Package opennlp.maxent

Examples of opennlp.maxent.Event

269
270
271
272
273
274
275
276
277
278
279
280
281
282
    ce = new ClassificationEvaluator();
    List<Event> trainEvents = new ArrayList<Event>();
    List<Event> testEvents = new ArrayList<Event>();
    for(BagEvent be : bagEvents) {
      trainEvents.add(new Event(be.getClassLabel(), be.getFeatures().getSet().toArray(new String[0])));
    }
    for(BagEvent be : testBagEvents) {
      testEvents.add(new Event(be.getClassLabel(), be.getFeatures().getSet().toArray(new String[0])));
    }
    DataIndexer di = new TwoPassDataIndexer(new EventCollectorAsStream(new SimpleEventCollector(trainEvents)), 1);
    GISModel gm = GIS.trainModel(100, di);
   
    //ClassificationEvaluator ce = new ClassificationEvaluator();
View Full Code Here
138
139
140
141
142
143
144
145
146
147
148
    for(String word : trainSet) {
      Collection<String> f = overallFeatures.get(word);
      //System.out.println(f);
      String type = chemFeatures.containsKey(word) ? "CHEM" : "NONCHEM";

      Event event = new Event(type, f.toArray(new String[0]));
      events.add(event);
    }
    if(events.size() == 1) events.add(events.get(0));
    DataIndexer di = new TwoPassDataIndexer(new EventCollectorAsStream(new SimpleEventCollector(events)), 3);
    GISModel gm = GIS.trainModel(100, di);
View Full Code Here
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
        //tokenSet.remove(stemmer.getStem(s));
        tokenSet.add("PROTECT:" + s);
        tokenSet.add("PROTECT:stem=" + stemmer.getStem(s));
      }
      if(hasPotentialReact) {
        Event e = new Event(hasReact ? "TRUE" : "FALSE", tokenSet.toArray(new String[0]));
        events.add(e);
        BagEvent be = new BagEvent(hasReact ? "TRUE" : "FALSE", tokenBag);
        eventBags.add(be);
      }
    }
       
    if(false) {
      ClassificationEvaluator ce = new ClassificationEvaluator();

      MultinomialNaiveBayes mnb = new MultinomialNaiveBayes(eventBags);
      for(int i=0;i<eventBags.size();i++) {
        BagEvent be = eventBags.get(i);
      //for(BagEvent be : eventBags) {
        Map<String,Double> results = mnb.testBag(be.getClassLabel(), be.getFeatures());
        System.out.println(be.getClassLabel() + "\t" + mnb.testBag(be.getFeatures()));
        ce.logEvent(be.getClassLabel(), mnb.bestResult(results));
        String rf = "MNB:" + mnb.bestResult(results);
        Event e = events.get(i);
        String [] sa = new String[e.getContext().length + 1];
        for(int j=0;j<e.getContext().length;j++) {
          sa[j] = e.getContext()[j];
        }
        sa[e.getContext().length] = rf;
        events.set(i, new Event(e.getOutcome(), sa));
      }
      System.out.println(ce.getAccuracy());
      System.out.println(ce.getKappa());     
      ce.pprintConfusionMatrix();
      ce.pprintPrecisionRecallEval();
View Full Code Here
333
334
335
336
337
338
339
340
341
342
343
    classifiers = new HashMap<String,GISModel>();
    for(String type : trainingData.keySet()) {
      List<Event> events = new ArrayList<Event>();
      for(String subtype : trainingData.get(type).keySet()) {
        for(List<String> features : trainingData.get(type).get(subtype)) {
          Event ev = new Event(subtype, features.toArray(new String[0]));
          events.add(ev);
        }
      }
      if(events.size() < 2) continue;
      DataIndexer di = null;
View Full Code Here
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
   
    List<Event> events = new ArrayList<Event>();
    for(String s : batch1) {
      String outcome = "E";
      if(isChem.get(s)) outcome = "C";
      events.add(new Event(outcome, getFeatures(s)));
    }
    SimpleEventCollector sec = new SimpleEventCollector(events);
    DataIndexer di = new TwoPassDataIndexer(new EventCollectorAsStream(sec), 1);
    GISModel gis = GIS.trainModel(100, di);
   
    System.out.println(gis.getIndex("FOO"));
    if(true) return;
   
   
    long time = System.currentTimeMillis();
    StringGISModelWriter sgmw = new StringGISModelWriter(gis);
    sgmw.persist();
    String modelStr = sgmw.toString();

    //System.out.println(modelStr);
   
    StringGISModelReader sgmr = new StringGISModelReader(modelStr);
    gis = sgmr.getModel();
    System.out.println("Round trip in " + (System.currentTimeMillis() - time));
    System.out.println(modelStr.length());
   
    //if(true) return;
   
