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

uk.ac.cam.ch.wwmm.oscar3.recogniser.document.NamedEntity
This runs Oscar modules on SciXML Documents. You put the SciXML in with the constructor, call methods to run the modules, and then use getter methods to get various Documents back. @author ptc24

    //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

    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

  // 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

    }    
  }


  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

      }
      return;
    }
    
    if(mode.equals("BuildPubChem")) {
      new NewPubChem().initialise();
      return;
    }
    
    if(mode.equals("Server")) {
      if(Oscar3Props.getInstance().serverType.equals("none")) {

View Full Code Here

    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

    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

        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

          } 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

  
  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

0 1 2 3 4 5 6 7 8 9

TOP

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

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.