Java ClassicCounter.setCount方法代码示例

import edu.stanford.nlp.stats.ClassicCounter; //导入方法依赖的package包/类
/**
 * Calculate sister annotation statistics suitable for doing
 * selective sister splitting in the PCFGParser inside the
 * FactoredParser.
 *
 * @param args One argument: path to the Treebank
 */
public static void main(String[] args) {

  ClassicCounter<String> c = new ClassicCounter<String>();
  c.setCount("A", 0);
  c.setCount("B", 1);

  double d = Counters.klDivergence(c, c);
  System.out.println("KL Divergence: " + d);


  String encoding = "UTF-8";
  if (args.length > 1) {
    encoding = args[1];
  }
  if (args.length < 1) {
    System.out.println("Usage: ParentAnnotationStats treebankPath");
  } else {
    SisterAnnotationStats pas = new SisterAnnotationStats();
    Treebank treebank = new DiskTreebank(new TreeReaderFactory() {
      public TreeReader newTreeReader(Reader in) {
        return new PennTreeReader(in, new LabeledScoredTreeFactory(new StringLabelFactory()), new BobChrisTreeNormalizer());
      }
    }, encoding);
    treebank.loadPath(args[0]);
    treebank.apply(pas);
    pas.printStats();
  }
}
 

import edu.stanford.nlp.stats.ClassicCounter; //导入方法依赖的package包/类
public UnknownWordModel finishTraining() {
  if (useGT) {
    unknownGTTrainer.finishTraining();
  }
  
  for (Label tag : c.keySet()) {
    /* outer iteration is over tags */
    ClassicCounter<String> wc = c.get(tag); // counts for words given a tag
    
    if (!tagHash.containsKey(tag)) {
      tagHash.put(tag, new ClassicCounter<String>());
    }
    
    /* the UNKNOWN sequence is assumed to be seen once in each tag */
    // This is sort of broken, but you can regard it as a Dirichlet prior.
    tc.incrementCount(tag);
    wc.setCount(unknown, 1.0);
    
    /* inner iteration is over words */
    for (String end : wc.keySet()) {
      double prob = Math.log((wc.getCount(end)) / (tc.getCount(tag)));  // p(sig|tag)
      tagHash.get(tag).setCount(end, prob);
      //if (Test.verbose)
      //EncodingPrintWriter.out.println(tag + " rewrites as " + end + " endchar with probability " + prob,encoding);
    }
  }

  return model;
}
 

import edu.stanford.nlp.stats.ClassicCounter; //导入方法依赖的package包/类
public UnknownWordModel finishTraining() {
  Map<String,Float> unknownGT = null;
  if (useGT) {
    unknownGTTrainer.finishTraining();
    unknownGT = unknownGTTrainer.unknownGT;
  }
  
  for (Label tagLab : c.keySet()) {
    // outer iteration is over tags as Labels
    ClassicCounter<String> wc = c.get(tagLab); // counts for words given a tag
    
    if ( ! tagHash.containsKey(tagLab)) {
      tagHash.put(tagLab, new ClassicCounter<String>());
    }
    
    // the UNKNOWN first character is assumed to be seen once in
    // each tag
    // this is really sort of broken!  (why??)
    tc.incrementCount(tagLab);
    wc.setCount(unknown, 1.0);
    
    // inner iteration is over words  as strings
    for (String first : wc.keySet()) {
      double prob = Math.log(((wc.getCount(first))) / tc.getCount(tagLab));
      tagHash.get(tagLab).setCount(first, prob);
      //if (Test.verbose)
      //EncodingPrintWriter.out.println(tag + " rewrites as " + first + " firstchar with probability " + prob,encoding);
    }
  }

  return model;
}
 

import edu.stanford.nlp.stats.ClassicCounter; //导入方法依赖的package包/类
public UnknownWordModel finishTraining() {
  HashMap<String,Float> unknownGT = null;
  if (useGT) {
    unknownGTTrainer.finishTraining();
    unknownGT = unknownGTTrainer.unknownGT;
  }
  
  for (Label tagLab : c.keySet()) {
    // outer iteration is over tags as Labels
    ClassicCounter<String> wc = c.get(tagLab); // counts for words given a tag
    
    if ( ! tagHash.containsKey(tagLab)) {
      tagHash.put(tagLab, new ClassicCounter<String>());
    }
    
    // the UNKNOWN first character is assumed to be seen once in
    // each tag
    // this is really sort of broken!  (why??)
    tc.incrementCount(tagLab);
    wc.setCount(unknown, 1.0);
    
    // inner iteration is over words  as strings
    for (String first : wc.keySet()) {
      double prob = Math.log(((wc.getCount(first))) / tc.getCount(tagLab));
      tagHash.get(tagLab).setCount(first, prob);
      //if (Test.verbose)
      //EncodingPrintWriter.out.println(tag + " rewrites as " + first + " firstchar with probability " + prob,encoding);
    }
  }

  return model;
}