Package uk.ac.cam.ch.wwmm.oscar3.flow

Examples of uk.ac.cam.ch.wwmm.oscar3.flow.OscarFlow

244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
      int skip = 0;
     
      if(request.getParameter("size") != null) size = Integer.parseInt(request.getParameter("size"));
      if(request.getParameter("skip") != null) skip = Integer.parseInt(request.getParameter("skip"));
     
      UserQuery uq = new UserQuery(rt, size, skip);
      if(request.getParameter("morelikethis") != null) {
        uq.setToMoreLikeThis(Integer.parseInt(request.getParameter("morelikethis")));
      }
      if(request.getParameter("query") != null) {
        String query = request.getParameter("query");
        String queryType = request.getParameter("type");
        String parameter = request.getParameter("parameter");
       
        uq.addTerm(query, queryType, parameter);
       
        for(int i=2;request.getParameter("query" + Integer.toString(i)) != null;i++) {
          query = request.getParameter("query" + Integer.toString(i));
          queryType = request.getParameter("type" + Integer.toString(i));
          parameter = request.getParameter("parameter" + Integer.toString(i));
          uq.addTerm(query, queryType, parameter);     
        }
       
      }
   
      try {
View Full Code Here
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
        ne.addAttribute(new Attribute("InChI", a));
        ne.appendChild(name);
        li.appendChild(ne);

        Element anchor = new Element("a");
        UserQuery nuq = new UserQuery(uq, UserQuery.ResultsType.SNIPPETS);
        nuq.addTerm(a, "inchi", "");
        anchor.addAttribute(new Attribute("href", nuq.getQueryURL(0, nuq.getSize())));
        anchor.appendChild("search");
       
        li.appendChild(" ");
        li.appendChild(anchor);
      } else if(a.matches("0\\.\\d+ like InChI=.+")) {
        String [] sp = a.split("\\s+");
        String name = lis.nameForInChI(sp[2]);
        li.appendChild(sp[0] + " like ");
       
        Element ne = new Element("ne");
        ne.addAttribute(new Attribute("type", "CM"));
        ne.addAttribute(new Attribute("InChI", a));
        ne.appendChild(name);
        li.appendChild(ne);
       
      } else if(a.startsWith("ONT: ")) {
        String postFix = a.substring(5);
        String name = OBOOntology.getInstance().getNameForID(postFix);
        Element ne = new Element("ne");
        ne.addAttribute(new Attribute("type", "ONT"));
        ne.addAttribute(new Attribute("ontIDs", postFix));
        ne.appendChild(name);
        li.appendChild(ne);
       
        Element anchor = new Element("a");
        UserQuery nuq = new UserQuery(uq, UserQuery.ResultsType.SNIPPETS);
        nuq.addTerm(postFix, "ontology", "");
        anchor.addAttribute(new Attribute("href", nuq.getQueryURL(0, nuq.getSize())));
        anchor.appendChild("search");
       
        li.appendChild(" ");
        li.appendChild(anchor);       
        } else {
        li.appendChild(a);       

        Element anchor = new Element("a");
        UserQuery nuq = new UserQuery(uq, UserQuery.ResultsType.SNIPPETS);
        nuq.addTerm(a, "word", "strict");
        anchor.addAttribute(new Attribute("href", nuq.getQueryURL(0, nuq.getSize())));
        anchor.appendChild("search");
       
        li.appendChild(" ");
        li.appendChild(anchor);
      }
View Full Code Here
33
34
35
36
37
38
39
40
41
42
43
44
    BooleanQuery bq = new BooleanQuery(true);
    if(queryItems.size() <= BooleanQuery.getMaxClauseCount()) {
      for(String ont : queryItems) {
        bq.add(new BooleanClause(new TermQuery(new Term("Ontology", ont)), Occur.SHOULD));
      }
      VectorCollector vc = new VectorCollector();
      is.search(bq, vc);
      cache.put(ontQ, vc);
      return vc;
    }
    return new VectorCollector();
  }
View Full Code Here
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
    //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
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
      dff.put(i, docFreqs.get(dfl.get(i)) / nd);
    }
   
