Java DocumentReaderAndWriter类代码示例

import edu.stanford.nlp.sequences.DocumentReaderAndWriter; //导入依赖的package包/类
/**
 * Train a model given a preprocessor.
 * 
 * @param preProcessor
 */
protected void train(Preprocessor preProcessor) {
  DocumentReaderAndWriter<CoreLabel> docReader = 
      new ProcessorTools.PostprocessorDocumentReaderAndWriter(preProcessor);
  ObjectBank<List<CoreLabel>> lines =
    classifier.makeObjectBankFromFile(flags.trainFile, docReader);

  classifier.train(lines, docReader);
  System.err.println("Finished training.");
}
 

import edu.stanford.nlp.sequences.DocumentReaderAndWriter; //导入依赖的package包/类
/**
 * @param filename adaptation file
 * @param trainDataset original dataset (used in training)
 */
public void adapt(String filename, Dataset<String, String> trainDataset,
                  DocumentReaderAndWriter<IN> readerWriter) {
  flags.ocrTrain = false;  // ?? Do we need this? (Pi-Chuan Sat Nov  5 15:42:49 2005)
  ObjectBank<List<IN>> docs =
    makeObjectBankFromFile(filename, readerWriter);
  adapt(docs, trainDataset);
}
 

import edu.stanford.nlp.sequences.DocumentReaderAndWriter; //导入依赖的package包/类
@SuppressWarnings("unchecked")
public static void main(String[] args) throws Exception {
  Properties props = StringUtils.argsToProperties(args);
  NumberSequenceClassifier nsc =
    new NumberSequenceClassifier(props, true, props);
  String trainFile = nsc.flags.trainFile;
  String testFile = nsc.flags.testFile;
  String textFile = nsc.flags.textFile;
  String loadPath = nsc.flags.loadClassifier;
  String serializeTo = nsc.flags.serializeTo;

  if (loadPath != null) {
    nsc.loadClassifierNoExceptions(loadPath);
    nsc.flags.setProperties(props);
  } else if (trainFile != null) {
    nsc.train(trainFile);
  }

  if (serializeTo != null) {
    nsc.serializeClassifier(serializeTo);
  }

  if (testFile != null) {
    nsc.classifyAndWriteAnswers(testFile, nsc.makeReaderAndWriter());
  }

  if (textFile != null) {
    DocumentReaderAndWriter readerAndWriter =
      new PlainTextDocumentReaderAndWriter();
    nsc.classifyAndWriteAnswers(textFile, readerAndWriter);
  }
}
 

import edu.stanford.nlp.sequences.DocumentReaderAndWriter; //导入依赖的package包/类
public static String classifyToString(List<CoreMap> sentence, DocumentReaderAndWriter<CoreMap> readerAndWriter, AbstractSequenceClassifier classif) {
  PlainTextDocumentReaderAndWriter.OutputStyle outFormat =
    PlainTextDocumentReaderAndWriter.OutputStyle.fromShortName("inlineXML");

  DocumentReaderAndWriter<CoreMap> tmp = readerAndWriter;
  readerAndWriter = new PlainTextDocumentReaderAndWriter<CoreMap>();
  readerAndWriter.init(classif.flags);

  StringBuilder sb = new StringBuilder();
  sb.append(((PlainTextDocumentReaderAndWriter<CoreMap>) readerAndWriter).getAnswers(sentence, outFormat, true));
  return sb.toString();
}
 

import edu.stanford.nlp.sequences.DocumentReaderAndWriter; //导入依赖的package包/类
/**
 * Evaluate the postprocessor given an input file specified in the flags.
 * 
 * @param preProcessor
 * @param pwOut
 */
protected void evaluate(Preprocessor preProcessor, PrintWriter pwOut) {
  System.err.println("Starting evaluation...");
  DocumentReaderAndWriter<CoreLabel> docReader = new ProcessorTools.PostprocessorDocumentReaderAndWriter(preProcessor);
  ObjectBank<List<CoreLabel>> lines =
    classifier.makeObjectBankFromFile(flags.testFile, docReader);

  Counter<String> labelTotal = new ClassicCounter<String>();
  Counter<String> labelCorrect = new ClassicCounter<String>();
  int total = 0;
  int correct = 0;
  PrintWriter pw = new PrintWriter(IOTools.getWriterFromFile("apply.out"));
  for (List<CoreLabel> line : lines) {
    line = classifier.classify(line);
    pw.println(Sentence.listToString(ProcessorTools.toPostProcessedSequence(line)));
    total += line.size();
    for (CoreLabel label : line) {
      String hypothesis = label.get(CoreAnnotations.AnswerAnnotation.class);
      String reference = label.get(CoreAnnotations.GoldAnswerAnnotation.class);
      labelTotal.incrementCount(reference);
      if (hypothesis.equals(reference)) {
        correct++;
        labelCorrect.incrementCount(reference);
      }
    }
  }
  pw.close();

  double accuracy = ((double) correct) / ((double) total);
  accuracy *= 100.0;

  pwOut.println("EVALUATION RESULTS");
  pwOut.printf("#datums:\t%d%n", total);
  pwOut.printf("#correct:\t%d%n", correct);
  pwOut.printf("accuracy:\t%.2f%n", accuracy);
  pwOut.println("==================");

