Package opennlp.tools.cmdline

Examples of opennlp.tools.cmdline.TerminateToolException

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
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, CVToolParams.class)) {
      System.err.println(getHelp());
      throw new TerminateToolException(1);
    }
   
    CVToolParams params = ArgumentParser.parse(args, CVToolParams.class);

    opennlp.tools.util.TrainingParameters mlParams = CmdLineUtil
        .loadTrainingParameters(params.getParams(), false);

    File trainingDataInFile = params.getData();
    CmdLineUtil.checkInputFile("Training Data", trainingDataInFile);

    ObjectStream<POSSample> sampleStream = POSTaggerTrainerTool.openSampleData(
        "Training Data", trainingDataInFile, params.getEncoding());

    POSTaggerCrossValidator validator;
   
    POSTaggerEvaluationMonitor missclassifiedListener = null;
    if (params.getMisclassified()) {
      missclassifiedListener = new POSEvaluationErrorListener();
    }
   
    if (mlParams == null) {
      mlParams = new TrainingParameters();
      mlParams.put(TrainingParameters.ALGORITHM_PARAM, "MAXENT");
      mlParams.put(TrainingParameters.ITERATIONS_PARAM,
          Integer.toString(params.getIterations()));
      mlParams.put(TrainingParameters.CUTOFF_PARAM,
          Integer.toString(params.getCutoff()));
    }
   
    try {
      // TODO: Move to util method ...
      POSDictionary tagdict = null;
      if (params.getDict() != null) {
        tagdict = POSDictionary.create(new FileInputStream(params.getDict()));
      }

      validator = new POSTaggerCrossValidator(params.getLang(), mlParams,
          tagdict, params.getNgram(), missclassifiedListener);
     
      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
View Full Code Here
91
92
93
94
95
96
97
98
99
100
101
 
  public void run(String[] args) {
   
    if (args.length < 1) {
      System.out.println(getHelp());
      throw new TerminateToolException(1);
    }
   
    ParserModel model = new ParserModelLoader().load(new File(args[args.length - 1]));
   
    Integer beamSize = CmdLineUtil.getIntParameter("-bs", args);
View Full Code Here
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
139
140
  }
 
  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(), true);
   
    if (mlParams != null && !TrainUtil.isValid(mlParams.getSettings())) {
      System.err.println("Training parameters file is invalid!");
      throw new TerminateToolException(-1);
    }
   
    File trainingDataInFile = params.getData();
    File modelOutFile = params.getModel();
   
    CmdLineUtil.checkOutputFile("pos tagger model", modelOutFile);
    ObjectStream<POSSample> sampleStream = openSampleData("Training", trainingDataInFile,
        params.getEncoding());
   
   
    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) {
        CmdLineUtil.printTrainingIoError(e);
        throw new TerminateToolException(-1);
      }
      System.err.println("done");
    }
   
    POSModel model;
    try {
     
      // TODO: Move to util method ...
      POSDictionary tagdict = null;
      if (params.getDict() != null) {
        tagdict = POSDictionary.create(new FileInputStream(params.getDict()));
      }
     
      if (mlParams == null) {
        // depending on model and sequence choose training method
        model = opennlp.tools.postag.POSTaggerME.train(params.getLang(),
             sampleStream, getModelType(params.getType()), tagdict, ngramDict, params.getCutoff(), params.getIterations());
      }
      else {
        model = opennlp.tools.postag.POSTaggerME.train(params.getLang(),
            sampleStream, mlParams, tagdict, ngramDict);
      }
    }
    catch (IOException e) {
      CmdLineUtil.printTrainingIoError(e);
      throw new TerminateToolException(-1);
    }
    finally {
      try {
        sampleStream.close();
      } catch (IOException e) {
View Full Code Here
71
72
73
74
75
76
77
78
79
80
81
    try {
      trainingDataIn = new FileInputStream(trainingDataFile);
    } catch (FileNotFoundException e) {
      System.err.println("failed");
      System.err.println("File not found: " + e.getMessage());
      throw new TerminateToolException(-1);
    }
   