    GISModel gis2 = null;
   
    if(false) {
      List<Event> events2 = new ArrayList<Event>();
      for(String s : batch2) {
        double prob = gis.eval(getFeatures(s))[gis.getIndex("C")];
        String outcome = "E";
        if(isChem.get(s)) outcome = "C";
        events.add(new Event(outcome, probToFeatures(prob)));
      }
      sec = new SimpleEventCollector(events);
      di = new TwoPassDataIndexer(new EventCollectorAsStream(sec), 2);
      gis2 = GIS.trainModel(1000, di);     
    }
View Full Code Here
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
      for(Entry e : entriesByFileName.get(fn)) {
        Token t = procDoc.getTokenByStart(e.start);
        if(t != null) {
          List<String> features = featuresForToken(t);
          Event event = new Event(e.type, features.toArray(new String[0]));
          events.add(event);
        }
      }
      //System.out.println(nr.tokensByEnd);
    }
   
    Collections.shuffle(events, new Random(5));
   
    List<Event> trainData = events.subList(0, events.size()/2);
    List<Event> testData = events.subList(events.size()/2, events.size());
   
    if(trainData.size() == 1) trainData.add(trainData.get(0));
    DataIndexer di = new TwoPassDataIndexer(new EventCollectorAsStream(new SimpleEventCollector(trainData)), 1);
    GISModel gm = GIS.trainModel(100, di);
   
    ClassificationEvaluator ce = new ClassificationEvaluator();
   
    for(Event event : testData) {
      double [] results = gm.eval(event.getContext());
      String result = gm.getBestOutcome(results);
      System.out.println(event.getOutcome() + "\t" + result + "\t" + results[gm.getIndex(event.getOutcome())] + "\t" + StringTools.arrayToList(event.getContext()));
      ce.logEvent(event.getOutcome(), result);
    }
    System.out.println(ce.getAccuracy());
    System.out.println(ce.getKappa());
    ce.pprintConfusionMatrix();
    ce.pprintPrecisionRecallEval();
View Full Code Here
291
292
293
294
295
296
297
298
299
300
301
302
303
304
    if(false) {
      ce = new ClassificationEvaluator();
      List<Event> trainEvents = new ArrayList<Event>();
      List<Event> testEvents = new ArrayList<Event>();
      for(BagEvent be : bagEvents) {
        trainEvents.add(new Event(be.getClassLabel(), be.getFeatures().getSet().toArray(new String[0])));
      }
      for(BagEvent be : testBagEvents) {
        testEvents.add(new Event(be.getClassLabel(), be.getFeatures().getSet().toArray(new String[0])));
      }
      DataIndexer di = new TwoPassDataIndexer(new EventCollectorAsStream(new SimpleEventCollector(trainEvents)), 1);
      GISModel gm = GIS.trainModel(100, di);
     
      //ClassificationEvaluator ce = new ClassificationEvaluator();
View Full Code Here
42
43
44
45
46
47
48
        words.add(st.getStem(termArray[j]).intern());
        words.add(termArray[j].intern());
      }
    }
    String c = hasCue ? "TRUE" : "FALSE";
    return new Event(c, words.toArray(new String[0]));
  }
View Full Code Here
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
    Map<String,Double> byProb = new HashMap<String,Double>();
    Map<String,String> res = new HashMap<String,String>();
    int mp = 0;
    int mn = 0;
    for(int i=numDocs/2;i<numDocs;i++) {
      Event e = docToEvent(ir, i, c);
      //System.out.println(gm.getBestOutcome(gm.eval(e.getContext())));
      double prob = gm.eval(e.getContext())[gm.getIndex("TRUE")];
      //System.out.println(ir.document(i).getField("filename").stringValue().replaceAll("markedup", "source"));
      String name = ir.document(i).getField("filename").stringValue().replaceAll("markedup", "source");
      byProb.put(name, prob);
      res.put(name, e.getOutcome());
      if(e.getOutcome().equals("TRUE")) {
        mp++;
      } else {
        mn++;
      }
    }
View Full Code Here
116
117
118
119
120
121
122
123
124
125
126
      List<String> features = new ArrayList<String>();
      for(int i=0;i<event.getContext().length;i++) {
        String feature = event.getContext()[i];
        if(allowableFeatures.contains(feature)) features.add(feature);
      }
      Event newEvent = new Event(event.getOutcome(), features.toArray(new String[0]));
      newEvents.add(newEvent);
    }

    if(Oscar3Props.getInstance().verbose) System.out.println("Selected " + allowableFeatures.size() + " features from " + featureCounts.size());
    return newEvents;
View Full Code Here
TOP

Related Classes of opennlp.maxent.Event

  • opennlp.tools.chunker.ChunkerEventStream
  • opennlp.tools.coref.resolver.DefaultNonReferentialResolver
  • opennlp.tools.coref.resolver.MaxentResolver
  • opennlp.tools.coref.sim.GenderModel
  • opennlp.tools.coref.sim.NumberModel
  • opennlp.tools.coref.sim.SimilarityModel
  • opennlp.tools.namefind.NameFinderEventStream
  • opennlp.tools.parser.ParserEventStream
  • opennlp.tools.postag.POSEventCollector
  • opennlp.tools.tokenize.TokEventCollector
    • 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.