use of de.lmu.ifi.dbs.elki.database.ids.DoubleDBIDListIter in project elki by elki-project.
the class MkCoPTree method reverseKNNQuery.
/**
* Performs a reverse k-nearest neighbor query for the given object ID. The
* query result is in ascending order to the distance to the query object.
*
* @param id the query object id
* @param k the number of nearest neighbors to be returned
* @return a List of the query results
*/
@Override
public DoubleDBIDList reverseKNNQuery(DBIDRef id, int k) {
if (k > settings.kmax) {
throw new IllegalArgumentException("Parameter k has to be less or equal than " + "parameter kmax of the MCop-Tree!");
}
ModifiableDoubleDBIDList result = DBIDUtil.newDistanceDBIDList();
ModifiableDBIDs candidates = DBIDUtil.newArray();
doReverseKNNQuery(k, id, result, candidates);
// refinement of candidates
Map<DBID, KNNList> knnLists = batchNN(getRoot(), candidates, k);
result.sort();
for (DBIDIter iter = candidates.iter(); iter.valid(); iter.advance()) {
DBID cid = DBIDUtil.deref(iter);
KNNList cands = knnLists.get(cid);
for (DoubleDBIDListIter iter2 = cands.iter(); iter2.valid(); iter2.advance()) {
if (DBIDUtil.equal(id, iter2)) {
result.add(iter2.doubleValue(), cid);
break;
}
}
}
result.sort();
// rkNNStatistics.addResults(result.size());
return result;
}
use of de.lmu.ifi.dbs.elki.database.ids.DoubleDBIDListIter in project elki by elki-project.
the class LDF method run.
/**
* Run the naive kernel density LOF algorithm.
*
* @param database Database to query
* @param relation Data to process
* @return LOF outlier result
*/
public OutlierResult run(Database database, Relation<O> relation) {
StepProgress stepprog = LOG.isVerbose() ? new StepProgress("LDF", 3) : null;
final int dim = RelationUtil.dimensionality(relation);
DBIDs ids = relation.getDBIDs();
LOG.beginStep(stepprog, 1, "Materializing neighborhoods w.r.t. distance function.");
KNNQuery<O> knnq = DatabaseUtil.precomputedKNNQuery(database, relation, getDistanceFunction(), k);
// Compute LDEs
LOG.beginStep(stepprog, 2, "Computing LDEs.");
WritableDoubleDataStore ldes = DataStoreUtil.makeDoubleStorage(ids, DataStoreFactory.HINT_HOT | DataStoreFactory.HINT_TEMP);
FiniteProgress densProgress = LOG.isVerbose() ? new FiniteProgress("Densities", ids.size(), LOG) : null;
for (DBIDIter it = ids.iter(); it.valid(); it.advance()) {
final KNNList neighbors = knnq.getKNNForDBID(it, k);
double sum = 0.0;
int count = 0;
// Fast version for double distances
for (DoubleDBIDListIter neighbor = neighbors.iter(); neighbor.valid(); neighbor.advance()) {
if (DBIDUtil.equal(neighbor, it)) {
continue;
}
final double nkdist = knnq.getKNNForDBID(neighbor, k).getKNNDistance();
if (!(nkdist > 0.) || nkdist == Double.POSITIVE_INFINITY) {
sum = Double.POSITIVE_INFINITY;
count++;
break;
}
final double v = MathUtil.max(nkdist, neighbor.doubleValue()) / (h * nkdist);
sum += kernel.density(v) / MathUtil.powi(h * nkdist, dim);
count++;
}
ldes.putDouble(it, sum / count);
LOG.incrementProcessed(densProgress);
}
LOG.ensureCompleted(densProgress);
// Compute local density factors.
LOG.beginStep(stepprog, 3, "Computing LDFs.");
WritableDoubleDataStore ldfs = DataStoreUtil.makeDoubleStorage(ids, DataStoreFactory.HINT_STATIC);
// track the maximum value for normalization.
DoubleMinMax lofminmax = new DoubleMinMax();
FiniteProgress progressLOFs = LOG.isVerbose() ? new FiniteProgress("Local Density Factors", ids.size(), LOG) : null;
for (DBIDIter it = ids.iter(); it.valid(); it.advance()) {
final double lrdp = ldes.doubleValue(it);
final KNNList neighbors = knnq.getKNNForDBID(it, k);
double sum = 0.0;
int count = 0;
for (DBIDIter neighbor = neighbors.iter(); neighbor.valid(); neighbor.advance()) {
// skip the point itself
if (DBIDUtil.equal(neighbor, it)) {
continue;
}
sum += ldes.doubleValue(neighbor);
count++;
}
sum /= count;
final double div = lrdp + c * sum;
double ldf = div == Double.POSITIVE_INFINITY ? (sum < Double.POSITIVE_INFINITY ? 0. : 1) : (div > 0) ? sum / div : 0;
ldfs.putDouble(it, ldf);
// update minimum and maximum
lofminmax.put(ldf);
LOG.incrementProcessed(progressLOFs);
}
LOG.ensureCompleted(progressLOFs);
LOG.setCompleted(stepprog);
// Build result representation.
