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

Example 46 with KNNList

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

the class MkCoPTree method insertAll.

@Override
public void insertAll(List<MkCoPEntry> entries) {
    if (entries.isEmpty()) {
        return;
    }
    if (LOG.isDebugging()) {
        LOG.debugFine("insert " + entries + "\n");
    }
    if (!initialized) {
        initialize(entries.get(0));
    }
    ModifiableDBIDs ids = DBIDUtil.newArray(entries.size());
    // insert
    for (MkCoPEntry entry : entries) {
        ids.add(entry.getRoutingObjectID());
        // insert the object
        super.insert(entry, false);
    }
    // perform nearest neighbor queries
    Map<DBID, KNNList> knnLists = batchNN(getRoot(), ids, settings.kmax);
    // adjust the knn distances
    adjustApproximatedKNNDistances(getRootEntry(), knnLists);
    if (EXTRA_INTEGRITY_CHECKS) {
        getRoot().integrityCheck(this, getRootEntry());
    }
}

Example 47 with KNNList

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

the class AbstractMkTree method batchNN.

/**
 * Performs a batch k-nearest neighbor query for a list of query objects.
 *
 * @param node the node representing the subtree on which the query should be
 *        performed
 * @param ids the ids of the query objects
 * @param kmax Maximum k value
 *
 * @deprecated Change to use by-object NN lookups instead.
 */
@Deprecated
protected final Map<DBID, KNNList> batchNN(N node, DBIDs ids, int kmax) {
    Map<DBID, KNNList> res = new HashMap<>(ids.size());
    for (DBIDIter iter = ids.iter(); iter.valid(); iter.advance()) {
        DBID id = DBIDUtil.deref(iter);
        res.put(id, knnq.getKNNForDBID(id, kmax));
    }
    return res;
}

Example 48 with KNNList

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

the class ValidateApproximativeKNNIndex method run.

