Package opennlp.tools.cmdline

Examples of opennlp.tools.cmdline.TerminateToolException

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
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
128
129
130
131
132
133
134
135
136
137
138
  public void run(String format, String[] args) {
    super.run(format, args);

    mlParams = CmdLineUtil.loadTrainingParameters(params.getParams(), true);
    if (mlParams != null && !TrainerFactory.isValid(mlParams.getSettings())) {
      throw new TerminateToolException(1, "Training parameters file '" + params.getParams() +
          "' is invalid!");
    }

    if(mlParams == null) {
      mlParams = ModelUtil.createDefaultTrainingParameters();
      mlParams.put(TrainingParameters.ALGORITHM_PARAM, getModelType(params.getType()).toString());
    }

    File modelOutFile = params.getModel();
    CmdLineUtil.checkOutputFile("pos tagger model", modelOutFile);

    Dictionary ngramDict = null;

    Integer ngramCutoff = params.getNgram();

    if (ngramCutoff != null) {
      System.err.print("Building ngram dictionary ... ");
      try {
        ngramDict = POSTaggerME.buildNGramDictionary(sampleStream, ngramCutoff);
        sampleStream.reset();
      } catch (IOException e) {
        throw new TerminateToolException(-1,
            "IO error while building NGram Dictionary: " + e.getMessage(), e);
      }
      System.err.println("done");
    }

    POSTaggerFactory postaggerFactory = null;
    try {
      postaggerFactory = POSTaggerFactory.create(params.getFactory(), ngramDict, null);
    } catch (InvalidFormatException e) {
      throw new TerminateToolException(-1, e.getMessage(), e);
    }

    if (params.getDict() != null) {
      try {
        postaggerFactory.setTagDictionary(postaggerFactory
            .createTagDictionary(params.getDict()));
      } catch (IOException e) {
        throw new TerminateToolException(-1,
            "IO error while loading POS Dictionary: " + e.getMessage(), e);
      }
    }

    if (params.getTagDictCutoff() != null) {
      try {
        TagDictionary dict = postaggerFactory.getTagDictionary();
        if (dict == null) {
          dict = postaggerFactory.createEmptyTagDictionary();
          postaggerFactory.setTagDictionary(dict);
        }
        if (dict instanceof MutableTagDictionary) {
          POSTaggerME.populatePOSDictionary(sampleStream, (MutableTagDictionary)dict,
              params.getTagDictCutoff());
        } else {
          throw new IllegalArgumentException(
              "Can't extend a POSDictionary that does not implement MutableTagDictionary.");
        }
        sampleStream.reset();
      } catch (IOException e) {
        throw new TerminateToolException(-1,
            "IO error while creating/extending POS Dictionary: "
                + e.getMessage(), e);
      }
    }

    POSModel model;
    try {
      model = opennlp.tools.postag.POSTaggerME.train(params.getLang(),
          sampleStream, mlParams, postaggerFactory);
    }
    catch (IOException e) {
      throw new TerminateToolException(-1, "IO error while reading training data or indexing data: "
          + e.getMessage(), e);
    }
    finally {
      try {
        sampleStream.close();
View Full Code Here
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
      try {
        reportOutputStream = new FileOutputStream(reportFile);
        reportListener = new DoccatFineGrainedReportListener(reportOutputStream);
        listeners.add(reportListener);
      } catch (FileNotFoundException e) {
        throw new TerminateToolException(-1,
            "IO error while creating Doccat fine-grained report file: "
                + 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>() {

      public DocumentSample 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");
      throw new TerminateToolException(-1, "IO error while reading test data: "
          + e.getMessage(), e);
    } finally {
      try {
        measuredSampleStream.close();
      } catch (IOException e) {
View Full Code Here
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
    mlParams = CmdLineUtil.loadTrainingParameters(params.getParams(), false);

    if (mlParams != null) {
      if (!TrainerFactory.isValid(mlParams.getSettings())) {
        throw new TerminateToolException(1, "Training parameters file '" + params.getParams() +
            "' is invalid!");
      }

      if (!TrainerType.EVENT_MODEL_TRAINER.equals(TrainerFactory.getTrainerType(mlParams.getSettings()))) {
        throw new TerminateToolException(1, "Sequence training is not supported!");
      }
    }

    if(mlParams == null) {
      mlParams = ModelUtil.createDefaultTrainingParameters();
    }

