Examples with Cluster de.lmu.ifi.dbs.elki.data.Cluster used on opensource projects

Example 26 with Cluster

use of de.lmu.ifi.dbs.elki.data.Cluster in project elki by elki-project.

the class EvaluateRankingQuality method run.

@Override
public HistogramResult run(Database database) {
    final Relation<V> relation = database.getRelation(getInputTypeRestriction()[0]);
    final DistanceQuery<V> distQuery = database.getDistanceQuery(relation, getDistanceFunction());
    final KNNQuery<V> knnQuery = database.getKNNQuery(distQuery, relation.size());
    if (LOG.isVerbose()) {
        LOG.verbose("Preprocessing clusters...");
    }
    // Cluster by labels
    Collection<Cluster<Model>> split = (new ByLabelOrAllInOneClustering()).run(database).getAllClusters();
    // Compute cluster averages and covariance matrix
    HashMap<Cluster<?>, double[]> averages = new HashMap<>(split.size());
    HashMap<Cluster<?>, double[][]> covmats = new HashMap<>(split.size());
    for (Cluster<?> clus : split) {
        CovarianceMatrix covmat = CovarianceMatrix.make(relation, clus.getIDs());
        averages.put(clus, covmat.getMeanVector());
        covmats.put(clus, covmat.destroyToPopulationMatrix());
    }
    MeanVarianceStaticHistogram hist = new MeanVarianceStaticHistogram(numbins, 0.0, 1.0);
    if (LOG.isVerbose()) {
        LOG.verbose("Processing points...");
    }
    FiniteProgress rocloop = LOG.isVerbose() ? new FiniteProgress("Computing ROC AUC values", relation.size(), LOG) : null;
    ROCEvaluation roc = new ROCEvaluation();
    // sort neighbors
    for (Cluster<?> clus : split) {
        ModifiableDoubleDBIDList cmem = DBIDUtil.newDistanceDBIDList(clus.size());
        double[] av = averages.get(clus);
        double[][] covm = covmats.get(clus);
        for (DBIDIter iter = clus.getIDs().iter(); iter.valid(); iter.advance()) {
            double d = mahalanobisDistance(covm, relation.get(iter).toArray(), av);
            cmem.add(d, iter);
        }
        cmem.sort();
        for (DBIDArrayIter it = cmem.iter(); it.valid(); it.advance()) {
            KNNList knn = knnQuery.getKNNForDBID(it, relation.size());
            double result = EvaluateClustering.evaluateRanking(roc, clus, knn);
            hist.put(((double) it.getOffset()) / clus.size(), result);
            LOG.incrementProcessed(rocloop);
        }
    }
    LOG.ensureCompleted(rocloop);
    // Collections.sort(results);
    // Transform Histogram into a Double Vector array.
    Collection<double[]> res = new ArrayList<>(relation.size());
    for (ObjHistogram.Iter<MeanVariance> iter = hist.iter(); iter.valid(); iter.advance()) {
        res.add(new double[] { iter.getCenter(), iter.getValue().getCount(), iter.getValue().getMean(), iter.getValue().getSampleVariance() });
    }
    return new HistogramResult("Ranking Quality Histogram", "ranking-histogram", res);
}

Example 27 with Cluster

use of de.lmu.ifi.dbs.elki.data.Cluster in project elki by elki-project.

the class NaiveAgglomerativeHierarchicalClustering1 method run.

