Package edu.umd.cloud9.collection.wikipedia

Examples of edu.umd.cloud9.collection.wikipedia.WikipediaPage

658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
  public DocnoMapping getDocnoMapping() throws IOException {
    return loadDocnoMapping(indexPath, fs);
  }

  public static DocnoMapping loadDocnoMapping(String indexPath, FileSystem fs) throws IOException {
    DocnoMapping mDocMapping = null;
    // load the docid to docno mappings
    try {
      LOG.info("Loading DocnoMapping file...");
      RetrievalEnvironment env = new RetrievalEnvironment(indexPath, fs);

      String className = env.readDocnoMappingClass();
      LOG.info(" - Class name: " + className);
      mDocMapping = (DocnoMapping) Class.forName(className).newInstance();

      Path mappingFile = env.getDocnoMappingData();
      LOG.info(" - File name: " + mappingFile);
      mDocMapping.loadMapping(mappingFile, fs);
      LOG.info("Done!");
    } catch (Exception e) {
      throw new IOException("Error initializing DocnoMapping!");
    }
    return mDocMapping;
View Full Code Here
359
360
361
362
363
364
365
366
367
368
369
    if (list.getLength() > 0) {  conf.set(Constants.StemmedStopwordListQ, list.item(0).getTextContent());  } 
  }

  static float eval(QueryEngine qe, Configuration conf, String setting){
    Qrels qrels = new Qrels(conf.get(Constants.QrelsPath));
    DocnoMapping mapping = qe.getDocnoMapping();
    float apSum = 0, p10Sum = 0;
    Map<String, Accumulator[]> results = qe.getResults();
    for (String qid : results.keySet()) {
      float ap = (float) RankedListEvaluator.computeAP(results.get(qid), mapping,
          qrels.getReldocsForQid(qid));
View Full Code Here
115
116
117
118
119
120
121
122
123
124
125
      return -1;
    }

    RetrievalEnvironment env = new RetrievalEnvironment(indexPath, fs);
    Path mappingFile = env.getDocnoMappingData();
    new ClueWarcDocnoMappingBuilder().build(new Path(collection), mappingFile, conf);

    conf.set(Constants.CollectionName, "ClueWeb:English:Segment" + segment);
    conf.set(Constants.CollectionPath, collection);
    conf.set(Constants.IndexPath, indexPath);
    conf.set(Constants.InputFormat, SequenceFileInputFormat.class.getCanonicalName());
View Full Code Here
82
83
84
85
86
87
88
89
90
91
92
93
94
    if (!fs.exists(p)) {
      sLogger.info("docno-mapping.dat doesn't exist, creating...");
      String[] arr = new String[] { collection, mappingDir.toString(), mappingFile.toString(),
          new Integer(numMappers).toString() };
      NumberTextDocuments tool = new NumberTextDocuments();
      tool.setConf(conf);
      tool.run(arr);

      fs.delete(mappingDir, true);
    }

    // Now we're ready to start the preprocessing pipeline... set
View Full Code Here
79
80
81
82
83
84
85
86
87
88
89
90
91
    // (sequentially-number integer). If it doesn't exist create it.
    Path mappingFile = env.getDocnoMappingData();
    if (!fs.exists(mappingFile)) {
      sLogger.info(mappingFile + " doesn't exist, creating...");
      String[] arr = new String[] { collection, indexPath + "/medline-docid-tmp",  mappingFile.toString(), new Integer(numMappers).toString() };
      NumberMedlineCitations tool = new NumberMedlineCitations();
      tool.setConf(conf);
      tool.run(arr);

      fs.delete(new Path(indexPath + "/medline-docid-tmp"), true);
    }

    // Now we're ready to start the preprocessing pipeline... set
View Full Code Here
82
83
84
85
86
87
88
89
90
91
92
93
94
    if (!fs.exists(mappingFile)) {
      LOG.info("docno-mapping.dat doesn't exist, creating...");
      String[] arr = new String[] { collection, mappingDir.toString(),
              mappingFile.toString() };
      NumberTrecDocuments2 tool = new NumberTrecDocuments2();
      tool.setConf(conf);
      tool.run(arr);

      fs.delete(mappingDir, true);
    }

    conf.set(Constants.CollectionName, "TREC_vol45");
View Full Code Here
82
83
84
85
86
87
88
89
90
91
92
93
94
    if (!fs.exists(mappingFile)) {
      LOG.info("docno-mapping.dat doesn't exist, creating...");
      String[] arr = new String[] { collection, mappingDir.toString(),
          mappingFile.toString(), "100" };
      NumberTrecWebDocuments tool = new NumberTrecWebDocuments();
      tool.setConf(conf);
      tool.run(arr);