DoubleRelation scoreResult = new MaterializedDoubleRelation("Local Density Factor", "ldf-outlier", ldfs, ids);
OutlierScoreMeta scoreMeta = new BasicOutlierScoreMeta(lofminmax.getMin(), lofminmax.getMax(), 0.0, 1. / c, 1 / (1 + c));
OutlierResult result = new OutlierResult(scoreMeta, scoreResult);
return result;
}
use of de.lmu.ifi.dbs.elki.database.ids.DoubleDBIDListIter in project elki by elki-project.
the class LOCI method run.
/**
* Run the algorithm
*
* @param database Database to process
* @param relation Relation to process
* @return Outlier result
*/
public OutlierResult run(Database database, Relation<O> relation) {
DistanceQuery<O> distFunc = database.getDistanceQuery(relation, getDistanceFunction());
RangeQuery<O> rangeQuery = database.getRangeQuery(distFunc);
DBIDs ids = relation.getDBIDs();
// LOCI preprocessing step
WritableDataStore<DoubleIntArrayList> interestingDistances = DataStoreUtil.makeStorage(relation.getDBIDs(), DataStoreFactory.HINT_TEMP | DataStoreFactory.HINT_SORTED, DoubleIntArrayList.class);
precomputeInterestingRadii(ids, rangeQuery, interestingDistances);
// LOCI main step
FiniteProgress progressLOCI = LOG.isVerbose() ? new FiniteProgress("LOCI scores", relation.size(), LOG) : null;
WritableDoubleDataStore mdef_norm = DataStoreUtil.makeDoubleStorage(relation.getDBIDs(), DataStoreFactory.HINT_STATIC);
WritableDoubleDataStore mdef_radius = DataStoreUtil.makeDoubleStorage(relation.getDBIDs(), DataStoreFactory.HINT_STATIC);
DoubleMinMax minmax = new DoubleMinMax();
// Shared instance, to save allocations.
MeanVariance mv_n_r_alpha = new MeanVariance();
for (DBIDIter iditer = ids.iter(); iditer.valid(); iditer.advance()) {
final DoubleIntArrayList cdist = interestingDistances.get(iditer);
final double maxdist = cdist.getDouble(cdist.size() - 1);
final int maxneig = cdist.getInt(cdist.size() - 1);
double maxmdefnorm = 0.0;
double maxnormr = 0;
if (maxneig >= nmin) {
// Compute the largest neighborhood we will need.
DoubleDBIDList maxneighbors = rangeQuery.getRangeForDBID(iditer, maxdist);
// For any critical distance, compute the normalized MDEF score.
for (int i = 0, size = cdist.size(); i < size; i++) {
// Only start when minimum size is fulfilled
if (cdist.getInt(i) < nmin) {
continue;
}
final double r = cdist.getDouble(i);
final double alpha_r = alpha * r;
// compute n(p_i, \alpha * r) from list (note: alpha_r is not cdist!)
final int n_alphar = cdist.getInt(cdist.find(alpha_r));
// compute \hat{n}(p_i, r, \alpha) and the corresponding \simga_{MDEF}
mv_n_r_alpha.reset();
for (DoubleDBIDListIter neighbor = maxneighbors.iter(); neighbor.valid(); neighbor.advance()) {
// Stop at radius r
if (neighbor.doubleValue() > r) {
break;
}
DoubleIntArrayList cdist2 = interestingDistances.get(neighbor);
int rn_alphar = cdist2.getInt(cdist2.find(alpha_r));
mv_n_r_alpha.put(rn_alphar);
}
// We only use the average and standard deviation
final double nhat_r_alpha = mv_n_r_alpha.getMean();
final double sigma_nhat_r_alpha = mv_n_r_alpha.getNaiveStddev();
// Redundant divisions by nhat_r_alpha removed.
final double mdef = nhat_r_alpha - n_alphar;
final double sigmamdef = sigma_nhat_r_alpha;
final double mdefnorm = mdef / sigmamdef;
if (mdefnorm > maxmdefnorm) {
maxmdefnorm = mdefnorm;
maxnormr = r;
}
}
} else {
// FIXME: when nmin was not fulfilled - what is the proper value then?
