Java Counters.toSortedList方法代码示例

import edu.stanford.nlp.stats.Counters; //导入方法依赖的package包/类
/**
 * Returns a list of featured thresholded by minPrecision and sorted by their frequency of occurrence.
 * precision in this case, is defined as the frequency of majority label over total frequency for that feature.
 * @return list of high precision features.
 */
private List<F> getHighPrecisionFeatures(GeneralDataset<L,F> dataset, double minPrecision, int maxNumFeatures){
  int[][] feature2label = new int[dataset.numFeatures()][dataset.numClasses()];
  for(int f = 0; f < dataset.numFeatures(); f++)
    Arrays.fill(feature2label[f],0);

  int[][] data = dataset.data;
  int[] labels = dataset.labels;
  for(int d = 0; d < data.length; d++){
    int label = labels[d];
    //System.out.println("datum id:"+d+" label id: "+label);
    if(data[d] != null){
      //System.out.println(" number of features:"+data[d].length);
      for(int n = 0; n < data[d].length; n++){
        feature2label[data[d][n]][label]++;
      }
    }
  }
  Counter<F> feature2freq = new ClassicCounter<F>();
  for(int f = 0; f < dataset.numFeatures(); f++){
   int maxF = ArrayMath.max(feature2label[f]);
   int total = ArrayMath.sum(feature2label[f]);
   double precision = ((double)maxF)/total;
   F feature = dataset.featureIndex.get(f);
   if(precision >= minPrecision){
     feature2freq.incrementCount(feature, total);
   }
  }
  if(feature2freq.size() > maxNumFeatures){
    Counters.retainTop(feature2freq, maxNumFeatures);
  }
  //for(F feature : feature2freq.keySet())
    //System.out.println(feature+" "+feature2freq.getCount(feature));
  //System.exit(0);
  return Counters.toSortedList(feature2freq);
}
 

import edu.stanford.nlp.stats.Counters; //导入方法依赖的package包/类
/**
 * Run the classifier on the documents in an ObjectBank, and print the
 * answers to a given PrintWriter (with timing to stderr). The value of
 * flags.documentReader is used to determine testFile format.
 *
 * @param documents The ObjectBank to test on.
 */
public void classifyAndWriteAnswersKBest(ObjectBank<List<IN>> documents, int k, PrintWriter printWriter,
                                         DocumentReaderAndWriter<IN> readerAndWriter) throws IOException {
  Timing timer = new Timing();
  int numWords = 0;
  int numSentences = 0;

  for (List<IN> doc : documents) {
    Counter<List<IN>> kBest = classifyKBest(doc, CoreAnnotations.AnswerAnnotation.class, k);
    numWords += doc.size();
    List<List<IN>> sorted = Counters.toSortedList(kBest);
    int n = 1;
    for (List<IN> l : sorted) {
      System.out.println("<sentence id=" + numSentences + " k=" + n + " logProb=" + kBest.getCount(l) + " prob="
          + Math.exp(kBest.getCount(l)) + '>');
      writeAnswers(l, printWriter, readerAndWriter);
      System.out.println("</sentence>");
      n++;
    }
    numSentences++;
  }

  long millis = timer.stop();
  double wordspersec = numWords / (((double) millis) / 1000);
  NumberFormat nf = new DecimalFormat("0.00"); // easier way!
  System.err.println(this.getClass().getName() + " tagged " + numWords + " words in " + numSentences
      + " documents at " + nf.format(wordspersec) + " words per second.");
}
 

import edu.stanford.nlp.stats.Counters; //导入方法依赖的package包/类
private static <E> void appendIntCountStats(StringBuilder sb, String label, IntCounter<E> counts)
{
  sb.append(label).append("\n");
  List<E> sortedKeys = Counters.toSortedList(counts);
  int total = counts.totalIntCount();
  for (E key:sortedKeys) {
    int count = counts.getIntCount(key);
    appendFrac(sb, key.toString(), count, total);
    sb.append("\n");
  }
}