/**
 * Run the algorithm.
 *
 * @param database Database
 * @param relation Relation
 * @return Null result
 */
public Result run(Database database, Relation<O> relation) {
    // Get a distance and kNN query instance.
    DistanceQuery<O> distQuery = database.getDistanceQuery(relation, getDistanceFunction());
    // Approximate query:
    KNNQuery<O> knnQuery = database.getKNNQuery(distQuery, k, DatabaseQuery.HINT_OPTIMIZED_ONLY);
    if (knnQuery == null || knnQuery instanceof LinearScanQuery) {
        throw new AbortException("Expected an accelerated query, but got a linear scan -- index is not used.");
    }
    // Exact query:
    KNNQuery<O> truekNNQuery;
    if (forcelinear) {
        truekNNQuery = QueryUtil.getLinearScanKNNQuery(distQuery);
    } else {
        truekNNQuery = database.getKNNQuery(distQuery, k, DatabaseQuery.HINT_EXACT);
    }
    if (knnQuery.getClass().equals(truekNNQuery.getClass())) {
        LOG.warning("Query classes are the same. This experiment may be invalid!");
    }
    // No query set - use original database.
    if (queries == null || pattern != null) {
        // Relation to filter on
        Relation<String> lrel = (pattern != null) ? DatabaseUtil.guessLabelRepresentation(database) : null;
        final DBIDs sample = DBIDUtil.randomSample(relation.getDBIDs(), sampling, random);
        FiniteProgress prog = LOG.isVeryVerbose() ? new FiniteProgress("kNN queries", sample.size(), LOG) : null;
        MeanVariance mv = new MeanVariance(), mvrec = new MeanVariance();
        MeanVariance mvdist = new MeanVariance(), mvdaerr = new MeanVariance(), mvdrerr = new MeanVariance();
        int misses = 0;
        for (DBIDIter iditer = sample.iter(); iditer.valid(); iditer.advance()) {
            if (pattern == null || pattern.matcher(lrel.get(iditer)).find()) {
                // Query index:
                KNNList knns = knnQuery.getKNNForDBID(iditer, k);
                // Query reference:
                KNNList trueknns = truekNNQuery.getKNNForDBID(iditer, k);
                // Put adjusted knn size:
                mv.put(knns.size() * k / (double) trueknns.size());
                // Put recall:
                mvrec.put(DBIDUtil.intersectionSize(knns, trueknns) / (double) trueknns.size());
                if (knns.size() >= k) {
                    double kdist = knns.getKNNDistance();
                    final double tdist = trueknns.getKNNDistance();
                    if (tdist > 0.0) {
                        mvdist.put(kdist);
                        mvdaerr.put(kdist - tdist);
                        mvdrerr.put(kdist / tdist);
                    }
                } else {
                    // Less than k objects.
                    misses++;
                }
            }
            LOG.incrementProcessed(prog);
        }
        LOG.ensureCompleted(prog);
        if (LOG.isStatistics()) {
            LOG.statistics("Mean number of results: " + mv.getMean() + " +- " + mv.getNaiveStddev());
            LOG.statistics("Recall of true results: " + mvrec.getMean() + " +- " + mvrec.getNaiveStddev());
            if (mvdist.getCount() > 0) {
                LOG.statistics("Mean k-distance: " + mvdist.getMean() + " +- " + mvdist.getNaiveStddev());
                LOG.statistics("Mean absolute k-error: " + mvdaerr.getMean() + " +- " + mvdaerr.getNaiveStddev());
                LOG.statistics("Mean relative k-error: " + mvdrerr.getMean() + " +- " + mvdrerr.getNaiveStddev());
            }
            if (misses > 0) {
                LOG.statistics(String.format("Number of queries that returned less than k=%d objects: %d (%.2f%%)", k, misses, misses * 100. / mv.getCount()));
            }
        }
    } else {
        // Separate query set.
        TypeInformation res = getDistanceFunction().getInputTypeRestriction();
        MultipleObjectsBundle bundle = queries.loadData();
        int col = -1;
        for (int i = 0; i < bundle.metaLength(); i++) {
            if (res.isAssignableFromType(bundle.meta(i))) {
                col = i;
                break;
            }
        }
        if (col < 0) {
            throw new AbortException("No compatible data type in query input was found. Expected: " + res.toString());
        }
        // Random sampling is a bit of hack, sorry.
        // But currently, we don't (yet) have an "integer random sample" function.
        DBIDRange sids = DBIDUtil.generateStaticDBIDRange(bundle.dataLength());
        final DBIDs sample = DBIDUtil.randomSample(sids, sampling, random);
        FiniteProgress prog = LOG.isVeryVerbose() ? new FiniteProgress("kNN queries", sample.size(), LOG) : null;
        MeanVariance mv = new MeanVariance(), mvrec = new MeanVariance();
        MeanVariance mvdist = new MeanVariance(), mvdaerr = new MeanVariance(), mvdrerr = new MeanVariance();
        int misses = 0;
        for (DBIDIter iditer = sample.iter(); iditer.valid(); iditer.advance()) {
            int off = sids.binarySearch(iditer);
            assert (off >= 0);
            @SuppressWarnings("unchecked") O o = (O) bundle.data(off, col);
            // Query index:
            KNNList knns = knnQuery.getKNNForObject(o, k);
            // Query reference:
            KNNList trueknns = truekNNQuery.getKNNForObject(o, k);
            // Put adjusted knn size:
            mv.put(knns.size() * k / (double) trueknns.size());
            // Put recall:
            mvrec.put(DBIDUtil.intersectionSize(knns, trueknns) / (double) trueknns.size());
            if (knns.size() >= k) {
                double kdist = knns.getKNNDistance();
                final double tdist = trueknns.getKNNDistance();
                if (tdist > 0.0) {
                    mvdist.put(kdist);
                    mvdaerr.put(kdist - tdist);
                    mvdrerr.put(kdist / tdist);
                }
            } else {
                // Less than k objects.
                misses++;
            }
            LOG.incrementProcessed(prog);
        }
        LOG.ensureCompleted(prog);
        if (LOG.isStatistics()) {
            LOG.statistics("Mean number of results: " + mv.getMean() + " +- " + mv.getNaiveStddev());
            LOG.statistics("Recall of true results: " + mvrec.getMean() + " +- " + mvrec.getNaiveStddev());
            if (mvdist.getCount() > 0) {
                LOG.statistics("Mean absolute k-error: " + mvdaerr.getMean() + " +- " + mvdaerr.getNaiveStddev());
                LOG.statistics("Mean relative k-error: " + mvdrerr.getMean() + " +- " + mvdrerr.getNaiveStddev());
            }
            if (misses > 0) {
                LOG.statistics(String.format("Number of queries that returned less than k=%d objects: %d (%.2f%%)", k, misses, misses * 100. / mv.getCount()));
            }
        }
    }
    return null;
}

