Examples of opennlp.maxent.DataStream

opennlp.maxent.DataStream
A interface for objects which can deliver a stream of training data to be supplied to an EventStream. It is not necessary to use a DataStream in a Maxent application, but it can be used to support a wider variety of formats in which your training data can be held.

      predictor.eval("Rainy");
      predictor.eval("Blarmey");
  }
  else {
      try {
    DataStream ds =
        new PlainTextByLineDataStream(
      new FileReader(new File(dataFileName)));


    while (ds.hasNext()) {
        String s = (String)ds.nextToken();
        predictor.eval(s.substring(0, s.lastIndexOf(' ')),real);
    }
    return;
      }
      catch (Exception e) {

View Full Code Here

      throws FileNotFoundException, IOException {
    System.err.println("Building dictionary");


    NGramModel ngramModel = new NGramModel();


    DataStream data = new opennlp.maxent.PlainTextByLineDataStream(new java.io.FileReader(inFile));
    while(data.hasNext()) {
      String tagStr = (String) data.nextToken();
      String[] tt = tagStr.split(" ");
      String[] words = new String[tt.length];
      for (int wi=0;wi<words.length;wi++) {
        words[wi] =
            tt[wi].substring(0,tt[wi].lastIndexOf('_'));

View Full Code Here

   * other than the default ones.  They are "\\.|!|\\?|\\\"|\\)".
   *
   */
  public static GISModel train(File inFile, int iterations, int cut, EndOfSentenceScanner scanner) throws IOException {
    EventStream es;
    DataStream ds;
    Reader reader;


    reader = new BufferedReader(new FileReader(inFile));
    ds = new PlainTextByLineDataStream(reader);
    es = new SDEventStream(ds, scanner);

View Full Code Here

      }
      GISModel mod;
      if (dict != null) {
        System.err.println("Building dictionary");
        MutableDictionary mdict = new MutableDictionary(cutoff);
        DataStream data = new opennlp.maxent.PlainTextByLineDataStream(new java.io.FileReader(inFile));
        while(data.hasNext()) {
          String tagStr = (String) data.nextToken();
          String[] tt = tagStr.split(" ");
          String[] words = new String[tt.length];
          for (int wi=0;wi<words.length;wi++) {
            words[wi] = tt[wi].substring(0,tt[wi].lastIndexOf('_'));
          }

View Full Code Here

    if (fun) {
      Parse.useFunctionTags(true);
    }
    if (dict || all) {
      System.err.println("Building dictionary");
      DataStream data = new opennlp.maxent.PlainTextByLineDataStream(new java.io.FileReader(inFile));
      MutableDictionary mdict = buildDictionary(data, rules, cutoff);
      System.out.println("Saving the dictionary");
      mdict.persist(dictFile);
    }
    if (tag || all) {

View Full Code Here

      throws FileNotFoundException, IOException {
    System.err.println("Building dictionary");


    NGramModel ngramModel = new NGramModel();


    DataStream data = new opennlp.maxent.PlainTextByLineDataStream(new java.io.FileReader(inFile));
    while(data.hasNext()) {
      String tagStr = (String) data.nextToken();
      String[] tt = tagStr.split(" ");
      String[] words = new String[tt.length];
      for (int wi=0;wi<words.length;wi++) {
        words[wi] =
            tt[wi].substring(0,tt[wi].lastIndexOf('_'));

View Full Code Here

TOP

Related Classes of opennlp.maxent.DataStream

opennlp.tools.parser.ParserME

opennlp.tools.postag.POSTaggerME

opennlp.tools.postag.POSTaggerTrainer

opennlp.tools.sentdetect.SentenceDetectorME

Predict

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.