Package de.lmu.ifi.dbs.elki.database.ids

Examples of de.lmu.ifi.dbs.elki.database.ids.ModifiableDBIDs

368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
    return minmax;
  }

  private void shrinkHeap(TreeSet<FCPair<Double, DBID>> hotset, int k) {
    // drop duplicates
    ModifiableDBIDs seenids = DBIDUtil.newHashSet(2 * k);
    int cnt = 0;
    for(Iterator<FCPair<Double, DBID>> i = hotset.iterator(); i.hasNext();) {
      FCPair<Double, DBID> p = i.next();
      if(cnt > k || seenids.contains(p.getSecond())) {
        i.remove();
      }
      else {
        seenids.add(p.getSecond());
        cnt++;
      }
    }
  }
View Full Code Here
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
    if(scaling instanceof OutlierScalingFunction) {
      OutlierScalingFunction oscaling = (OutlierScalingFunction) scaling;
      oscaling.prepare(or);
    }

    ModifiableDBIDs ids = DBIDUtil.newHashSet(or.getScores().getDBIDs());
    DBIDs outlierIds = DatabaseUtil.getObjectsByLabelMatch(database, positiveClassName);
    // first value for outliers, second for each object
    final AggregatingHistogram<DoubleDoublePair, DoubleDoublePair> hist;
    // If we have useful (finite) min/max, use these for binning.
    double min = scaling.getMin();
    double max = scaling.getMax();
    if(Double.isInfinite(min) || Double.isNaN(min) || Double.isInfinite(max) || Double.isNaN(max)) {
      hist = FlexiHistogram.DoubleSumDoubleSumHistogram(bins);
    }
    else {
      hist = AggregatingHistogram.DoubleSumDoubleSumHistogram(bins, min, max);
    }
    // first fill histogram only with values of outliers
    DoubleDoublePair positive, negative;
    if(!splitfreq) {
      positive = new DoubleDoublePair(0., 1. / ids.size());
      negative = new DoubleDoublePair(1. / ids.size(), 0.);
    }
    else {
      positive = new DoubleDoublePair(0., 1. / outlierIds.size());
      negative = new DoubleDoublePair(1. / (ids.size() - outlierIds.size()), 0.);
    }
    ids.removeDBIDs(outlierIds);
    // fill histogram with values of each object
    for(DBID id : ids) {
      double result = or.getScores().get(id);
      result = scaling.getScaled(result);
      hist.aggregate(result, negative);
View Full Code Here
174
175
176
177
178
179
180
181
182
183
184
185
186
    if(ors == null || ors.size() <= 0) {
      // logger.warning("No results found for "+JudgeOutlierScores.class.getSimpleName());
      return;
    }

    ModifiableDBIDs ids = DBIDUtil.newHashSet(ors.iterator().next().getScores().getDBIDs());
    DBIDs outlierIds = DatabaseUtil.getObjectsByLabelMatch(db, positiveClassName);
    ids.removeDBIDs(outlierIds);

    for(OutlierResult or : ors) {
      db.getHierarchy().add(or, computeScore(ids, outlierIds, or));
    }
  }
View Full Code Here
133
134
135
136
137
138
139
140
141
142
143
144
   * Return a collection of all IDs in the cache.
   *
   * @return Collection of all IDs in the cache.
   */
  public DBIDs getIDs() {
    ModifiableDBIDs ids = DBIDUtil.newTreeSet();
    for(DBIDPair pair : cache.keySet()) {
      ids.add(pair.getFirst());
      ids.add(pair.getSecond());
    }
    return ids;
  }
View Full Code Here
53
54
55
56
57
58
59
60
61
62
63
64
  @Override
  public abstract Matrix processIds(DBIDs ids, Relation<? extends V> database);

