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

Examples of uk.ac.cam.ch.wwmm.oscar3.indexersearcher.LuceneIndexerSearcher

453
454
455
456
457
458
459
460
461
462
463
464
465
    //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);
    //q = pq;
    VectorCollector vc = new VectorCollector();
    is.search(q, vc);
    Map<String,Double> scores = simpleExcessAnalyseCluster(vc.getResultsVector(), lis.getIndexReader(), 0.01);
    for(String s : StringTools.getSortedList(scores)) {
      System.out.println(s + "\t" + scores.get(s));
    }

    //tfIdfAnalyseCluster(vc.getResultsVector(), lis.getIndexReader());
View Full Code Here
170
171
172
173
174
175
176
177
178
179
180
    String normWord = StringTools.normaliseName(word);
    if (!word.equals(normWord)) {
      contextable.add(makeWordFeature(normWord));
    }

    ExtractTrainingData etd = ExtractTrainingData.getInstance();
    makeWordFeatures(word, normWord, bigramable, etd);
    makeReactionFeatures(word, bigramable, contextable, etd);

    String wts = StringTools.removeTerminalS(normWord);
    contextable.add(WITHOUT_TERMINAL_S_FEATURE + wts);
View Full Code Here
32
33
34
35
36
37
38
39
40
41
42
43
44
45
  // I'm sure there's a nice analytic way of doing this. Ah well...
  public static void main(String[] args) {
    List<Double> positiveExamples = new ArrayList<Double>();
    List<Double> negativeExamples = new ArrayList<Double>();
   
    ExtractTrainingData etd1 = ExtractTrainingData.getInstance();
    List<File> sbFiles = new ArrayList<File>();
    sbFiles.addAll(FileTools.getFilesFromDirectoryByName(new File("/home/ptc24/newows/goodrsc"), "scrapbook.xml"));
    ExtractTrainingData etd2 = new ExtractTrainingData(sbFiles);
    Set<String> chem = new HashSet<String>(etd2.chemicalWords);
    //chem.removeAll(etd1.chemicalWords);
    for(String w : chem) {
      if(!NGramBuilder.getInstance().chemSet.contains(NGram.parseWord(w))) {
        double score = NGram.getInstance().testWord(w);
View Full Code Here
306
307
308
309
310
311
312
313
314
315
316
317
318
    }   
  }

  private boolean resolveVsNewPubChem(ProcessState state, String name) {
    try {
      NewPubChem npc = NewPubChem.getInstance();
      if(npc != null) {
        String [] results = npc.getShortestSmilesAndInChI(name);
        if(results == null) return false;
        state.smiles = results[0];
        state.inchi = results[1];
        if(state.smiles != null) setNEAttribute(state.ne, "SMILES", state.smiles);
        if(state.inchi != null) setNEAttribute(state.ne, "InChI", state.inchi);
View Full Code Here
383
384
385
386
387
388
389
390
391
392
393
      }
      return;
    }
   
    if(mode.equals("BuildPubChem")) {
      new NewPubChem().initialise();
      return;
    }
   
