Examples with KNNList de.lmu.ifi.dbs.elki.database.ids.KNNList used on opensource projects

Example 11 with KNNList

use of de.lmu.ifi.dbs.elki.database.ids.KNNList 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;
}

Example 12 with KNNList

use of de.lmu.ifi.dbs.elki.database.ids.KNNList in project elki by elki-project.

the class AbstractMkTreeUnified method insertAll.

@Override
public void insertAll(List<E> entries) {
    if (entries.isEmpty()) {
        return;
    }
    if (!initialized) {
        initialize(entries.get(0));
    }
    ModifiableDBIDs ids = DBIDUtil.newArray(entries.size());
    // insert sequentially
    for (E entry : entries) {
        ids.add(entry.getRoutingObjectID());
        // insert the object
        super.insert(entry, false);
    }
    // do batch nn
    Map<DBID, KNNList> knnLists = batchNN(getRoot(), ids, settings.kmax);
    // adjust the knn distances
    kNNdistanceAdjustment(getRootEntry(), knnLists);
    if (EXTRA_INTEGRITY_CHECKS) {
        getRoot().integrityCheck(this, getRootEntry());
    }
}

Example 13 with KNNList

use of de.lmu.ifi.dbs.elki.database.ids.KNNList in project elki by elki-project.

the class COF method computeCOFScores.

/**
 * Compute Connectivity outlier factors.
 *
 * @param knnq KNN query
 * @param ids IDs to process
 * @param acds Average chaining distances
 * @param cofs Connectivity outlier factor storage
 * @param cofminmax Score minimum/maximum tracker
 */
private void computeCOFScores(KNNQuery<O> knnq, DBIDs ids, DoubleDataStore acds, WritableDoubleDataStore cofs, DoubleMinMax cofminmax) {
    FiniteProgress progressCOFs = LOG.isVerbose() ? new FiniteProgress("COF for objects", ids.size(), LOG) : null;
    for (DBIDIter iter = ids.iter(); iter.valid(); iter.advance()) {
        final KNNList neighbors = knnq.getKNNForDBID(iter, k);
        // Aggregate the average chaining distances of all neighbors:
        double sum = 0.;
        for (DBIDIter neighbor = neighbors.iter(); neighbor.valid(); neighbor.advance()) {
            // skip the point itself
            if (DBIDUtil.equal(neighbor, iter)) {
                continue;
            }
            sum += acds.doubleValue(neighbor);
        }
        final double cof = (sum > 0.) ? (acds.doubleValue(iter) * k / sum) : (acds.doubleValue(iter) > 0. ? Double.POSITIVE_INFINITY : 1.);
        cofs.putDouble(iter, cof);
        // update minimum and maximum
        cofminmax.put(cof);
        LOG.incrementProcessed(progressCOFs);
    }
    LOG.ensureCompleted(progressCOFs);
}

Example 14 with KNNList

use of de.lmu.ifi.dbs.elki.database.ids.KNNList 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;
}

Example 15 with KNNList

use of de.lmu.ifi.dbs.elki.database.ids.KNNList 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);
}