Package opennlp.tools.cmdline

Examples of opennlp.tools.cmdline.TerminateToolException

69
70
71
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
 
  public void run(String[] args) {
   
    if (!ArgumentParser.validateArguments(args, TrainerToolParams.class)) {
      System.err.println(getHelp());
      throw new TerminateToolException(1);
    }
   
    TrainerToolParams params = ArgumentParser.parse(args,
        TrainerToolParams.class);
   
    opennlp.tools.util.TrainingParameters mlParams =
      CmdLineUtil.loadTrainingParameters(params.getParams(), false);
   
    File trainingDataInFile = params.getData();
    File modelOutFile = params.getModel();

    CmdLineUtil.checkOutputFile("sentence detector model", modelOutFile);
    ObjectStream<ChunkSample> sampleStream =
      openSampleData("Training", trainingDataInFile, params.getEncoding());
   
    ChunkerModel model;
    try {
      if (mlParams == null) {
        model = ChunkerME.train(params.getLang(), sampleStream,
            params.getCutoff(), params.getIterations());
      }
      else {
        model = ChunkerME.train(params.getLang(), sampleStream,
            new DefaultChunkerContextGenerator(), mlParams);
      }
    } catch (IOException e) {
      CmdLineUtil.printTrainingIoError(e);
      throw new TerminateToolException(-1);
    }
    finally {
      try {
        sampleStream.close();
      } catch (IOException e) {
View Full Code Here
60
61
62
63
64
65
66
67
          CmdLineUtil.openInFile(new File(params.getData())), params.getEncoding()));
     
      return new WordTagSampleStream(lineStream);
    } catch (UnsupportedEncodingException e) {
      System.err.println("Encoding not supported: " + params.getEncoding());
      throw new TerminateToolException(-1);
    }
  }
View Full Code Here
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
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
  public void run(String[] args) {

    if (!ArgumentParser.validateArguments(args, EvaluatorParams.class)) {
      System.err.println(getHelp());
      throw new TerminateToolException(1);
    }
   
    EvalToolParams params = ArgumentParser.parse(args, EvalToolParams.class);
   
    File testData =params.getData();

    CmdLineUtil.checkInputFile("Test data", testData);

    Charset encoding = params.getEncoding();

    ChunkerModel model = new ChunkerModelLoader().load(params.getModel());
   
    List<EvaluationMonitor<ChunkSample>> listeners = new LinkedList<EvaluationMonitor<ChunkSample>>();
    ChunkerDetailedFMeasureListener detailedFMeasureListener = null;
    if(params.getMisclassified()) {
      listeners.add(new ChunkEvaluationErrorListener());
    }
    if(params.getDetailedF()) {
      detailedFMeasureListener = new ChunkerDetailedFMeasureListener();
      listeners.add(detailedFMeasureListener);
    }

    ChunkerEvaluator evaluator = new ChunkerEvaluator(new ChunkerME(model,
        ChunkerME.DEFAULT_BEAM_SIZE, new DefaultChunkerSequenceValidator()),
        listeners.toArray(new ChunkerEvaluationMonitor[listeners.size()]));
   
    final ObjectStream<ChunkSample> sampleStream = ChunkerTrainerTool.openSampleData("Test",
        testData, encoding);

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

    ObjectStream<ChunkSample> measuredSampleStream = new ObjectStream<ChunkSample>() {

      public ChunkSample read() throws IOException {
        monitor.incrementCounter();
        return sampleStream.read();
      }

      public void reset() throws IOException {
        sampleStream.reset();
      }

      public void close() throws IOException {
        sampleStream.close();
      }
    };

    monitor.startAndPrintThroughput();

    try {
      evaluator.evaluate(measuredSampleStream);
    } catch (IOException e) {
      System.err.println("failed");
      System.err.println("Reading test data error " + e.getMessage());
      throw new TerminateToolException(-1);
    } finally {
      try {
        measuredSampleStream.close();
      } catch (IOException e) {
        // sorry that this can fail
View Full Code Here
60
61
62
63
64
65
66
67
68
69
      detokenizer = new DictionaryDetokenizer(new DetokenizationDictionary(
          new FileInputStream(new File(params.getDetokenizer()))));
    } catch (IOException e) {
      System.err.println("Error while loading detokenizer dict: "
          + e.getMessage());
      throw new TerminateToolException(-1);
    }

    return new NameToTokenSampleStream(detokenizer, nameSampleStream);
  }
View Full Code Here
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
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
  public void run(String[] args) {

    if (!ArgumentParser
        .validateArguments(args, EvalToolParams.class)) {
      System.err.println(getHelp());
      throw new TerminateToolException(1);
    }

    EvalToolParams params = ArgumentParser.parse(args,
        EvalToolParams.class);

    File testData = params.getData();
    CmdLineUtil.checkInputFile("Test data", testData);

    Charset encoding = params.getEncoding();

    TokenNameFinderModel model = new TokenNameFinderModelLoader().load(params
        .getModel());
   
