Package opennlp.tools.doccat

Examples of opennlp.tools.doccat.DoccatModel

83
84
85
86
87
88
89
90
91
92
93
    CmdLineUtil.checkOutputFile("document categorizer model", modelOutFile);
    ObjectStream<DocumentSample> sampleStream =
        openSampleData("Training", trainingDataInFile, params.getEncoding());
   
    DoccatModel model;
    try {
      if (mlParams == null) {
       model = DocumentCategorizerME.train(params.getLang(), sampleStream,
           params.getCutoff(), params.getIterations());
      }
View Full Code Here
52
53
54
55
56
57
58
59
60
61
62
    if (args.length != 1) {
      System.out.println(getHelp());
      throw new TerminateToolException(1);
    }
   
    DoccatModel model = new DoccatModelLoader().load(new File(args[0]));
   
    DocumentCategorizerME doccat = new DocumentCategorizerME(model);
   
    ObjectStream<String> documentStream = new ParagraphStream(
        new PlainTextByLineStream(new InputStreamReader(System.in)));
View Full Code Here
36
37
38
39
40
41
42
  }
 
  @Override
  protected DoccatModel loadModel(InputStream modelIn) throws IOException,
      InvalidFormatException {
    return new DoccatModel(modelIn);
  }
View Full Code Here
54
55
56
57
58
59
60
61
62
63
64
    File modelOutFile = params.getModel();

    CmdLineUtil.checkOutputFile("document categorizer model", modelOutFile);

    DoccatModel model;
    try {
      model = DocumentCategorizerME.train(params.getLang(), sampleStream, mlParams);
    } catch (IOException e) {
      throw new TerminateToolException(-1, "IO error while reading training data or indexing data: " +
          e.getMessage(), e);
View Full Code Here
47
48
49
50
51
52
53
54
55
56
57
   
    if (0 == args.length) {
      System.out.println(getHelp());
    } else {

      DoccatModel model = new DoccatModelLoader().load(new File(args[0]));

      DocumentCategorizerME doccat = new DocumentCategorizerME(model);

      ObjectStream<String> documentStream = new ParagraphStream(
          new PlainTextByLineStream(new InputStreamReader(System.in)));
View Full Code Here
34
35
36
37
38
39
40
    super("Document Categorizer");
  }
 
  @Override
  protected DoccatModel loadModel(InputStream modelIn) throws IOException {
    return new DoccatModel(modelIn);
  }
View Full Code Here
59
60
61
62
63
64
65
66
67
68
69
  }

  public void run(String format, String[] args) {
    super.run(format, args);

    DoccatModel model = new DoccatModelLoader().load(params.getModel());

    List<EvaluationMonitor<DocumentSample>> listeners = new LinkedList<EvaluationMonitor<DocumentSample>>();
    if (params.getMisclassified()) {
      listeners.add(new DoccatEvaluationErrorListener());
    }
View Full Code Here
67
68
69
70
71
72
73
74
75
76
77
    FeatureGenerator[] featureGenerators = createFeatureGenerators(params
        .getFeatureGenerators());

    Tokenizer tokenizer = createTokenizer(params.getTokenizer());

    DoccatModel model;
    try {
      DoccatFactory factory = DoccatFactory.create(params.getFactory(),
          tokenizer, featureGenerators);
      model = DocumentCategorizerME.train(params.getLang(), sampleStream,
          mlParams, factory);
View Full Code Here
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
    if (0 == args.length) {
      System.out.println(getHelp());
    } else {

      DoccatModel model = new DoccatModelLoader().load(new File(args[0]));

      DocumentCategorizerME doccat = new DocumentCategorizerME(model);

      /**
       * moved initialization to the try block to catch new IOException
       */
      ObjectStream<String> documentStream;

      PerformanceMonitor perfMon = new PerformanceMonitor(System.err, "doc");
      perfMon.start();

      try {
        documentStream = new ParagraphStream(
                new PlainTextByLineStream(new SystemInputStreamFactory(), SystemInputStreamFactory.encoding()));
        String document;
        while ((document = documentStream.read()) != null) {
          String[] tokens = model.getFactory().getTokenizer().tokenize(document);

          double prob[] = doccat.categorize(tokens);
          String category = doccat.getBestCategory(prob);

          DocumentSample sample = new DocumentSample(category, tokens);
View Full Code Here
34
35
36
37
38
39
40
    super("Document Categorizer");
  }

  @Override
  protected DoccatModel loadModel(InputStream modelIn) throws IOException {
    return new DoccatModel(modelIn);
  }
View Full Code Here
TOP

Related Classes of opennlp.tools.doccat.DoccatModel

  • com.tamingtext.classifier.maxent.TestMaxent
  • com.tamingtext.classifier.maxent.TrainMaxent
  • com.tamingtext.qa.AnswerTypeClassifier
  • com.tamingtext.qa.QuestionQParserPlugin
  • opennlp.tools.cmdline.doccat.DoccatEvaluatorTool
  • opennlp.tools.cmdline.doccat.DoccatModelLoader
  • opennlp.tools.cmdline.doccat.DoccatTool
  • opennlp.tools.cmdline.doccat.DoccatTrainerTool
  • opennlp.uima.doccat.AbstractDocumentCategorizer
  • opennlp.uima.doccat.DoccatModelResourceImpl
    • 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.