    System.err.println("done");
   
    return new ParseSampleStream(
View Full Code Here
103
104
105
106
107
108
109
110
111
112
113
    ParserType type = null;
    if(typeAsString != null && typeAsString.length() > 0) {
      type = ParserType.parse(typeAsString);
      if(type == null) {
        System.err.println("ParserType training parameter is invalid!");
        throw new TerminateToolException(-1);
      }
    }
   
    return type;
  }
View Full Code Here
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
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
  // TODO: Add param to train tree insert parser
  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(), true);
   
    if (mlParams != null) {
      if (!TrainUtil.isValid(mlParams.getSettings("build"))) {
        System.err.println("Build training parameters are invalid!");
        throw new TerminateToolException(-1);
      }
     
      if (!TrainUtil.isValid(mlParams.getSettings("check"))) {
        System.err.println("Check training parameters are invalid!");
        throw new TerminateToolException(-1);
      }
     
      if (!TrainUtil.isValid(mlParams.getSettings("attach"))) {
        System.err.println("Attach training parameters are invalid!");
        throw new TerminateToolException(-1);
      }
     
      if (!TrainUtil.isValid(mlParams.getSettings("tagger"))) {
        System.err.println("Tagger training parameters are invalid!");
        throw new TerminateToolException(-1);
      }
     
      if (!TrainUtil.isValid(mlParams.getSettings("chunker"))) {
        System.err.println("Chunker training parameters are invalid!");
        throw new TerminateToolException(-1);
      }
    }
   
    ObjectStream<Parse> sampleStream = openTrainingData(params.getData(), params.getEncoding());
   
    File modelOutFile = params.getModel();
    CmdLineUtil.checkOutputFile("parser model", modelOutFile);
   
    ParserModel model;
    try {
     
      HeadRules rules = new opennlp.tools.parser.lang.en.HeadRules(
          new InputStreamReader(new FileInputStream(params.getHeadRules()),
              params.getEncoding()));
     
      ParserType type = parseParserType(params.getParserType());
     
      if (mlParams == null) {
        if (ParserType.CHUNKING.equals(type)) {
          model = opennlp.tools.parser.chunking.Parser.train(
              params.getLang(), sampleStream, rules,
              params.getIterations(), params.getCutoff());
        }
        else if (ParserType.TREEINSERT.equals(type)) {
          model = opennlp.tools.parser.treeinsert.Parser.train(params.getLang(), sampleStream, rules, params.getIterations(),
              params.getCutoff());
        }
        else {
          throw new IllegalStateException();
        }
      }
      else {
        if (ParserType.CHUNKING.equals(type)) {
          model = opennlp.tools.parser.chunking.Parser.train(
              params.getLang(), sampleStream, rules,
              mlParams);
        }
        else if (ParserType.TREEINSERT.equals(type)) {
          model = opennlp.tools.parser.treeinsert.Parser.train(params.getLang(), sampleStream, rules,
              mlParams);
        }
        else {
          throw new IllegalStateException();
        }

      }
    }
    catch (IOException e) {
      CmdLineUtil.printTrainingIoError(e);
      throw new TerminateToolException(-1);
    }
    finally {
      try {
        sampleStream.close();
      } catch (IOException e) {
View Full Code Here
39
40
41
42
43
44
45
46
47
48
49
  }
 
  public void run(String[] args) {
    if (args.length != 1) {
      System.out.println(getHelp());
      throw new TerminateToolException(1);
    }
   
    TokenizerModel model = new TokenizerModelLoader().load(new File(args[0]));
   
    CommandLineTokenizer tokenizer =
View Full Code Here
67
68
69
70
71
72
73
74
75
76
77
    Parameters params = ArgumentParser.parse(args, Parameters.class);

    Charset encoding = CmdLineUtil.getEncodingParameter(args);

    if (encoding == null) {
      throw new TerminateToolException(1);
    }
   
    ADChunkSampleStream sampleStream = new ADChunkSampleStream(CmdLineUtil.openInFile(new File(params
        .getData())), encoding.name());
View Full Code Here
61
62
63
64
65
66
67
68
69
70
71
    else if ("es".equals(params.getLang())) {
      lang = LANGUAGE.ES;
      language = params.getLang();
    }
    else {
      throw new TerminateToolException(1, "Unsupported language: " + params.getLang());
    }
   
    int typesToGenerate = 0;
   
    if (params.getTypes().contains("per")) {
View Full Code Here
59
60
61
62
63
64
65
66
      System.setOut(new PrintStream(System.out, true, "UTF-8"));

      return new ConllXPOSSampleStream(lineStream);
    } catch (UnsupportedEncodingException e) {
      // this shouldn't happen
      throw new TerminateToolException(-1, "UTF-8 encoding is not supported: " + e.getMessage(), e);
    }
  }
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.