    File modelOutFile = params.getModel();
    CmdLineUtil.checkOutputFile("tokenizer model", modelOutFile);

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

      TokenizerFactory tokFactory = TokenizerFactory.create(
          params.getFactory(), params.getLang(), dict,
          params.getAlphaNumOpt(), null);
      model = opennlp.tools.tokenize.TokenizerME.train(sampleStream,
          tokFactory, mlParams);

    } catch (IOException e) {
      throw new TerminateToolException(-1, "IO error while reading training data or indexing data: "
          + e.getMessage(), e);
    }
    finally {
      try {
        sampleStream.close();
View Full Code Here
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
      try {
        reportOutputStream = new FileOutputStream(reportFile);
        reportListener = new DoccatFineGrainedReportListener(reportOutputStream);
        listeners.add(reportListener);
      } catch (FileNotFoundException e) {
        throw new TerminateToolException(-1,
            "IO error while creating Doccat fine-grained report file: "
                + e.getMessage());
      }
    }

    FeatureGenerator[] featureGenerators = DoccatTrainerTool
        .createFeatureGenerators(params.getFeatureGenerators());

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

    DoccatEvaluationMonitor[] listenersArr = listeners
        .toArray(new DoccatEvaluationMonitor[listeners.size()]);

    DoccatCrossValidator validator;
    try {
      DoccatFactory factory = DoccatFactory.create(params.getFactory(),
          tokenizer, featureGenerators);
      validator = new DoccatCrossValidator(params.getLang(), mlParams,
          factory, listenersArr);

      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();
View Full Code Here
71
72
73
74
75
76
77
78
79
80
81
          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();
View Full Code Here
74
75
76
77
78
79
80
81
82
83
84
      DoccatFactory factory = DoccatFactory.create(params.getFactory(),
          tokenizer, featureGenerators);
      model = DocumentCategorizerME.train(params.getLang(), sampleStream,
          mlParams, factory);
    } catch (IOException e) {
      throw new TerminateToolException(-1, "IO error while reading training data or indexing data: " +
          e.getMessage(), e);
    }
    finally {
      try {
        sampleStream.close();
View Full Code Here
59
60
61
62
63
64
65
66
67
68
69
    try {
      evaluator.evaluate(sampleStream);
    } catch (IOException e) {
      System.err.println("failed");
      throw new TerminateToolException(-1, "IO error while reading test data: " + e.getMessage(), e);
    } finally {
      try {
        sampleStream.close();
      } catch (IOException e) {
        // sorry that this can fail
View Full Code Here
101
102
103
104
105
106
107
108
109
110
111
    try {
      evaluator.evaluate(measuredSampleStream);
    } catch (IOException e) {
      System.err.println("failed");
      throw new TerminateToolException(-1, "IO error while reading test data: " + e.getMessage(), e);
    } finally {
      try {
        measuredSampleStream.close();
      } catch (IOException e) {
        // sorry that this can fail
View Full Code Here
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
    Dictionary mDictionary;
    try {
      System.out.println("Creating Dictionary...");
      mDictionary = createDictionary(sampleStream);
    } 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 this can fail..
      }
    }

    System.out.println("Saving Dictionary...");

    OutputStream out = null;

    try {
      out = new FileOutputStream(dictOutFile);
      mDictionary.serialize(out);
    } catch (IOException e) {
      throw new TerminateToolException(-1, "IO error while writing dictionary file: "
          + e.getMessage(), e);
    }
    finally {
      if (out != null)
        try {
          out.close();
        } catch (IOException e) {
          // file might be damaged
          throw new TerminateToolException(-1, "Attention: Failed to correctly write dictionary:" +
              e.getMessage(), e);
        }
    }
  }
View Full Code Here
76
77
78
79
80
81
82
83
84
85
86
          errorListener);

      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();
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.