    List<EvaluationMonitor<NameSample>> listeners = new LinkedList<EvaluationMonitor<NameSample>>();
    if (params.getMisclassified()) {
      listeners.add(new NameEvaluationErrorListener());
    }
    TokenNameFinderDetailedFMeasureListener detailedFListener = null;
    if (params.getDetailedF()) {
      detailedFListener = new TokenNameFinderDetailedFMeasureListener();
      listeners.add(detailedFListener);
    }

    TokenNameFinderEvaluator evaluator = new TokenNameFinderEvaluator(
        new NameFinderME(model),
        listeners.toArray(new TokenNameFinderEvaluationMonitor[listeners.size()]));

    final ObjectStream<NameSample> sampleStream = TokenNameFinderTrainerTool.openSampleData("Test",
        testData, encoding);

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

    ObjectStream<NameSample> measuredSampleStream = new ObjectStream<NameSample>() {

      public NameSample read() throws IOException {
        monitor.incrementCounter();
        return sampleStream.read();
      }

      public void reset() throws IOException {
        sampleStream.reset();
      }

      public void close() throws IOException {
        sampleStream.close();
      }
    };

    monitor.startAndPrintThroughput();

    try {
      evaluator.evaluate(measuredSampleStream);
    } catch (IOException e) {
      System.err.println("failed");
      System.err.println("Reading test data error " + e.getMessage());
      throw new TerminateToolException(-1);
    } finally {
      try {
        measuredSampleStream.close();
      } catch (IOException e) {
        // sorry that this can fail
View Full Code Here
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
92
93
94
95
96
97
98
99
100
101
102
103
104
105
  }
 
  public void run(String[] args) {
    if (!ArgumentParser.validateArguments(args, TrainerToolParams.class)) {
      System.err.println(getHelp());
      throw new TerminateToolException(1);
    }
   
    TrainerToolParams params = ArgumentParser.parse(args,
        TrainerToolParams.class);
   
    opennlp.tools.util.TrainingParameters mlParams =
      CmdLineUtil.loadTrainingParameters(params.getParams(), false);
   
    File trainingDataInFile = params.getData();
    File modelOutFile = params.getModel();

    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());
      }
      else {
        model = DocumentCategorizerME.train(params.getLang(), sampleStream,
            mlParams);
      }
    } catch (IOException e) {
      CmdLineUtil.printTrainingIoError(e);
      throw new TerminateToolException(-1);
    }
    finally {
      try {
        sampleStream.close();
      } catch (IOException e) {
View Full Code Here
60
61
62
63
64
65
66
67
68
69
      detokenizer = new DictionaryDetokenizer(new DetokenizationDictionary(
          new FileInputStream(new File(params.getDetokenizer()))));
    } catch (IOException e) {
      System.err.println("Error while loading detokenizer dict: "
          + e.getMessage());
      throw new TerminateToolException(-1);
    }

    return new POSToTokenSampleStream(detokenizer, posSampleStream);
  }
View Full Code Here
50
51
52
53
54
55
56
57
58
59
60
  }

  public void run(String[] args) {
    if (args.length != 1) {
      System.out.println(getHelp());
      throw new TerminateToolException(1);
    }
   
    ChunkerModel model = new ChunkerModelLoader().load(new File(args[0]));
   
    ChunkerME chunker = new ChunkerME(model, ChunkerME.DEFAULT_BEAM_SIZE,
View Full Code Here
62
63
64
65
66
67
68
69
70
71
    Detokenizer detokenizer;
    try {
      detokenizer = new DictionaryDetokenizer(new DetokenizationDictionary(new FileInputStream(new File(params.getDetokenizer()))));
    } catch (IOException e) {
      System.err.println("Error while loading detokenizer dict: " + e.getMessage());
      throw new TerminateToolException(-1);
    }
   
    return new POSToSentenceSampleStream(detokenizer, posSampleStream, 30);
  }
View Full Code Here
49
50
51
52
53
54
55
56
57
58
59
  public void run(String[] args) {
   
    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);
View Full Code Here
TOP

Related Classes of opennlp.tools.cmdline.TerminateToolException

  • opennlp.tools.cmdline.chunker.ChunkerCrossValidatorTool
  • opennlp.tools.cmdline.chunker.ChunkerEvaluatorTool
  • opennlp.tools.cmdline.chunker.ChunkerMETool
  • opennlp.tools.cmdline.chunker.ChunkerTrainerTool
  • opennlp.tools.cmdline.coref.CoreferencerTool
  • opennlp.tools.cmdline.coref.CoreferencerTrainerTool
  • opennlp.tools.cmdline.dictionary.DictionaryBuilderTool
  • opennlp.tools.cmdline.doccat.DoccatCrossValidatorTool
  • opennlp.tools.cmdline.doccat.DoccatEvaluatorTool
  • opennlp.tools.cmdline.doccat.DoccatTool
    • 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.