      fs.delete(mappingDir, true);
    }

    conf.set(Constants.CollectionName, "Wt10g");
View Full Code Here
82
83
84
85
86
87
88
89
90
91
92
93
94
    if (!fs.exists(mappingFile)) {
      LOG.info("docno-mapping.dat doesn't exist, creating...");
      String[] arr = new String[] { collection, mappingDir.toString(),
          mappingFile.toString(), "100" };
      NumberTrecWebDocuments tool = new NumberTrecWebDocuments();
      tool.setConf(conf);
      tool.run(arr);

      fs.delete(mappingDir, true);
    }

    conf.set(Constants.CollectionName, "Gov2");
View Full Code Here
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
208
209
210
211
          "-output_path=" + indexRootPath + "/wiki-docid-tmp",
          "-output_file=" + mappingFile.toString(),
          "-lang=" + collectionLang };
      LOG.info("Running BuildWikipediaDocnoMapping with args " + Arrays.toString(arr));

      BuildWikipediaDocnoMapping tool = new BuildWikipediaDocnoMapping();
      tool.setConf(conf);
      tool.run(arr);

      fs.delete(new Path(indexRootPath + "/wiki-docid-tmp"), true);
    }

    // Repack Wikipedia into sequential compressed block
    p = new Path(seqCollection);
    LOG.info(seqCollection + " doesn't exist, creating...");
    String[] arr = new String[] { "-input=" + rawCollection,
        "-output=" + seqCollection,
        "-mapping_file=" + mappingFile.toString(),
        "-compression_type=block",
        "-wiki_language=" + collectionLang };
    LOG.info("Running RepackWikipedia with args " + Arrays.toString(arr));

    RepackWikipedia tool = new RepackWikipedia();
    tool.setConf(conf);
    tool.run(arr);

    conf.set(Constants.CollectionName, "Wikipedia-"+collectionLang);
    conf.setInt(Constants.NumMapTasks, numMappers);
    conf.setInt(Constants.NumReduceTasks, numReducers);
    conf.set(Constants.CollectionPath, seqCollection);
View Full Code Here
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
    Path mappingFile = env.getDocnoMappingData();
    if (!fs.exists(mappingFile)) {
      LOG.info(mappingFile + " doesn't exist, creating...");
      String[] arr = new String[] { rawCollection, indexRootPath + "/wiki-docid-tmp",
          mappingFile.toString(), new Integer(numMappers).toString() };
      BuildWikipediaDocnoMapping tool = new BuildWikipediaDocnoMapping();
      tool.setConf(conf);
      tool.run(arr);

      fs.delete(new Path(indexRootPath + "/wiki-docid-tmp"), true);
    }else{
      LOG.info(p+" exists");
    }

    // Repack Wikipedia into sequential compressed block
    p = new Path(seqCollection);
    if (!fs.exists(p)) {
      LOG.info(seqCollection + " doesn't exist, creating...");
      String[] arr = new String[] { rawCollection, seqCollection, mappingFile.toString(), "block"};
      RepackWikipedia tool = new RepackWikipedia();
      tool.setConf(conf);
      tool.run(arr);
    }

    conf.set("Ivory.CollectionName", "Wikipedia-"+collectionLang);
    conf.setInt("Ivory.NumMapTasks", numMappers);
    conf.setInt("Ivory.NumReduceTasks", numReducers);
View Full Code Here
TOP

Related Classes of edu.umd.cloud9.collection.wikipedia.WikipediaPage

  • bak.pcj.IntIterator
  • edu.umd.cloud9.example.bfs.BfsNodeTest
  • edu.umd.cloud9.example.pagerank.PageRankNodeTest
  • edu.umd.cloud9.io.array.ArrayListOfIntsWritable
  • edu.umd.cloud9.io.fastutil.Int2FloatOpenHashMapWritableTest
  • edu.umd.cloud9.io.fastutil.Int2IntOpenHashMapWritableTest
  • edu.umd.cloud9.io.fastutil.String2FloatOpenHashMapWritableTest
  • edu.umd.cloud9.io.fastutil.String2IntOpenHashMapWritableTest
  • edu.umd.cloud9.io.map.HMapIDW
  • edu.umd.cloud9.io.map.HMapIDWTest
    • 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.