    for(int i=0;i<50;i++) {
      TermQuery tq = new TermQuery(new Term("txt", dfl.get(i)));
      VectorCollector vc = new VectorCollector();
      is.search(tq, vc);
      float vcs = vc.getResultsVector().size();
      Map<Integer,Float> stf = new HashMap<Integer,Float>();
     
      for(Integer j : vc.getResultsVector().keySet()) {
        TermFreqVector tv = ir.getTermFreqVector(j, "txt");
        String [] terms = tv.getTerms();
        for(int k=0;k<tv.size();k++) {
          String term = terms[k];
          if(termMap.containsKey(term)) {
View Full Code Here
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
    System.out.println(totalEntropy);
   
    List<String> termList = tfBag.getList().subList(0, 2000);
    for(String splitTerm : termList) {
      Query q = new TermQuery(new Term("txt", splitTerm));
      VectorCollector vc = new VectorCollector();
      is.search(q, vc);
      Bag<String> inBag = new Bag<String>();
      Bag<String> outBag = new Bag<String>();
      for(int i=0;i<ir.maxDoc();i++) {
        Bag<String> bag = inBag;
        if(!vc.getResultsVector().containsKey(i)) continue;
       
        //Bag<String> bag = outBag;
        //if(vc.getResultsVector().containsKey(i)) bag = inBag;
        TermFreqVector tv = ir.getTermFreqVector(i, "txt");
        String [] terms = tv.getTerms();
View Full Code Here
63
64
65
66
67
68
69
70
71
72
73
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
108
109
110
111
112
113
114
115
116
117
118
119
120
121
      Map<Integer,Integer> bestClusters = new HashMap<Integer,Integer>();
      Map<Integer,Float> bestClusterScores = new HashMap<Integer,Float>();
      List<Map<Integer,Float>> clusters = new ArrayList<Map<Integer,Float>>();
      for(int j=0;j<queries.size();j++) {
        clusters.add(new HashMap<Integer,Float>());
        VectorCollector vc = new VectorCollector();
        is.search(queries.get(j), vc);
        //System.out.println(vc.getResultsVector());
        for(Integer k : vc.getResultsVector().keySet()) {
          float score = vc.getResultsVector().get(k);
          if(score < 0.001) continue;
          if(!bestClusterScores.containsKey(k) || bestClusterScores.get(k) < score) {
            bestClusters.put(k, j);
            bestClusterScores.put(k, score);
          }
        }
      }
      for(Integer j : bestClusters.keySet()) {
        clusters.get(bestClusters.get(j)).put(j, bestClusterScores.get(j));
      }
      //for(Map<Integer,Float> cluster : clusters) System.out.println(cluster);
      queries.clear();
      for(int j=0;j<clusters.size();j++) {
        System.out.println("Size: " + clusters.get(j).size());
        /*if(i == 9) {
          for(Integer k : clusters.get(j).keySet()) {
            System.out.println(docFiles.get(k) + "\t" + bestClusterScores.get(k));
          }
        }*/
        //if(i == 9) ClusterAnalyser.excessAnalyseCluster(clusters.get(j), lis.getIndexReader(), 0.2, true);
        Map<String,Double> scores = ClusterAnalyser.simpleExcessAnalyseCluster(clusters.get(j), lis.getIndexReader(), 0.1);
        BooleanQuery bq = new BooleanQuery(false);
        List<String> terms = StringTools.getSortedList(scores);
        if(terms.size() > 20) terms = terms.subList(0, 20);
        for(String s : terms) {
          System.out.println(s + "\t" + scores.get(s));
          TermQuery tq = new TermQuery(new Term("txt", s));
          tq.setBoost(scores.get(s).floatValue());
          bq.add(new BooleanClause(tq, Occur.SHOULD));
        }
        System.out.println();
        queries.add(bq);
      }
      System.out.println();
    }
    List<Map<Integer,Float>> clusters = new ArrayList<Map<Integer,Float>>();
    final Map<Integer,Integer> clusterSizes = new HashMap<Integer,Integer>();
    for(int j=0;j<queries.size();j++) {
      VectorCollector vc = new VectorCollector();
      is.search(queries.get(j), vc);
      final Map<Integer,Float> cluster = new HashMap<Integer,Float>();
      //System.out.println(vc.getResultsVector());
      for(Integer k : vc.getResultsVector().keySet()) {
        float score = vc.getResultsVector().get(k);
        if(score < 0.2) continue;
        cluster.put(k, score);
      }
      clusters.add(cluster);
      clusterSizes.put(j, cluster.size());
View Full Code Here
66
67
68
69
70
71
72
73
74
75
76
77
78
      if(s.matches("\\S+")) {
        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));
        VectorCollector vc = new VectorCollector();
        is.search(pq, vc);
        docFreq = vc.getResultsVector().size();
      }
      double idf = Math.log(numDocs) - Math.log(docFreq);
      tfIdf.put(s, tf.getCount(s) * idf);
    }
    for(String s : StringTools.getSortedList(tfIdf)) {
View Full Code Here
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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
      } 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);           
        }
      }
     
