Package opennlp.tools.doccat

Examples of opennlp.tools.doccat.DocumentCategorizerME

115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
    InputStream modelStream = //<co id="tmx.modelreader"/>
        new FileInputStream(modelFile);
    DoccatModel model = new DoccatModel(modelStream);
    DocumentCategorizer categorizer //<co id="tmx.categorizer"/>
      = new DocumentCategorizerME(model, nffg, bowfg);
    Tokenizer tokenizer = SimpleTokenizer.INSTANCE;
  
    int catCount = categorizer.getNumberOfCategories();
    Collection<String> categories
      = new ArrayList<String>(catCount);
    for (int i=0; i < catCount; i++) {
      categories.add(categorizer.getCategory(i));
    }
    ResultAnalyzer resultAnalyzer = //<co id="tmx.results"/>
        new ResultAnalyzer(categories, "unknown");
    runTest(inputFiles, categorizer, tokenizer, resultAnalyzer); //<co id="tmx.run"/>
    /*<calloutlist>
 
View Full Code Here
69
70
71
72
73
74
75
      model = modelResource.getModel();
    } catch (ResourceAccessException e) {
      throw new ResourceInitializationException(e);
    }

    mCategorizer = new DocumentCategorizerME(model);
  }
View Full Code Here
69
70
71
72
73
74
75
      model = modelResource.getModel();
    } catch (ResourceAccessException e) {
      throw new ResourceInitializationException(e);
    }

    mCategorizer = new DocumentCategorizerME(model);
  }
View Full Code Here
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
      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)));
   
    PerformanceMonitor perfMon = new PerformanceMonitor(System.err, "doc");
    perfMon.start();
   
    try {
      String document;
      while ((document = documentStream.read()) != null) {
        double prob[] = doccat.categorize(document);
        String category = doccat.getBestCategory(prob);
       
        DocumentSample sample = new DocumentSample(category, document);
        System.out.println(sample.toString());
       
        perfMon.incrementCounter();
View Full Code Here
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
      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)));

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

      try {
        String document;
        while ((document = documentStream.read()) != null) {
          double prob[] = doccat.categorize(WhitespaceTokenizer.INSTANCE.tokenize(document));
          String category = doccat.getBestCategory(prob);

          DocumentSample sample = new DocumentSample(category, document);
          System.out.println(sample.toString());

          perfMon.incrementCounter();
View Full Code Here
83
84
85
86
87
88
89
90
91
92
93
                + e.getMessage());
      }
    }

    DocumentCategorizerEvaluator evaluator = new DocumentCategorizerEvaluator(
        new DocumentCategorizerME(model),
        listeners.toArray(new DoccatEvaluationMonitor[listeners.size()]));

    final PerformanceMonitor monitor = new PerformanceMonitor("doc");

    ObjectStream<DocumentSample> measuredSampleStream = new ObjectStream<DocumentSample>() {
View Full Code Here
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
76
77
78
      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);
          System.out.println(sample.toString());

          perfMon.incrementCounter();
View Full Code Here
69
70
71
72
73
74
75
      model = modelResource.getModel();
    } catch (ResourceAccessException e) {
      throw new ResourceInitializationException(e);
    }

    mCategorizer = new DocumentCategorizerME(model);
  }
View Full Code Here
TOP

Related Classes of opennlp.tools.doccat.DocumentCategorizerME

  • com.tamingtext.classifier.maxent.TestMaxent
  • opennlp.model.AbstractModel
  • opennlp.model.TwoPassDataIndexer
  • opennlp.tools.cmdline.doccat.DoccatEvaluatorTool
  • opennlp.tools.cmdline.doccat.DoccatTool
  • opennlp.tools.ml.model.MaxentModel
  • opennlp.tools.tokenize.Tokenizer
  • opennlp.uima.doccat.AbstractDocumentCategorizer
    • 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.