maxmdefnorm = Double.POSITIVE_INFINITY;
maxnormr = maxdist;
}
mdef_norm.putDouble(iditer, maxmdefnorm);
mdef_radius.putDouble(iditer, maxnormr);
minmax.put(maxmdefnorm);
LOG.incrementProcessed(progressLOCI);
}
LOG.ensureCompleted(progressLOCI);
DoubleRelation scoreResult = new MaterializedDoubleRelation("LOCI normalized MDEF", "loci-mdef-outlier", mdef_norm, relation.getDBIDs());
OutlierScoreMeta scoreMeta = new QuotientOutlierScoreMeta(minmax.getMin(), minmax.getMax(), 0.0, Double.POSITIVE_INFINITY, 0.0);
OutlierResult result = new OutlierResult(scoreMeta, scoreResult);
result.addChildResult(new MaterializedDoubleRelation("LOCI MDEF Radius", "loci-critical-radius", mdef_radius, relation.getDBIDs()));
return result;
}
use of de.lmu.ifi.dbs.elki.database.ids.DoubleDBIDListIter in project elki by elki-project.
the class LoOP method computePDists.
/**
* Compute the probabilistic distances used by LoOP.
*
* @param relation Data relation
* @param knn kNN query
* @param pdists Storage for distances
*/
protected void computePDists(Relation<O> relation, KNNQuery<O> knn, WritableDoubleDataStore pdists) {
// computing PRDs
FiniteProgress prdsProgress = LOG.isVerbose() ? new FiniteProgress("pdists", relation.size(), LOG) : null;
for (DBIDIter iditer = relation.iterDBIDs(); iditer.valid(); iditer.advance()) {
// +
final KNNList neighbors = knn.getKNNForDBID(iditer, kreach + 1);
// query
// point
// use first kref neighbors as reference set
int ks = 0;
double ssum = 0.;
for (DoubleDBIDListIter neighbor = neighbors.iter(); neighbor.valid() && ks < kreach; neighbor.advance()) {
if (DBIDUtil.equal(neighbor, iditer)) {
continue;
}
final double d = neighbor.doubleValue();
ssum += d * d;
ks++;
}
double pdist = ks > 0 ? FastMath.sqrt(ssum / ks) : 0.;
pdists.putDouble(iditer, pdist);
LOG.incrementProcessed(prdsProgress);
}
LOG.ensureCompleted(prdsProgress);
}
use of de.lmu.ifi.dbs.elki.database.ids.DoubleDBIDListIter in project elki by elki-project.
the class KNNWeightOutlier method run.
/**
* Runs the algorithm in the timed evaluation part.
*
* @param database Database context
* @param relation Data relation
*/
public OutlierResult run(Database database, Relation<O> relation) {
final DistanceQuery<O> distanceQuery = database.getDistanceQuery(relation, getDistanceFunction());
// + query point
KNNQuery<O> knnQuery = database.getKNNQuery(distanceQuery, k + 1);
FiniteProgress prog = LOG.isVerbose() ? new FiniteProgress("Compute kNN weights", relation.size(), LOG) : null;
DoubleMinMax minmax = new DoubleMinMax();
WritableDoubleDataStore knnw_score = DataStoreUtil.makeDoubleStorage(relation.getDBIDs(), DataStoreFactory.HINT_STATIC);
for (DBIDIter iditer = relation.iterDBIDs(); iditer.valid(); iditer.advance()) {
// + query point
final KNNList knn = knnQuery.getKNNForDBID(iditer, k + 1);
// sum of the distances to the k nearest neighbors
double skn = 0;
// number of neighbors so far
int i = 0;
for (DoubleDBIDListIter neighbor = knn.iter(); i < k && neighbor.valid(); neighbor.advance()) {
if (DBIDUtil.equal(iditer, neighbor)) {
continue;
}
skn += neighbor.doubleValue();
++i;
}
if (i < k) {
// Less than k neighbors found
// Approximative index, or k > data set size!
skn = Double.POSITIVE_INFINITY;
}
knnw_score.putDouble(iditer, skn);
minmax.put(skn);
LOG.incrementProcessed(prog);
}
LOG.ensureCompleted(prog);
DoubleRelation res = new MaterializedDoubleRelation("kNN weight Outlier Score", "knnw-outlier", knnw_score, relation.getDBIDs());
OutlierScoreMeta meta = new BasicOutlierScoreMeta(minmax.getMin(), minmax.getMax(), 0., Double.POSITIVE_INFINITY, 0.);
return new OutlierResult(meta, res);
}
Aggregations