How to use

preprocess

method

in

de.lmu.ifi.dbs.elki.algorithm.clustering.gdbscan.PreDeConNeighborPredicate

@SuppressWarnings("unchecked")
@Override
public Instance instantiate(Database database) {
 DistanceQuery<V> dq = QueryUtil.getDistanceQuery(database, distFunc);
 Relation<V> relation = (Relation<V>) dq.getRelation();
 RangeQuery<V> rq = database.getRangeQuery(dq);
 mvSize.reset();
 mvVar.reset();
 DataStore<PreDeConModel> storage = preprocess(PreDeConModel.class, relation, rq);
 if(LOG.isVerbose()) {
  LOG.verbose("Average neighborhood size: " + mvSize.toString());
  LOG.verbose("Average variance size: " + mvVar.toString());
  final int dim = RelationUtil.dimensionality(relation);
  if(mvSize.getMean() < 5 * dim) {
   LOG.verbose("The epsilon parameter may be chosen too small.");
  }
  else if(mvSize.getMean() > .5 * relation.size()) {
   LOG.verbose("The epsilon parameter may be chosen too large.");
  }
  else {
   LOG.verbose("As a first guess, you can try minPts < " + ((int) mvSize.getMean() / dim) //
     + " and delta > " + mvVar.getMean() + //
     ", but you will need to experiment with these parameters and epsilon.");
  }
 }
 return new Instance(dq.getRelation().getDBIDs(), storage);
}

@SuppressWarnings("unchecked")
@Override
public <T> NeighborPredicate.Instance<T> instantiate(Database database, SimpleTypeInformation<?> type) {
 DistanceQuery<V> dq = QueryUtil.getDistanceQuery(database, distFunc);
 Relation<V> relation = (Relation<V>) dq.getRelation();
 RangeQuery<V> rq = database.getRangeQuery(dq);
 mvSize.reset();
 mvVar.reset();
 DataStore<PreDeConModel> storage = preprocess(PreDeConModel.class, relation, rq);
 if(LOG.isVerbose()) {
  LOG.verbose("Average neighborhood size: " + mvSize.toString());
  LOG.verbose("Average variance size: " + mvVar.toString());
  final int dim = RelationUtil.dimensionality(relation);
  if(mvSize.getMean() < 5 * dim) {
   LOG.verbose("The epsilon parameter may be chosen too small.");
  }
  else if(mvSize.getMean() > .5 * relation.size()) {
   LOG.verbose("The epsilon parameter may be chosen too large.");
  }
  else {
   LOG.verbose("As a first guess, you can try minPts < " + ((int) mvSize.getMean() / dim) //
     + " and delta > " + mvVar.getMean() + //
     ", but you will need to experiment with these parameters and epsilon.");
  }
 }
 return (NeighborPredicate.Instance<T>) new Instance(dq.getRelation().getDBIDs(), storage);
}

@SuppressWarnings("unchecked")
@Override
public Instance instantiate(Database database) {
 DistanceQuery<V> dq = QueryUtil.getDistanceQuery(database, distFunc);
 Relation<V> relation = (Relation<V>) dq.getRelation();
 RangeQuery<V> rq = database.getRangeQuery(dq);
 mvSize.reset();
 mvVar.reset();
 DataStore<PreDeConModel> storage = preprocess(PreDeConModel.class, relation, rq);
 if(LOG.isVerbose()) {
  LOG.verbose("Average neighborhood size: " + mvSize.toString());
  LOG.verbose("Average variance size: " + mvVar.toString());
  final int dim = RelationUtil.dimensionality(relation);
  if(mvSize.getMean() < 5 * dim) {
   LOG.verbose("The epsilon parameter may be chosen too small.");
  }
  else if(mvSize.getMean() > .5 * relation.size()) {
   LOG.verbose("The epsilon parameter may be chosen too large.");
  }
  else {
   LOG.verbose("As a first guess, you can try minPts < " + ((int) mvSize.getMean() / dim) //
     + " and delta > " + mvVar.getMean() + //
     ", but you will need to experiment with these parameters and epsilon.");
  }
 }
 return new Instance(dq.getRelation().getDBIDs(), storage);
}