/**
 * Run the algorithm
 *
 * @param db Database
 * @param relation Relation
 * @return Clustering hierarchy
 */
public Result run(Database db, Relation<O> relation) {
    DistanceQuery<O> dq = db.getDistanceQuery(relation, getDistanceFunction());
    ArrayDBIDs ids = DBIDUtil.ensureArray(relation.getDBIDs());
    final int size = ids.size();
    LOG.verbose("Notice: SLINK is a much faster algorithm for single-linkage clustering!");
    // Compute the initial distance matrix.
    double[][] matrix = new double[size][size];
    DBIDArrayIter ix = ids.iter(), iy = ids.iter();
    for (int x = 0; ix.valid(); x++, ix.advance()) {
        iy.seek(0);
        for (int y = 0; y < x; y++, iy.advance()) {
            final double dist = dq.distance(ix, iy);
            matrix[x][y] = dist;
            matrix[y][x] = dist;
        }
    }
    // Initialize space for result:
    double[] height = new double[size];
    Arrays.fill(height, Double.POSITIVE_INFINITY);
    // Parent node, to track merges
    // have every object point to itself initially
    ArrayModifiableDBIDs parent = DBIDUtil.newArray(ids);
    // Active clusters, when not trivial.
    Int2ReferenceMap<ModifiableDBIDs> clusters = new Int2ReferenceOpenHashMap<>();
    // Repeat until everything merged, except the desired number of clusters:
    final int stop = size - numclusters;
    FiniteProgress prog = LOG.isVerbose() ? new FiniteProgress("Agglomerative clustering", stop, LOG) : null;
    for (int i = 0; i < stop; i++) {
        double min = Double.POSITIVE_INFINITY;
        int minx = -1, miny = -1;
        for (int x = 0; x < size; x++) {
            if (height[x] < Double.POSITIVE_INFINITY) {
                continue;
            }
            for (int y = 0; y < x; y++) {
                if (height[y] < Double.POSITIVE_INFINITY) {
                    continue;
                }
                if (matrix[x][y] < min) {
                    min = matrix[x][y];
                    minx = x;
                    miny = y;
                }
            }
        }
        assert (minx >= 0 && miny >= 0);
        // Avoid allocating memory, by reusing existing iterators:
        ix.seek(minx);
        iy.seek(miny);
        // Perform merge in data structure: x -> y
        // Since y < x, prefer keeping y, dropping x.
        height[minx] = min;
        parent.set(minx, iy);
        // Merge into cluster
        ModifiableDBIDs cx = clusters.get(minx);
        ModifiableDBIDs cy = clusters.get(miny);
        if (cy == null) {
            cy = DBIDUtil.newHashSet();
            cy.add(iy);
        }
        if (cx == null) {
            cy.add(ix);
        } else {
            cy.addDBIDs(cx);
            clusters.remove(minx);
        }
        clusters.put(miny, cy);
        // Update distance matrix for y:
        for (int j = 0; j < size; j++) {
            matrix[j][miny] = Math.min(matrix[j][minx], matrix[j][miny]);
            matrix[miny][j] = Math.min(matrix[minx][j], matrix[miny][j]);
        }
        LOG.incrementProcessed(prog);
    }
    LOG.ensureCompleted(prog);
    // Build the clustering result
    final Clustering<Model> dendrogram = new Clustering<>("Hierarchical-Clustering", "hierarchical-clustering");
    for (int x = 0; x < size; x++) {
        if (height[x] < Double.POSITIVE_INFINITY) {
            DBIDs cids = clusters.get(x);
            if (cids == null) {
                ix.seek(x);
                cids = DBIDUtil.deref(ix);
            }
            Cluster<Model> cluster = new Cluster<>("Cluster", cids);
            dendrogram.addToplevelCluster(cluster);
        }
    }
    return dendrogram;
}

Example 28 with Cluster

use of de.lmu.ifi.dbs.elki.data.Cluster in project elki by elki-project.

the class NaiveMeanShiftClustering method run.

