Package org.apache.lucene.util

Examples of org.apache.lucene.util.OpenBitSet.cardinality()

202
203
204
205
206
207
208
209
210
211
212
        }

        // AND the term's bitset with cluster doc bitset to get the term's in-cluster frequency.
        // This modifies the termBitset, but that's fine as we are not using it anywhere else.
        termBitset.and(clusterDocBitset);
        int inclusterDF = (int) termBitset.cardinality();

        TermEntry entry = new TermEntry(term.text(), count++, inclusterDF);
        termEntryMap.put(entry.getTerm(), entry);
      } while (te.next());
    } finally {
View Full Code Here
255
256
257
258
259
260
261
262
263
264
265
      }
      if (idSet.contains(id)) {
        bitset.set(i);
      }
    }
    log.info("Created bitset for in-cluster documents : {}", bitset.cardinality());
    return bitset;
  }

  private static double scoreDocumentFrequencies(long inDF, long outDF, long clusterSize, long corpusSize) {
    long k12 = clusterSize - inDF;
View Full Code Here
236
237
238
239
240
241
242
243
244
245
246
      }

      // AND the term's bitset with cluster doc bitset to get the term's in-cluster frequency.
      // This modifies the termBitset, but that's fine as we are not using it anywhere else.
      termBitset.and(clusterDocBitset);
      int inclusterDF = (int) termBitset.cardinality();

      TermEntry entry = new TermEntry(term.text(), count++, inclusterDF);
      termEntryMap.put(entry.term, entry);
    } while (te.next());
    te.close();
View Full Code Here
286
287
288
289
290
291
292
293
294
295
296
      }
      if (idSet.contains(id)) {
        bitset.set(i);
      }
    }
    log.info("Created bitset for in-cluster documents : {}", bitset.cardinality());
    return bitset;
  }

  private static double scoreDocumentFrequencies(int inDF, int outDF, int clusterSize, int corpusSize) {
    int k12 = clusterSize - inDF;
View Full Code Here
60
61
62
63
64
65
66
67
68
69
70
    ScoredDocIDs scoredDocIDs = ScoredDocIdsUtils.createScoredDocIds(bits, n);

    Directory dir = newDirectory();
    IndexReader reader = createReaderWithNDocs(random, n, dir);
    try {
      assertEquals(n - verify.cardinality(), ScoredDocIdsUtils.getComplementSet(scoredDocIDs,
        reader).size());
    } finally {
      reader.close();
      dir.close();
    }
View Full Code Here
550
551
552
553
554
555
556
557
558
559
560
          sumTotalTermFreq += totalTermFreq;
          totalTermFreq = 0;
          termCount++;
        }
      }
      docCount = (int) visitedDocs.cardinality();
      fst = b.finish();
      /*
      PrintStream ps = new PrintStream("out.dot");
      fst.toDot(ps);
      ps.close();
View Full Code Here
162
163
164
165
166
167
168
169
170
171
172
      }
    }
    // collisions resolved, now re-queue
    // empty (partially) the queue until seeing all pps advanced for resolving collisions
    int n = 0;
    while (bits.cardinality() > 0) {
      PhrasePositions pp2 = pq.pop();
      rptStack[n++] = pp2;
      if (pp2.rptGroup >= 0 && bits.get(pp2.rptInd)) {
        bits.clear(pp2.rptInd);
      }
View Full Code Here
206
207
208
209
210
211
212
213
214
215
216
        }
      }
      // AND the term's bitset with cluster doc bitset to get the term's in-cluster frequency.
      // This modifies the termBitset, but that's fine as we are not using it anywhere else.
      termBitset.and(clusterDocBitset);
      int inclusterDF = (int) termBitset.cardinality();

      TermEntry entry = new TermEntry(term.utf8ToString(), count++, inclusterDF);
      termEntryMap.put(entry.getTerm(), entry);

    }
View Full Code Here
262
263
264
265
266
267
268
269
270
271
272
      }
      if (idSet.contains(id)) {
        bitset.set(i);
      }
    }
    log.info("Created bitset for in-cluster documents : {}", bitset.cardinality());
    return bitset;
  }

  private static double scoreDocumentFrequencies(long inDF, long outDF, long clusterSize, long corpusSize) {
    long k12 = clusterSize - inDF;
View Full Code Here
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
      }
    }
    if (maxOrd != maxOrd2) {
      throw new RuntimeException("dv for field: " + fieldName + " reports wrong maxOrd=" + maxOrd + " but this is not the case: " + maxOrd2);
    }
    if (seenOrds.cardinality() != dv.getValueCount()) {
      throw new RuntimeException("dv for field: " + fieldName + " has holes in its ords, valueCount=" + dv.getValueCount() + " but only used: " + seenOrds.cardinality());
    }
   
    BytesRef lastValue = null;
    BytesRef scratch = new BytesRef();
View Full Code Here
TOP
Copyright © 2018 www.massapi.com. 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.