    if(mode.equals("Server")) {
      if(Oscar3Props.getInstance().serverType.equals("none")) {
View Full Code Here
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
    String type = a.type;
    //System.out.println(surface + " " + a.type);
    if(type.contains("_")) {
      type = type.split("_")[0];
    }
    NamedEntity ne = new NamedEntity(t.getTokens(a.startToken, endToken), surface, type);
    assert(collector instanceof NECollector);
    ((NECollector)collector).collect(ne);
    //System.out.println(surface + ": " + a.reps);
    if(a.type.startsWith("ONT")) {
      Set<String> ontIds = runAutToStateToOntIds.get(a.type).get(a.state);
      String s = OntologyTerms.idsForTerm(surface);
      if(s != null && s.length() > 0) {
        if(ontIds == null) ontIds = new HashSet<String>();
        ontIds.addAll(StringTools.arrayToList(s.split("\\s+")));       
      }
      ne.addOntIds(ontIds);
      //System.out.println(surface + "\t" + ontIds);
    }
    if(a.type.startsWith("CUST")) {
      Set<String> custTypes = runAutToStateToOntIds.get(a.type).get(a.state);
      ne.addCustTypes(custTypes);
      //System.out.println(surface + "\t" + ontIds);
    }
    //ne.setPattern(StringTools.collectionToString(a.getReps(), "_"));
  }
View Full Code Here
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
    String type = a.type;
    //System.out.println(surface + " " + a.type);
    if(type.contains("_")) {
      type = type.split("_")[0];
    }
    NamedEntity ne = new NamedEntity(t.getTokens(a.startToken, endToken), surface, type);
    assert(collector instanceof NECollector);
    ((NECollector)collector).collect(ne);
    //System.out.println(surface + ": " + a.reps);
    if(a.type.startsWith("ONT")) {
      Set<String> ontIds = runAutToStateToOntIds.get(a.type).get(a.state);
      String s = OntologyTerms.idsForTerm(StringTools.normaliseName(surface));
      if(s != null && s.length() > 0) {
        if(ontIds == null) ontIds = new HashSet<String>();
        ontIds.addAll(StringTools.arrayToList(s.split("\\s+")));       
      }
      ne.addOntIds(ontIds);
      //System.out.println(surface + "\t" + ontIds);
    }
    if(a.type.startsWith("CUST")) {
      //System.out.println(runAutToStateToOntIds.get(a.type));
      Set<String> custTypes = runAutToStateToOntIds.get(a.type).get(a.state);
      ne.addCustTypes(custTypes);
      //System.out.println(surface + "\t" + ontIds);
    }

    //ne.setPattern(StringTools.collectionToString(a.getReps(), "_"));
  }
View Full Code Here
68
69
70
71
72
73
74
75
76
77
78
79
        String value = token.getValue();
        value = value.toLowerCase();
        if(prwStrings.contains(value)) {
          List<Token> neTokens = new ArrayList<Token>();
          neTokens.add(token);
          NamedEntity ne = new NamedEntity(neTokens, token.getValue(), "PRW");
          safholder.appendChild(ne.toSAF());
          //System.out.println("**********");
        }
      }
      //System.out.println();
    }
 
View Full Code Here
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
          } else {
            featuresForAbbrev = new ArrayList<String>();
            abbrevFeatures.put(ne.getSurface(), featuresForAbbrev);
          }
          if(neByLastToken.containsKey(prev2)) {
            NamedEntity maybeAbbrev = neByLastToken.get(prev2);
            String abbrMode = "abbr1:";
            if(StringTools.testForAcronym(surf, maybeAbbrev.getSurface())) {
              abbrMode = "abbr2:";
            }
            if(surf.matches(".*\\s.*")) abbrMode += "wws:";
            for(double lthresh = -5.0;lthresh < 5.05;lthresh += 0.5) {
              double thresh = logitToProb(lthresh);
              if(maybeAbbrev.getConfidence() > thresh) {
                featuresForAbbrev.add(abbrMode + "abbr>" + thresh);
              } else {
                featuresForAbbrev.add(abbrMode + "abbr<" + thresh);
              }             
            }
View Full Code Here
216
217
218
219
220
221
222
 
  private static NamedEntity makeNE(List<Token> neTokens, String neType) {
    Token firstToken = neTokens.get(0);
    Token lastToken = neTokens.get(neTokens.size()-1);
    String surf = firstToken.getTokenSequence().getSubstring(firstToken.getId(), lastToken.getId());
    return new NamedEntity(neTokens, surf, "GENIA-" + neType);
  }
View Full Code Here
TOP

Related Classes of uk.ac.cam.ch.wwmm.oscar3.indexersearcher.LuceneIndexerSearcher

  • 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.