Package opennlp.maxent

Examples of opennlp.maxent.EventCollectorAsStream

205
206
207
208
209
210
211
212
  public static void train(String[] args) throws IOException {
      FileReader datafr = new FileReader(new File(args[0]));
      File output = new File(args[1]);
      EventStream evc =
        new EventCollectorAsStream(new TokEventCollector(datafr));
      train(evc, output);
  }
View Full Code Here
173
174
175
176
177
178
179
180
181
    modelsByType = new HashMap<String,GISModel>();
    for(String type : eventsByType.keySet()) {
      DataIndexer di = null;
      List<Event> evs = eventsByType.get(type);
      if(evs.size() == 1) evs.add(evs.get(0));
      di = new TwoPassDataIndexer(new EventCollectorAsStream(new SimpleEventCollector(evs)), 1);
      modelsByType.put(type, GIS.trainModel(trainingCycles, di));
    }
  }
View Full Code Here
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
    if(useUber) {
      List<Event> evs = new ArrayList<Event>();
      for(String prevTagg : evsByPrev.keySet()) {
        evs.addAll(evsByPrev.get(prevTagg));
      }
      DataIndexer di = new TwoPassDataIndexer(new EventCollectorAsStream(new SimpleEventCollector(evs)), featureCutOff);
      ubermodel = GIS.trainModel(trainingCycles, di);
    } else {
      for(String prevTagg : evsByPrev.keySet()) {
        if(Oscar3Props.getInstance().verbose) System.out.println(prevTagg);
        List<Event> evs = evsByPrev.get(prevTagg);
        if(featureSel) {
          evs = new FeatureSelector().selectFeatures(evs);           
        }   
        if(evs.size() == 1) {
          evs.add(evs.get(0));
        }
        DataIndexer di = null;
        try {
          di = new TwoPassDataIndexer(new EventCollectorAsStream(new SimpleEventCollector(evs)), featureCutOff);
          gmByPrev.put(prevTagg, GIS.trainModel(trainingCycles, di));
        } catch (Exception e) {
          di = new TwoPassDataIndexer(new EventCollectorAsStream(new SimpleEventCollector(evs)), 1);       
          gmByPrev.put(prevTagg, GIS.trainModel(trainingCycles, di));
        } 
      }
    }
  }
View Full Code Here
274
275
276
277
278
279
280
281
282
283
284
      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();
   
    for(Event event : testEvents) {
View Full Code Here
142
143
144
145
146
147
148
149
150
151
152
      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);
   
    ClassificationEvaluator ce = new ClassificationEvaluator();

    List<Double> chemList = new ArrayList<Double>();
View Full Code Here
141
142
143
144
145
146
147
148
149
150
151
      List<Event> trainData = events.subList(0, events.size()/2);
      //trainData = new FeatureSelector().selectFeatures(trainData, 200.0);
      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) {
View Full Code Here
339
340
341
342
343
344
345
346
347
348
349
          events.add(ev);
        }
      }
      if(events.size() < 2) continue;
      DataIndexer di = null;
      di = new TwoPassDataIndexer(new EventCollectorAsStream(new SimpleEventCollector(events)), 1);
      if(Oscar3Props.getInstance().verbose) System.out.println(di);
      GISModel gm = GIS.trainModel(100, di);
      classifiers.put(type, gm);
    }
  }
View Full Code Here
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
      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);     
    }
   
    double score = 0.0;
    List<Double> trialScores = new ArrayList<Double>();
View Full Code Here
131
132
133
134
135
136
137
138
139
140
141
   
    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) {
View Full Code Here
296
297
298
299
300
301
302
303
304
305
306
        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();
     
      for(Event event : testEvents) {
View Full Code Here
TOP

Related Classes of opennlp.maxent.EventCollectorAsStream

  • opennlp.tools.tokenize.TokenizerME
  • uk.ac.cam.ch.wwmm.oscar3.recogniser.memm.MEMM
  • uk.ac.cam.ch.wwmm.oscar3.recogniser.memm.rescorer.RescoreMEMMOut
  • uk.ac.cam.ch.wwmm.oscar3.subtypes.NESubtypes
  • uk.ac.cam.ch.wwmm.ptc.experimental.Attenuation
  • uk.ac.cam.ch.wwmm.ptc.experimental.DomainParaClassify
  • uk.ac.cam.ch.wwmm.ptc.experimental.indexersearcher.classify.DocClassifier
  • uk.ac.cam.ch.wwmm.ptc.experimental.ReactDocClassify
  • uk.ac.cam.ch.wwmm.ptc.experimental.ReactParaClassify
  • uk.ac.cam.ch.wwmm.ptc.experimental.WSD
    • 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.