanClause(pq, Occur.SHOULD));
        }
        VectorCollector vc = new VectorCollector();
        is.search(bq, vc);
        double score = similarity.similarity(cluster, vc.getResultsVector());
        if(score > threshold) {
          String s = multiWords.toString();
          int overlap = overlapDocs(vc.getResultsVector(), cluster);
          if(overlap > 1) {
            scores.put(s, score);
            overlaps.put(s, overlap);           
          }
        }
      }
    }
    for(String s : bs.getList()) {
      if(!s.matches(".*\\s+.*")) continue;
      PhraseQuery pq = new PhraseQuery();
      for(String ss : StringTools.arrayToList(s.split("\\s+"))) pq.add(new Term("txt", ss));
      VectorCollector vc = new VectorCollector();
      is.search(pq, vc);
      double score = similarity.similarity(cluster, vc.getResultsVector());
      if(score > threshold) {
        scores.put(s, score);
        overlaps.put(s, overlapDocs(vc.getResultsVector(), cluster));
      }
    }
   

    if(false) {
      for(String inchi : inchis) {
        Term luceneTerm = new Term("InChI", inchi);
        Query q = new TermQuery(luceneTerm);
        VectorCollector vc = new VectorCollector();
        is.search(q, vc);
        double score = similarity.similarity(cluster, vc.getResultsVector());
        if(score > threshold) {
          int overlap = overlapDocs(vc.getResultsVector(), cluster);
          if(overlap > 1) {
            String s = "InChi: " + lci.getName(lci.hitsByInChI(inchi));
            scores.put(s, score);
            overlaps.put(s, overlap);           
          }
        }
      }
View Full Code Here
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
  /**
   * @param args
   */
  public static void main(String[] args) throws Exception {
    LuceneIndexerSearcher lis = new LuceneIndexerSearcher(false);
    IndexSearcher is = lis.getIndexSearcher();

    Stemmer stemmerTools = new Stemmer(new EnglishStemmer());
   
    //QueryParser qp = new Oscar3QueryParser("txt", new Oscar3Analyzer(), lis, false);
    //Query q = qp.parse("NaCl");
   
    String queryTerm = "lipid";
    //PhraseQuery pq = new PhraseQuery();
    //pq.add(new Term("txt", "aromatase"));
    //pq.add(new Term("txt", "inhibitors"));
    Query q = new TermQuery(new Term("txt", queryTerm));
    //Query q = new StemQuery(new Term("txt", queryTerm), stemmerTools);

    for(int i=0;i<100;i++) {
      VectorCollector vc = new VectorCollector();
      is.search(q, vc);
      for(Integer j : new ArrayList<Integer>(vc.getResultsVector().keySet())) {
        if(vc.getResultsVector().get(j) < 0.2) vc.getResultsVector().remove(j);
      }
      Map<String,Double> scores = ClusterAnalyser.simpleExcessAnalyseCluster(vc.getResultsVector(), lis.getIndexReader(), 0.1);
      BooleanQuery bq = new BooleanQuery(false);
      List<String> terms = StringTools.getSortedList(scores);
      if(terms.size() > 10) terms = terms.subList(0, 10);
      for(String s : terms) {
        System.out.println(s + "\t" + scores.get(s));
View Full Code Here
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
   */
  public static void main(String[] args) throws Exception {
    //System.out.println(StringTools.arrayToList(StandardAnalyzer.STOP_WORDS));
    //if(true) return;
   
    LuceneIndexerSearcher lis = new LuceneIndexerSearcher(false);

    String queryTerm = "cyp2d6";
   
    /*List<String> queryList = StringTools.arrayToList(new String[] {
    "cyp2d6",
    "cyp3a4",
    "dextromethorphan"});*/
    List<String> queryList = new ArrayList<String>();
    long time = System.currentTimeMillis();
    IndexReader ir = lis.getIndexReader();
    TermEnum termEnum = ir.terms();
    while(termEnum.next()) {
      Term t = termEnum.term();
      if(t.field().equals("txt") && termEnum.docFreq() > 20) queryList.add(t.text());
    }
    //queryList.addAll(lis.termsFromQuery(new TermQuery(new Term("txt", queryTerm))));
    System.out.println("All terms loaded: " + (System.currentTimeMillis() - time));
   
