Package ivory.core.preprocess

Examples of ivory.core.preprocess.BuildDictionary

92
93
94
95
96
97
98
99
100
101
102
    conf.setInt(Constants.MinDf, 10);
    conf.setInt(Constants.MaxDf, Integer.MAX_VALUE);

    new BuildTermDocVectors(conf).run();
    new ComputeGlobalTermStatistics(conf).run();
    new BuildDictionary(conf).run();
    new BuildIntDocVectors(conf).run();

    new BuildIntDocVectorsForwardIndex(conf).run();
    new BuildTermDocVectorsForwardIndex(conf).run();
View Full Code Here
106
107
108
109
110
111
112
113
114
115
116
    conf.setInt("Ivory.MaxDf", Integer.MAX_VALUE);
    conf.setInt("Ivory.TermIndexWindow", 8);

    new BuildTermDocVectors(conf).run();
    new ComputeGlobalTermStatistics(conf).run();
    new BuildDictionary(conf).run();
    new BuildIntDocVectors(conf).run();

    new BuildIntDocVectorsForwardIndex(conf).run();
    new BuildTermDocVectorsForwardIndex(conf).run();
View Full Code Here
104
105
106
107
108
109
110
111
112
113
114
    conf.setInt(Constants.MaxDf, Integer.MAX_VALUE);
    conf.setInt(Constants.TermIndexWindow, 8);

    new BuildTermDocVectors(conf).run();
    new ComputeGlobalTermStatistics(conf).run();
    new BuildDictionary(conf).run();
    new BuildIntDocVectors(conf).run();

    new BuildIntDocVectorsForwardIndex(conf).run();
    new BuildTermDocVectorsForwardIndex(conf).run();
View Full Code Here
202
203
204
205
206
207
208
209
210
211
212
213
    // Build a map from terms to sequentially generated integer term ids
    startTime = System.currentTimeMillis();
    conf.setInt("Ivory.TermIndexWindow", TermIndexWindow);
    LOG.info("Building term-to-integer id mapping...");
    BuildDictionary termIDsDfCfTool = new BuildDictionary(conf);
    termIDsDfCfTool.run();
    LOG.info("Job finished in "+(System.currentTimeMillis()-startTime)/1000.0+" seconds");

    // Compute term weights, and output weighted term doc vectors
    startTime = System.currentTimeMillis();
    LOG.info("Building weighted term doc vectors...");
View Full Code Here
104
105
106
107
108
109
110
111
112
113
114
    conf.setInt(Constants.MaxDf, Integer.MAX_VALUE);
    conf.setInt(Constants.TermIndexWindow, 8);

    new BuildTermDocVectors(conf).run();
    new ComputeGlobalTermStatistics(conf).run();
    new BuildDictionary(conf).run();
    new BuildIntDocVectors(conf).run();

    new BuildIntDocVectorsForwardIndex(conf).run();
    new BuildTermDocVectorsForwardIndex(conf).run();
View Full Code Here
94
95
96
97
98
99
100
101
102
103
104
    conf.setInt(Constants.MaxDf, Integer.MAX_VALUE);
    conf.setInt(Constants.TermIndexWindow, 8);

    new BuildTermDocVectors(conf).run();
    new ComputeGlobalTermStatistics(conf).run();
    new BuildDictionary(conf).run();
    new BuildIntDocVectors(conf).run();

    new BuildIntDocVectorsForwardIndex(conf).run();
    new BuildTermDocVectorsForwardIndex(conf).run();
View Full Code Here
98
99
100
101
102
103
104
105
106
107
108
    conf.setInt(Constants.MaxDf, Integer.MAX_VALUE);
    conf.setInt(Constants.TermIndexWindow, 8);

    new BuildTermDocVectors(conf).run();
    new ComputeGlobalTermStatistics(conf).run();
    new BuildDictionary(conf).run();
    new BuildIntDocVectors(conf).run();

    new BuildIntDocVectorsForwardIndex(conf).run();
    new BuildTermDocVectorsForwardIndex(conf).run();
View Full Code Here
104
105
106
107
108
109
110
111
112
113
114
    conf.setInt(Constants.MaxDf, Integer.MAX_VALUE);
    conf.setInt(Constants.TermIndexWindow, 8);

    new BuildTermDocVectors(conf).run();
    new ComputeGlobalTermStatistics(conf).run();
    new BuildDictionary(conf).run();
    new BuildIntDocVectors(conf).run();

    new BuildIntDocVectorsForwardIndex(conf).run();
    new BuildTermDocVectorsForwardIndex(conf).run();
View Full Code Here
243
244
245
246
247
248
249
250
251
252
253
      return -1;
    }
    // Build a map from terms to sequentially generated integer term ids.
    startTime = System.currentTimeMillis();
    LOG.info("Building term-to-integer id mapping...");
    exitCode = new BuildDictionary(conf).run();
    if (exitCode >= 0) {
      LOG.info("Job BuildDictionary finished in " + (System.currentTimeMillis() - startTime) / 1000.0 + " seconds");
    }else{
      LOG.info("Error: BuildDictionary. Terminating...");
      return -1;
View Full Code Here
256
257
258
259
260
261
262
263
264
265
266
      return -1;
    }
    // Build a map from terms to sequentially generated integer term ids.
    startTime = System.currentTimeMillis();
    LOG.info("Building term-to-integer id mapping...");
    exitCode = new BuildDictionary(conf).run();
    if (exitCode >= 0) {
      LOG.info("Job BuildDictionary finished in " + (System.currentTimeMillis() - startTime) / 1000.0 + " seconds");
    }else{
      LOG.info("Error: BuildDictionary. Terminating...");
      return -1;
View Full Code Here
TOP

Related Classes of ivory.core.preprocess.BuildDictionary

  • edu.umd.cloud9.io.pair.PairOfIntLong
  • it.unimi.dsi.util.FrontCodedStringList
  • it.unimi.dsi.util.ShiftAddXorSignedStringMap
  • ivory.app.GenericIndexBuilder
  • ivory.app.PreprocessClueWebEnglish
  • ivory.app.PreprocessClueWebEnglishMultipleSegments
  • ivory.app.PreprocessCollection
  • ivory.app.PreprocessGov2
  • ivory.app.PreprocessMedline
  • ivory.app.PreprocessTextCollection
    • 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.