Example 49 with KNNList

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

the class SimpleCOP method run.

public OutlierResult run(Database database, Relation<V> data) throws IllegalStateException {
    KNNQuery<V> knnQuery = QueryUtil.getKNNQuery(data, getDistanceFunction(), k + 1);
    DBIDs ids = data.getDBIDs();
    WritableDoubleDataStore cop_score = DataStoreUtil.makeDoubleStorage(ids, DataStoreFactory.HINT_HOT | DataStoreFactory.HINT_STATIC);
    WritableDataStore<double[]> cop_err_v = DataStoreUtil.makeStorage(ids, DataStoreFactory.HINT_HOT | DataStoreFactory.HINT_STATIC, double[].class);
    WritableDataStore<double[][]> cop_datav = DataStoreUtil.makeStorage(ids, DataStoreFactory.HINT_HOT | DataStoreFactory.HINT_STATIC, double[][].class);
    WritableIntegerDataStore cop_dim = DataStoreUtil.makeIntegerStorage(ids, DataStoreFactory.HINT_HOT | DataStoreFactory.HINT_STATIC, -1);
    WritableDataStore<CorrelationAnalysisSolution<?>> cop_sol = DataStoreUtil.makeStorage(ids, DataStoreFactory.HINT_HOT | DataStoreFactory.HINT_STATIC, CorrelationAnalysisSolution.class);
    {
        // compute neighbors of each db object
        FiniteProgress progressLocalPCA = LOG.isVerbose() ? new FiniteProgress("Correlation Outlier Probabilities", data.size(), LOG) : null;
        double sqrt2 = MathUtil.SQRT2;
        for (DBIDIter id = data.iterDBIDs(); id.valid(); id.advance()) {
            KNNList neighbors = knnQuery.getKNNForDBID(id, k + 1);
            ModifiableDBIDs nids = DBIDUtil.newArray(neighbors);
            nids.remove(id);
            // TODO: do we want to use the query point as centroid?
            CorrelationAnalysisSolution<V> depsol = dependencyDerivator.generateModel(data, nids);
            double stddev = depsol.getStandardDeviation();
            double distance = depsol.distance(data.get(id));
            double prob = NormalDistribution.erf(distance / (stddev * sqrt2));
            cop_score.putDouble(id, prob);
            cop_err_v.put(id, times(depsol.errorVector(data.get(id)), -1));
            double[][] datav = depsol.dataProjections(data.get(id));
            cop_datav.put(id, datav);
            cop_dim.putInt(id, depsol.getCorrelationDimensionality());
            cop_sol.put(id, depsol);
            LOG.incrementProcessed(progressLocalPCA);
        }
        LOG.ensureCompleted(progressLocalPCA);
    }
    // combine results.
    DoubleRelation scoreResult = new MaterializedDoubleRelation("Original Correlation Outlier Probabilities", "origcop-outlier", cop_score, ids);
    OutlierScoreMeta scoreMeta = new ProbabilisticOutlierScore();
    OutlierResult result = new OutlierResult(scoreMeta, scoreResult);
    // extra results
    result.addChildResult(new MaterializedRelation<>("Local Dimensionality", COP.COP_DIM, TypeUtil.INTEGER, cop_dim, ids));
    result.addChildResult(new MaterializedRelation<>("Error vectors", COP.COP_ERRORVEC, TypeUtil.DOUBLE_ARRAY, cop_err_v, ids));
    result.addChildResult(new MaterializedRelation<>("Data vectors", "cop-datavec", TypeUtil.MATRIX, cop_datav, ids));
    result.addChildResult(new MaterializedRelation<>("Correlation analysis", "cop-sol", new SimpleTypeInformation<CorrelationAnalysisSolution<?>>(CorrelationAnalysisSolution.class), cop_sol, ids));
    return result;
}

Example 50 with KNNList

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

the class OPTICSOF method run.

