Package ivory.core.preprocess

Examples of ivory.core.preprocess.ComputeGlobalTermStatistics$MyMapper

194
195
196
197
198
199
200
201
202
203
204
    Path mappingFile = env.getDocnoMappingData();
    docnoMappingClass.newInstance().getBuilder().build(new Path(collection), mappingFile, conf);

    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
130
131
132
133
134
135
136
137
138
139
140
    conf.setInt(Constants.DocnoOffset, DOCNO_OFFSETS[segment]);
    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
232
233
234
235
236
237
238
239
240
241
242
    }

    // Get CF and DF counts.
    startTime = System.currentTimeMillis();
    LOG.info("Counting terms...");
    exitCode = new ComputeGlobalTermStatistics(conf).run();
    LOG.info("TermCount = " + env.readCollectionTermCount());
    if (exitCode >= 0) {
      LOG.info("Job ComputeGlobalTermStatistics finished in " + (System.currentTimeMillis() - startTime) / 1000.0 + " seconds");
    }else {
      LOG.info("Error: ComputeGlobalTermStatistics. Terminating...");
View Full Code Here
246
247
248
249
250
251
252
253
254
255
256
    }

    // Get CF and DF counts.
    startTime = System.currentTimeMillis();
    LOG.info("Counting terms...");
    exitCode = new ComputeGlobalTermStatistics(conf).run();
    LOG.info("TermCount = " + env.readCollectionTermCount());
    if (exitCode >= 0) {
      LOG.info("Job ComputeGlobalTermStatistics finished in " + (System.currentTimeMillis() - startTime) / 1000.0 + " seconds");
    }else {
      LOG.info("Error: ComputeGlobalTermStatistics. Terminating...");
View Full Code Here
109
110
111
112
113
114
115
116
117
118
119
    conf.setInt("Ivory.MinDf", 2); // toss away singleton terms
    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
68
69
70
71
72
73
74
75
76
77
78
    conf.setInt(Constants.MaxDf, Integer.MAX_VALUE);
    conf.setInt(Constants.TermIndexWindow, 8);
    conf.set(Constants.InputFormat, TrecDocumentInputFormat.class.getCanonicalName());

    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
224
225
226
227
228
229
230
231
232
233
234
    }

    // Get CF and DF counts.
    startTime = System.currentTimeMillis();
    LOG.info("Counting terms...");
    exitCode = new ComputeGlobalTermStatistics(conf).run();
    LOG.info("TermCount = " + env.readCollectionTermCount());
    if (exitCode >= 0) {
      LOG.info("Job ComputeGlobalTermStatistics finished in " + (System.currentTimeMillis() - startTime) / 1000.0 + " seconds");
    }else {
      LOG.info("Error: ComputeGlobalTermStatistics. Terminating...");
View Full Code Here
183
184
185
186
187
188
189
190
191
192
193
    Path mappingFile = env.getDocnoMappingData();
    docnoMappingClass.newInstance().getBuilder().build(new Path(collection), mappingFile, conf);

    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
91
92
93
94
95
96
97
98
99
100
101
    conf.setInt(Constants.DocnoOffset, 0); // docnos start at 1
    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
91
92
93
94
95
96
97
98
99
100
101
    conf.setInt(Constants.DocnoOffset, 0); // docnos start at 1
    conf.setInt(Constants.MinDf, 2); // toss away singleton terms
    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
TOP

Related Classes of ivory.core.preprocess.ComputeGlobalTermStatistics$MyMapper

  • edu.umd.cloud9.collection.clue.ClueWarcForwardIndex
  • edu.umd.cloud9.collection.clue.ClueWarcRecord
  • edu.umd.cloud9.collection.wikipedia.WikipediaPage
  • edu.umd.cloud9.io.array.ArrayListOfIntsWritable
  • edu.umd.cloud9.io.FSLineReader
  • edu.umd.cloud9.io.map.HMapIFW
  • edu.umd.cloud9.io.map.HMapIIW
  • edu.umd.cloud9.io.map.HMapSIW
  • edu.umd.cloud9.io.pair.PairOfIntLong
  • edu.umd.cloud9.io.pair.PairOfInts
    • 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.