Package org.terrier.structures

Examples of org.terrier.structures.EntryStatistics

301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
   
   
    for (int i = 0; i < queryLength; i++) {
     
      //get the entry statistics - perhaps this came from "far away"
      EntryStatistics entryStats = queryTerms.getStatistics(queryTermStrings[i]);
      //we seek the query term in the lexicon
      LexiconEntry lEntry = lexicon.getLexiconEntry(queryTermStrings[i]);
      if (entryStats == null)
        entryStats = lEntry;
     
      //and if it is not found, we continue with the next term
      if (lEntry==null)
      {
        //logger.info("Term Not Found: "+queryTermStrings[i]);
        continue;
      }
      queryTerms.setTermProperty(queryTermStrings[i], lEntry);
      logger.debug((i + 1) + ": " + queryTermStrings[i].trim() + " with " + entryStats.getDocumentFrequency()
          + " documents (TF is " + entryStats.getFrequency() + ").");
     
      //check if the IDF is very low.
      if (IGNORE_LOW_IDF_TERMS && collectionStatistics.getNumberOfDocuments() < lEntry.getFrequency()) {
        logger.debug("query term " + queryTermStrings[i] + " has low idf - ignored from scoring.");
        continue;
View Full Code Here
210
211
212
213
214
215
216
217
218
219
220
    {
      Map.Entry<String, LexiconEntry> termEntry    = queryTermsToMatchList.get(i);
      String               queryTerm    = termEntry.getKey();
      LexiconEntry           lexiconEntry = termEntry.getValue();
      //get the entry statistics - perhaps this came from "far away"
      EntryStatistics entryStats = queryTerms.getStatistics(queryTerm);
      //if none were provided with the query we seek the entry statistics query term in the lexicon
      if (entryStats == null)
      {
        entryStats = lexiconEntry;
        //save them as they may be useful for query expansion. HOWEVER ONLY IF we didnt
View Full Code Here
225
226
227
228
229
230
231
232
233
234
  /** Knows how to merge several EntryStatistics for a single effective term */
  public static EntryStatistics mergeStatistics(EntryStatistics[] entryStats)
  {
    if (entryStats == null)
      return null;
    EntryStatistics rtr = entryStats[0];
    for(int i=1;i<entryStats.length;i++)
      rtr.add(entryStats[i]);
    return rtr;
  }
View Full Code Here
242
243
244
245
246
247
248
249
   * @param wmodels WeightingModels for the synonym group (NOT one per member).
   * @throws IOException
   */
  public void addSingleTermAlternatives(String[] terms, String stringForm,  double weight, EntryStatistics[] entryStats, WeightingModel[] wmodels) throws IOException
  {   
    EntryStatistics joined = mergeStatistics(entryStats);
    addSingleTermAlternatives(terms, stringForm, weight, joined, wmodels);
  }
View Full Code Here
76
77
78
79
80
81
82
83
84
85
86
87
  public void setOriginalQueryTerms(MatchingQueryTerms query){
    String[] terms = query.getTerms();
    this.originalTermids.clear();
    for (int i=0; i<terms.length; i++)
      {
      EntryStatistics te = query.getStatistics(terms[i]);
      if (te != null) {
        this.originalTermids.put(te.getTermId(), terms[i]);
        this.originalTermFreqs.adjustOrPutValue(te.getTermId(), query.getTermWeight(terms[i]), query.getTermWeight(terms[i]));
      }
    }
  }
View Full Code Here
56
57
58
59
60
61
62
63
64
65
66
    assertEquals(1, mqt.length()); 
    assertEquals(1, mqt.getTerms().length); 
    assertEquals(term, mqt.getTerms()[0]);
    assertEquals(1.0d, mqt.getTermWeight(term), 0.0d);
    assertNull(mqt.getStatistics(term));
    EntryStatistics e = new BasicLexiconEntry(2, 1, 100);
    mqt.setTermProperty(term, e);
    assertEquals(2, mqt.getStatistics(term).getTermId());
    assertEquals(1, mqt.getStatistics(term).getDocumentFrequency());
    assertEquals(100, mqt.getStatistics(term).getFrequency());
  }
View Full Code Here
81
82
83
84
85
86
87
88
89
90
91
    assertEquals(1, mqt.length()); 
    assertEquals(1, mqt.getTerms().length); 
    assertEquals(term, mqt.getTerms()[0]);
    assertEquals(1.0d, mqt.getTermWeight(term), 0.0d);
    assertNull(mqt.getStatistics(term));
    EntryStatistics e = new BasicLexiconEntry(2, 1, 100);
    mqt.setTermProperty(term, e);
    assertEquals(2, mqt.getStatistics(term).getTermId());
    assertEquals(1, mqt.getStatistics(term).getDocumentFrequency());
    assertEquals(100, mqt.getStatistics(term).getFrequency());
  }
View Full Code Here
106
107
108
109
110
111
112
113
114
115
116
117
    assertEquals(1.0d, mqt.getTermWeight(term2), 0.0d);
   
    assertNull(mqt.getStatistics(term1));
    assertNull(mqt.getStatistics(term2));
       
    EntryStatistics e1 = new BasicLexiconEntry(2, 1, 100);
    EntryStatistics e2 = new BasicLexiconEntry(40, 100, 102);
    mqt.setTermProperty(term1, e1);
    mqt.setTermProperty(term2, e2);
   
    assertEquals(2, mqt.getStatistics(term1).getTermId());
    assertEquals(40, mqt.getStatistics(term2).getTermId());
View Full Code Here
132
133
134
135
136
137
138
139
140
141
142
    assertEquals(1, mqt.length()); 
    assertEquals(1, mqt.getTerms().length); 
    assertEquals(term, mqt.getTerms()[0]);
    assertEquals(1.0d, mqt.getTermWeight(term), 0.0d);
    assertNull(mqt.getStatistics(term));
    EntryStatistics e = new BasicLexiconEntry(2, 1, 100);
    mqt.setTermProperty(term, e);
    assertEquals(2, mqt.getStatistics(term).getTermId());
    assertEquals(1, mqt.getStatistics(term).getDocumentFrequency());
    assertEquals(100, mqt.getStatistics(term).getFrequency());
  }
View Full Code Here
151
152
153
154
155
156
157
158
159
160
161
    assertEquals(1, mqt.length()); 
    assertEquals(1, mqt.getTerms().length); 
    assertEquals(term, mqt.getTerms()[0]);
    assertEquals(1.0d, mqt.getTermWeight(term), 0.0d);
    assertNull(mqt.getStatistics(term));
    EntryStatistics e = new BasicLexiconEntry(2, 1, 100);
    mqt.setTermProperty(term, e);
    assertEquals(2, mqt.getStatistics(term).getTermId());
    assertEquals(1, mqt.getStatistics(term).getDocumentFrequency());
    assertEquals(100, mqt.getStatistics(term).getFrequency());
  }
View Full Code Here
TOP

Related Classes of org.terrier.structures.EntryStatistics

  • org.terrier.matching.BaseMatching
  • org.terrier.matching.OldBasicMatching
  • org.terrier.matching.PostingListManager
  • org.terrier.matching.TestMatchingQueryTerms
  • org.terrier.querying.ExpansionTerms
    • 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.