/**
 * Perform OPTICS-based outlier detection.
 *
 * @param database Database
 * @param relation Relation
 * @return Outlier detection result
 */
public OutlierResult run(Database database, Relation<O> relation) {
    DistanceQuery<O> distQuery = database.getDistanceQuery(relation, getDistanceFunction());
    KNNQuery<O> knnQuery = database.getKNNQuery(distQuery, minpts);
    RangeQuery<O> rangeQuery = database.getRangeQuery(distQuery);
    DBIDs ids = relation.getDBIDs();
    // FIXME: implicit preprocessor.
    WritableDataStore<KNNList> nMinPts = DataStoreUtil.makeStorage(ids, DataStoreFactory.HINT_HOT | DataStoreFactory.HINT_TEMP, KNNList.class);
    WritableDoubleDataStore coreDistance = DataStoreUtil.makeDoubleStorage(ids, DataStoreFactory.HINT_HOT | DataStoreFactory.HINT_TEMP);
    WritableIntegerDataStore minPtsNeighborhoodSize = DataStoreUtil.makeIntegerStorage(ids, DataStoreFactory.HINT_HOT | DataStoreFactory.HINT_TEMP, -1);
    for (DBIDIter iditer = relation.iterDBIDs(); iditer.valid(); iditer.advance()) {
        KNNList minptsNeighbours = knnQuery.getKNNForDBID(iditer, minpts);
        double d = minptsNeighbours.getKNNDistance();
        nMinPts.put(iditer, minptsNeighbours);
        coreDistance.putDouble(iditer, d);
        minPtsNeighborhoodSize.put(iditer, rangeQuery.getRangeForDBID(iditer, d).size());
    }
    // Pass 2
    WritableDataStore<List<Double>> reachDistance = DataStoreUtil.makeStorage(ids, DataStoreFactory.HINT_HOT | DataStoreFactory.HINT_TEMP, List.class);
    WritableDoubleDataStore lrds = DataStoreUtil.makeDoubleStorage(ids, DataStoreFactory.HINT_HOT | DataStoreFactory.HINT_TEMP);
    for (DBIDIter iditer = relation.iterDBIDs(); iditer.valid(); iditer.advance()) {
        List<Double> core = new ArrayList<>();
        double lrd = 0;
        // TODO: optimize for double distances
        for (DoubleDBIDListIter neighbor = nMinPts.get(iditer).iter(); neighbor.valid(); neighbor.advance()) {
            double coreDist = coreDistance.doubleValue(neighbor);
            double dist = distQuery.distance(iditer, neighbor);
            double rd = MathUtil.max(coreDist, dist);
            lrd = rd + lrd;
            core.add(rd);
        }
        lrd = minPtsNeighborhoodSize.intValue(iditer) / lrd;
        reachDistance.put(iditer, core);
        lrds.putDouble(iditer, lrd);
    }
    // Pass 3
    DoubleMinMax ofminmax = new DoubleMinMax();
    WritableDoubleDataStore ofs = DataStoreUtil.makeDoubleStorage(ids, DataStoreFactory.HINT_STATIC);
    for (DBIDIter iditer = relation.iterDBIDs(); iditer.valid(); iditer.advance()) {
        double of = 0;
        for (DBIDIter neighbor = nMinPts.get(iditer).iter(); neighbor.valid(); neighbor.advance()) {
            double lrd = lrds.doubleValue(iditer);
            double lrdN = lrds.doubleValue(neighbor);
            of = of + lrdN / lrd;
        }
        of = of / minPtsNeighborhoodSize.intValue(iditer);
        ofs.putDouble(iditer, of);
        // update minimum and maximum
        ofminmax.put(of);
    }
    // Build result representation.
    DoubleRelation scoreResult = new MaterializedDoubleRelation("OPTICS Outlier Scores", "optics-outlier", ofs, relation.getDBIDs());
    OutlierScoreMeta scoreMeta = new QuotientOutlierScoreMeta(ofminmax.getMin(), ofminmax.getMax(), 0.0, Double.POSITIVE_INFINITY, 1.0);
    return new OutlierResult(scoreMeta, scoreResult);
}