    time = System.currentTimeMillis();
    Map<String,Map<Integer,Float>> vectors = new HashMap<String,Map<Integer,Float>>();
    for(String query : queryList) {
      //System.out.println(query);
      vectors.put(query, lis.getScoresVectorForQuery(new TermQuery(new Term("txt", query))));
    }
    /*PhraseQuery pq = new PhraseQuery();
    pq.add(new Term("txt", "cyp2d6"));
    pq.add(new Term("txt", "inhibitors"));
    vectors.put("cyp2d6 inhibitors", lis.getScoresVectorForQuery(pq));*/
 
View Full Code Here
25
26
27
28
29
30
31
32
33
34
35
36
 
  /**
   * @param args
   */
  public static void main(String[] args) throws Exception{
    LuceneIndexerSearcher lis = new LuceneIndexerSearcher(false);
    IndexReader ir = lis.getIndexReader();
   
    int numDocs = ir.numDocs();
    TermEnum textEnum = ir.terms();
    Map<String,Integer> docFreqs = new HashMap<String,Integer>();
    while(textEnum.next()) {
View Full Code Here
21
22
23
24
25
26
27
28
29
30
31
32
33
  /**
   * @param args
   */
  public static void main(String[] args) throws Exception {
    LuceneIndexerSearcher lis = new LuceneIndexerSearcher(false);
    IndexSearcher is = lis.getIndexSearcher();
    IndexReader ir = lis.getIndexReader();
   
    TermEnum textEnum = ir.terms();
    Map<String,Integer> docFreqs = new HashMap<String,Integer>();
    float nd = ir.numDocs() * 1.0f;
    while(textEnum.next()) {
View Full Code Here
110
111
112
113
114
115
116
117
118
119
120
121
 
  /**
   * @param args
   */
  public static void main(String[] args) throws Exception {
    LuceneIndexerSearcher lis = new LuceneIndexerSearcher(false);
    IndexSearcher is = lis.getIndexSearcher();

    TreeNode tn = new TreeNode();
   
    tn.subCluster(is);
   
View Full Code Here
98
99
100
101
102
103
104
105
106
107
108
109
  /**
   * @param args
   */
  public static void main(String[] args) throws Exception {
    // TODO Auto-generated method stub
    LuceneIndexerSearcher lis = new LuceneIndexerSearcher(false);
    IndexReader ir = lis.getIndexReader();
    Directory dir = new RAMDirectory(ir.directory());
    ir.close();
    IndexSearcher is = new IndexSearcher(dir);
    ir = is.getIndexReader();

View Full Code Here
18
19
20
21
22
23
24
25
26
27
28
29
30
  /**
   * @param args
   */
  public static void main(String[] args) throws Exception {
    LuceneIndexerSearcher lis = new LuceneIndexerSearcher(false);
    IndexSearcher is = lis.getIndexSearcher();
    IndexReader ir = lis.getIndexReader();
    Bag<String> tfBag = new Bag<String>();
    for(int i=0;i<ir.maxDoc();i++) {
      TermFreqVector tv = ir.getTermFreqVector(i, "txt");
      String [] terms = tv.getTerms();
      int [] freqs = tv.getTermFrequencies();
View Full Code Here
144
145
146
147
148
149
150
151
152
153
154
155
 
  /**
   * @param args
   */
  public static void main(String[] args) throws Exception {
    LuceneIndexerSearcher lis = new LuceneIndexerSearcher(false);
    IndexReader ir = lis.getIndexReader();
   
    long allTime = System.currentTimeMillis();
   
    int numDocs = ir.numDocs();
    TermEnum textEnum = ir.terms();
View Full Code Here
TOP

Related Classes of uk.ac.cam.ch.wwmm.oscar3.recogniser.document.ProcessingDocument

  • dk.brics.automaton.Automaton
  • dk.brics.automaton.RunAutomaton
  • jregex.Pattern
  • nu.xom.Attribute
  • nu.xom.Builder
  • nu.xom.Document
  • nu.xom.Element
  • nu.xom.Elements
  • nu.xom.Node
  • nu.xom.Nodes
    • Copyright © 2018 www.massapicom. 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.