  @Override
  public <D extends NumberDistance<?, ?>> Matrix processQueryResults(Collection<DistanceResultPair<D>> results, Relation<? extends V> database, int k) {
    ModifiableDBIDs ids = DBIDUtil.newArray(k);
    int have = 0;
    for(Iterator<DistanceResultPair<D>> it = results.iterator(); it.hasNext() && have < k; have++) {
      ids.add(it.next().getDBID());
    }
    return processIds(ids, database);
  }
View Full Code Here
175
176
177
178
179
180
181
182
183
184
185
186
187
          }
        }
      }
    }
    else {
      ModifiableDBIDs ids = DBIDUtil.newArray(knnLists.size());
      for(DBID id : knnLists.keySet()) {
        ids.add(id);
      }
      List<DistanceEntry<D, SpatialEntry>> entries = getSortedEntries(node, ids);
      for(DistanceEntry<D, SpatialEntry> distEntry : entries) {
        D minDist = distEntry.getDistance();
        for(Entry<DBID, KNNHeap<D>> ent : knnLists.entrySet()) {
View Full Code Here
176
177
178
179
180
181
182
183
184
185
186
187
188
          }
        }
      }
    }
    else {
      ModifiableDBIDs ids = DBIDUtil.newArray(knnLists.size());
      for(DBID id : knnLists.keySet()) {
        ids.add(id);
      }
      List<DoubleDistanceEntry> entries = getSortedEntries(node, ids);
      for(DoubleDistanceEntry distEntry : entries) {
        double minDist = distEntry.distance;
        for(Entry<DBID, KNNHeap<DoubleDistance>> ent : knnLists.entrySet()) {
View Full Code Here
133
134
135
136
137
138
139
140
141
142
143
144
   * Return a collection of all IDs in the cache.
   *
   * @return Collection of all IDs in the cache.
   */
  public DBIDs getIDs() {
    ModifiableDBIDs ids = DBIDUtil.newHashSet();
    for(DBIDPair pair : cache.keySet()) {
      ids.add(pair.getFirst());
      ids.add(pair.getSecond());
    }
    return ids;
  }
View Full Code Here
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
      return candidates;
    }

    // refinement of candidates
    Map<DBID, KNNHeap<D>> knnLists = new HashMap<DBID, KNNHeap<D>>();
    ModifiableDBIDs candidateIDs = DBIDUtil.newArray();
    for(DistanceResultPair<D> candidate : candidates) {
      KNNHeap<D> knns = new KNNHeap<D>(k, getDistanceQuery().infiniteDistance());
      knnLists.put(candidate.getDBID(), knns);
      candidateIDs.add(candidate.getDBID());
    }
    batchNN(getRoot(), candidateIDs, knnLists);

    List<DistanceResultPair<D>> result = new ArrayList<DistanceResultPair<D>>();
    for(DBID cid : candidateIDs) {
View Full Code Here
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
    if(!initialized) {
      initialize(entries.get(0));
    }

    Map<DBID, KNNHeap<D>> knnHeaps = new HashMap<DBID, KNNHeap<D>>(entries.size());
    ModifiableDBIDs ids = DBIDUtil.newArray(entries.size());

    // insert
    for(MkCoPEntry<D> entry : entries) {
      DBID id = entry.getRoutingObjectID();
      // create knnList for the object
      knnHeaps.put(id, new KNNHeap<D>(k_max + 1, getDistanceQuery().infiniteDistance()));

      ids.add(id);
      // insert the object
      super.insert(entry, false);
    }

    // do batch nn
View Full Code Here
TOP

Related Classes of de.lmu.ifi.dbs.elki.database.ids.ModifiableDBIDs

  • de.lmu.ifi.dbs.elki.algorithm.clustering.AbstractProjectedDBSCAN
  • de.lmu.ifi.dbs.elki.algorithm.clustering.correlation.CASH
  • de.lmu.ifi.dbs.elki.algorithm.clustering.correlation.cash.CASHInterval
  • de.lmu.ifi.dbs.elki.algorithm.clustering.correlation.cash.CASHIntervalSplit
  • de.lmu.ifi.dbs.elki.algorithm.clustering.correlation.COPAC
  • de.lmu.ifi.dbs.elki.algorithm.clustering.correlation.ERiC
  • de.lmu.ifi.dbs.elki.algorithm.clustering.correlation.LMCLUS
  • de.lmu.ifi.dbs.elki.algorithm.clustering.DBSCAN
  • de.lmu.ifi.dbs.elki.algorithm.clustering.KMeans
  • de.lmu.ifi.dbs.elki.algorithm.clustering.kmeans.AbstractKMeans
    • 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.