  // Output the per label accuracies
  pwOut.println("PER LABEL ACCURACIES");
  for (String refLabel : labelTotal.keySet()) {
    double nTotal = labelTotal.getCount(refLabel);
    double nCorrect = labelCorrect.getCount(refLabel);
    double acc = (nCorrect / nTotal) * 100.0;
    pwOut.printf(" %s\t%.2f%n", refLabel, acc);
  }
}
 

import edu.stanford.nlp.sequences.DocumentReaderAndWriter; //导入依赖的package包/类
/** The main method, which is essentially the same as in CRFClassifier. See the class documentation. */
public static void main(String[] args) throws Exception {
  System.err.println("CRFBiasedClassifier invoked at " + new Date()
          + " with arguments:");
  for (String arg : args) {
    System.err.print(" " + arg);
  }
  System.err.println();

  Properties props = StringUtils.argsToProperties(args);
  CRFBiasedClassifier<CoreLabel> crf = new CRFBiasedClassifier<CoreLabel>(props);
  String testFile = crf.flags.testFile;
  String loadPath = crf.flags.loadClassifier;

  if (loadPath != null) {
    crf.loadClassifierNoExceptions(loadPath, props);
  } else if (crf.flags.loadJarClassifier != null) {
    crf.loadJarClassifier(crf.flags.loadJarClassifier, props);
  } else {
    crf.loadDefaultClassifier();
  }
  if(crf.flags.classBias != null) {
    StringTokenizer biases = new java.util.StringTokenizer(crf.flags.classBias,",");
    while (biases.hasMoreTokens()) {
      StringTokenizer bias = new java.util.StringTokenizer(biases.nextToken(),":");
      String cname = bias.nextToken();
      double w = Double.parseDouble(bias.nextToken());
      crf.setBiasWeight(cname,w);
      System.err.println("Setting bias for class "+cname+" to "+w);
    }
  }

  if (testFile != null) {
    DocumentReaderAndWriter<CoreLabel> readerAndWriter = crf.makeReaderAndWriter();
    if (crf.flags.printFirstOrderProbs) {
      crf.printFirstOrderProbs(testFile, readerAndWriter);
    } else if (crf.flags.printProbs) {
      crf.printProbs(testFile, readerAndWriter);
    } else if (crf.flags.useKBest) {
      int k = crf.flags.kBest;
      crf.classifyAndWriteAnswersKBest(testFile, k, readerAndWriter);
    } else {
      crf.classifyAndWriteAnswers(testFile, readerAndWriter);
    }
  }
}
 

import edu.stanford.nlp.sequences.DocumentReaderAndWriter; //导入依赖的package包/类
@SuppressWarnings("unchecked")
@Override
public void train(Collection<List<IN>> docs,
                  DocumentReaderAndWriter<IN> readerAndWriter) {
  throw new UnsupportedOperationException();
}
 

import edu.stanford.nlp.sequences.DocumentReaderAndWriter; //导入依赖的package包/类
/** Command-line version of the classifier.  See the class
 *  comments for examples of use, and SeqClassifierFlags
 *  for more information on supported flags.
 */
public static void main(String[] args) throws Exception {
  StringUtils.printErrInvocationString("CMMClassifier", args);

  Properties props = StringUtils.argsToProperties(args);
  CMMClassifier<CoreLabel> cmm = new CMMClassifier<CoreLabel>(props);
  String testFile = cmm.flags.testFile;
  String textFile = cmm.flags.textFile;
  String loadPath = cmm.flags.loadClassifier;
  String serializeTo = cmm.flags.serializeTo;

  // cmm.crossValidateTrainAndTest(trainFile);
  if (loadPath != null) {
    cmm.loadClassifierNoExceptions(loadPath, props);
  } else if (cmm.flags.loadJarClassifier != null) {
    cmm.loadJarClassifier(cmm.flags.loadJarClassifier, props);
  } else if (cmm.flags.trainFile != null) {
    if (cmm.flags.biasedTrainFile != null) {
      cmm.trainSemiSup();
    } else {
      cmm.train();
    }
  } else {
    cmm.loadDefaultClassifier();
  }

  if (serializeTo != null) {
    cmm.serializeClassifier(serializeTo);
  }

  if (testFile != null) {
    cmm.classifyAndWriteAnswers(testFile, cmm.makeReaderAndWriter());
  } else if (cmm.flags.testFiles != null) {
    cmm.classifyAndWriteAnswers(cmm.flags.baseTestDir, cmm.flags.testFiles,
                                cmm.makeReaderAndWriter());
  }

  if (textFile != null) {
    DocumentReaderAndWriter<CoreLabel> readerAndWriter =
      new PlainTextDocumentReaderAndWriter<CoreLabel>();
    cmm.classifyAndWriteAnswers(textFile, readerAndWriter);
  }
}
 

import edu.stanford.nlp.sequences.DocumentReaderAndWriter; //导入依赖的package包/类
public void train(Collection<List<CoreLabel>> docs,
DocumentReaderAndWriter<CoreLabel> readerAndWriter) {}
 

import edu.stanford.nlp.sequences.DocumentReaderAndWriter; //导入依赖的package包/类
@SuppressWarnings("unchecked")
@Override
public void train(Collection<List<CoreLabel>> docs,
                  DocumentReaderAndWriter<CoreLabel> readerAndWriter) {
}