Package opennlp.tools.tokenize

Examples of opennlp.tools.tokenize.TokenizerCrossValidator

72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
    ObjectStream<TokenSample> sampleStream =
        TokenizerTrainerTool.openSampleData("Training Data",
        trainingDataInFile, encoding);
   
   
    TokenizerCrossValidator validator;
   
    if (mlParams == null)
      mlParams = TokenizerTrainerTool.createTrainingParameters(
          params.getIterations(), params.getCutoff());
   
    TokenizerEvaluationMonitor listener = null;
    if (params.getMisclassified()) {
      listener = new TokenEvaluationErrorListener();
    }
   
    try {
      Dictionary dict = TokenizerTrainerTool.loadDict(params.getAbbDict());

      validator = new opennlp.tools.tokenize.TokenizerCrossValidator(
          params.getLang(), dict, params.getAlphaNumOpt(), mlParams, listener);

      validator.evaluate(sampleStream, params.getFolds());
    }
    catch (IOException e) {
      CmdLineUtil.printTrainingIoError(e);
      throw new TerminateToolException(-1);
    }
    finally {
      try {
        sampleStream.close();
      } catch (IOException e) {
        // sorry that this can fail
      }
    }
   
    FMeasure result = validator.getFMeasure();
   
    System.out.println(result.toString());
  }
View Full Code Here
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
79
80
81
82
83
84
85
86
87
88
89
90
    mlParams = CmdLineUtil.loadTrainingParameters(params.getParams(), false);
    if (mlParams == null) {
      mlParams = ModelUtil.createTrainingParameters(params.getIterations(), params.getCutoff());
    }

    TokenizerCrossValidator validator;
   
    TokenizerEvaluationMonitor listener = null;
    if (params.getMisclassified()) {
      listener = new TokenEvaluationErrorListener();
    }
   
    try {
      Dictionary dict = TokenizerTrainerTool.loadDict(params.getAbbDict());

      TokenizerFactory tokFactory = TokenizerFactory.create(
          params.getFactory(), params.getLang(), dict,
          params.getAlphaNumOpt(), null);
      validator = new opennlp.tools.tokenize.TokenizerCrossValidator(mlParams,
          tokFactory, listener);

      validator.evaluate(sampleStream, params.getFolds());
    }
    catch (IOException e) {
      throw new TerminateToolException(-1, "IO error while reading training data or indexing data: "
          + e.getMessage(), e);
    }
    finally {
      try {
        sampleStream.close();
      } catch (IOException e) {
        // sorry that this can fail
      }
    }
   
    FMeasure result = validator.getFMeasure();
   
    System.out.println(result.toString());
  }
View Full Code Here
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
79
80
81
82
83
84
85
86
87
88
89
90
    mlParams = CmdLineUtil.loadTrainingParameters(params.getParams(), false);
    if (mlParams == null) {
      mlParams = ModelUtil.createDefaultTrainingParameters();
    }

    TokenizerCrossValidator validator;

    TokenizerEvaluationMonitor listener = null;
    if (params.getMisclassified()) {
      listener = new TokenEvaluationErrorListener();
    }

    try {
      Dictionary dict = TokenizerTrainerTool.loadDict(params.getAbbDict());

      TokenizerFactory tokFactory = TokenizerFactory.create(
          params.getFactory(), params.getLang(), dict,
          params.getAlphaNumOpt(), null);
      validator = new opennlp.tools.tokenize.TokenizerCrossValidator(mlParams,
          tokFactory, listener);

      validator.evaluate(sampleStream, params.getFolds());
    }
    catch (IOException e) {
      throw new TerminateToolException(-1, "IO error while reading training data or indexing data: "
          + e.getMessage(), e);
    }
    finally {
      try {
        sampleStream.close();
      } catch (IOException e) {
        // sorry that this can fail
      }
    }

    FMeasure result = validator.getFMeasure();

    System.out.println(result.toString());
  }
View Full Code Here
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
   
    ObjectStream<TokenSample> sampleStream =
        TokenizerTrainerTool.openSampleData("Training Data",
        trainingDataInFile, parameters.getEncoding());
   
    TokenizerCrossValidator validator =
        new opennlp.tools.tokenize.TokenizerCrossValidator(
        parameters.getLanguage(), parameters.isAlphaNumericOptimizationEnabled());
     
    try {
      validator.evaluate(sampleStream, 10);
    }
    catch (IOException e) {
      CmdLineUtil.printTrainingIoError(e);
      throw new TerminateToolException(-1);
    }
    finally {
      try {
        sampleStream.close();
      } catch (IOException e) {
        // sorry that this can fail
      }
    }
   
    FMeasure result = validator.getFMeasure();
   
    System.out.println(result.toString());
  }
View Full Code Here
TOP

Related Classes of opennlp.tools.tokenize.TokenizerCrossValidator

  • opennlp.tools.cmdline.tokenizer.TokenizerCrossValidatorTool
    • 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.