      Map<String,Set<String>> ontQs = OBOOntology.getInstance().queriesForIds(onts);
     
      for(String ontQ : ontQs.keySet()) {
        /*BooleanQuery bq = new BooleanQuery(true);
        if(ontQs.get(ontQ).size() > BooleanQuery.getMaxClauseCount()) continue;
        for(String ont : ontQs.get(ontQ)) {
          bq.add(new BooleanClause(new TermQuery(new Term("Ontology", ont)), Occur.SHOULD));
        }
        VectorCollector vc = new VectorCollector();
        is.search(bq, vc);*/
        VectorCollector vc = OntologyQueryCache.getResultsStatic(ontQ, ontQs.get(ontQ), is);
        Map<Integer,Float> results = vc.getResultsVector();
        double expected = scaleFactor * results.size();
        int overlap = overlapDocs(vc.getResultsVector(), cluster);
        if(overlap < 2) continue;
        double excess = overlap - expected;
        double score = excess / clusterSize;
        if(score > threshold) {
          String s = ontQ + " " + OBOOntology.getInstance().getNameForID(ontQ);
View Full Code Here
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
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
    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);           
          }
        }
      }
     
      Map<String,Set<String>> ontQs = OBOOntology.getInstance().queriesForIds(onts);
     
      for(String ontQ : ontQs.keySet()) {
        BooleanQuery bq = new BooleanQuery(true);
        if(ontQs.get(ontQ).size() > BooleanQuery.getMaxClauseCount()) continue;
        for(String ont : ontQs.get(ontQ)) {
          bq.add(new BooleanClause(new TermQuery(new Term("Ontology", ont)), Occur.SHOULD));
        }
        VectorCollector vc = new VectorCollector();
        is.search(bq, vc);
        double score = similarity.similarity(cluster, vc.getResultsVector());
        if(score > threshold) {
          int overlap = overlapDocs(vc.getResultsVector(), cluster);
          if(overlap > 1) {
            String s = ontQ + " " + OBOOntology.getInstance().getNameForID(ontQ);
            scores.put(s, score);
            overlaps.put(s, overlap);           
          }
View Full Code Here
TOP

Related Classes of uk.ac.cam.ch.wwmm.oscar3.flow.OscarFlow

  • jregex.Pattern
  • nu.xom.Attribute
  • nu.xom.Builder
  • nu.xom.Document
  • nu.xom.Element
  • nu.xom.Elements
  • nu.xom.Node
  • nu.xom.Nodes
  • nu.xom.Serializer
  • opennlp.maxent.Event
    • 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.