/**
 * Run the mean-shift clustering algorithm.
 *
 * @param database Database
 * @param relation Data relation
 * @return Clustering result
 */
public Clustering<MeanModel> run(Database database, Relation<V> relation) {
    final DistanceQuery<V> distq = database.getDistanceQuery(relation, getDistanceFunction());
    final RangeQuery<V> rangeq = database.getRangeQuery(distq);
    final NumberVector.Factory<V> factory = RelationUtil.getNumberVectorFactory(relation);
    final int dim = RelationUtil.dimensionality(relation);
    // Stopping threshold
    final double threshold = bandwidth * 1E-10;
    // Result store:
    ArrayList<Pair<V, ModifiableDBIDs>> clusters = new ArrayList<>();
    ModifiableDBIDs noise = DBIDUtil.newArray();
    FiniteProgress prog = LOG.isVerbose() ? new FiniteProgress("Mean-shift clustering", relation.size(), LOG) : null;
    for (DBIDIter iter = relation.iterDBIDs(); iter.valid(); iter.advance()) {
        // Initial position:
        V position = relation.get(iter);
        iterations: for (int j = 1; j <= MAXITER; j++) {
            // Compute new position:
            V newvec = null;
            {
                DoubleDBIDList neigh = rangeq.getRangeForObject(position, bandwidth);
                boolean okay = (neigh.size() > 1) || (neigh.size() >= 1 && j > 1);
                if (okay) {
                    Centroid newpos = new Centroid(dim);
                    for (DoubleDBIDListIter niter = neigh.iter(); niter.valid(); niter.advance()) {
                        final double weight = kernel.density(niter.doubleValue() / bandwidth);
                        newpos.put(relation.get(niter), weight);
                    }
                    newvec = factory.newNumberVector(newpos.getArrayRef());
                // TODO: detect 0 weight!
                }
                if (!okay) {
                    noise.add(iter);
                    break iterations;
                }
            }
            // Test if we are close to one of the known clusters:
            double bestd = Double.POSITIVE_INFINITY;
            Pair<V, ModifiableDBIDs> bestp = null;
            for (Pair<V, ModifiableDBIDs> pair : clusters) {
                final double merged = distq.distance(newvec, pair.first);
                if (merged < bestd) {
                    bestd = merged;
                    bestp = pair;
                }
            }
            // Check for convergence:
            double delta = distq.distance(position, newvec);
            if (bestd < 10 * threshold || bestd * 2 < delta) {
                bestp.second.add(iter);
                break iterations;
            }
            if (j == MAXITER) {
                LOG.warning("No convergence after " + MAXITER + " iterations. Distance: " + delta);
            }
            if (Double.isNaN(delta)) {
                LOG.warning("Encountered NaN distance. Invalid center vector? " + newvec.toString());
                break iterations;
            }
            if (j == MAXITER || delta < threshold) {
                if (LOG.isDebuggingFine()) {
                    LOG.debugFine("New cluster:" + newvec + " delta: " + delta + " threshold: " + threshold + " bestd: " + bestd);
                }
                ArrayModifiableDBIDs cids = DBIDUtil.newArray();
                cids.add(iter);
                clusters.add(new Pair<V, ModifiableDBIDs>(newvec, cids));
                break iterations;
            }
            position = newvec;
        }
        LOG.incrementProcessed(prog);
    }
    LOG.ensureCompleted(prog);
    ArrayList<Cluster<MeanModel>> cs = new ArrayList<>(clusters.size());
    for (Pair<V, ModifiableDBIDs> pair : clusters) {
        cs.add(new Cluster<>(pair.second, new MeanModel(pair.first.toArray())));
    }
    if (noise.size() > 0) {
        cs.add(new Cluster<MeanModel>(noise, true));
    }
    Clustering<MeanModel> c = new Clustering<>("Mean-shift Clustering", "mean-shift-clustering", cs);
    return c;
}

Example 29 with Cluster

use of de.lmu.ifi.dbs.elki.data.Cluster in project elki by elki-project.

the class COPAC method run.

/**
 * Run the COPAC algorithm.
 *
 * @param database Database
 * @param relation Vector field relation
 * @return COPAC clustering
 */
public Clustering<DimensionModel> run(Database database, Relation<V> relation) {
    COPACNeighborPredicate.Instance npred = new COPACNeighborPredicate<V>(settings).instantiate(database, relation);
    CorePredicate.Instance<DBIDs> cpred = new MinPtsCorePredicate(settings.minpts).instantiate(database);
    Clustering<Model> dclusters = new GeneralizedDBSCAN.Instance<>(npred, cpred, false).run();
    // Re-wrap the detected clusters for COPAC:
    Clustering<DimensionModel> result = new Clustering<>("COPAC clustering", "copac-clustering");
    // Generalized DBSCAN clusterings will be flat.
    for (It<Cluster<Model>> iter = dclusters.iterToplevelClusters(); iter.valid(); iter.advance()) {
        Cluster<Model> clus = iter.get();
        if (clus.size() > 0) {
            int dim = npred.dimensionality(clus.getIDs().iter());
            DimensionModel model = new DimensionModel(dim);
            result.addToplevelCluster(new Cluster<>(clus.getIDs(), model));
        }
    }
    return result;
}

Example 30 with Cluster

use of de.lmu.ifi.dbs.elki.data.Cluster in project elki by elki-project.

the class OPTICSXi method extractClusters.

/**
 * Extract clusters from a cluster order result.
 *
 * @param clusterOrderResult cluster order result
 * @param relation Relation
 * @param ixi Parameter 1 - Xi
 * @param minpts Parameter minPts
 */
private Clustering<OPTICSModel> extractClusters(ClusterOrder clusterOrderResult, Relation<?> relation, double ixi, int minpts) {
    ArrayDBIDs clusterOrder = clusterOrderResult.ids;
    DoubleDataStore reach = clusterOrderResult.reachability;
    DBIDArrayIter tmp = clusterOrder.iter();
    DBIDVar tmp2 = DBIDUtil.newVar();
    double mib = 0.0;
    List<SteepArea> salist = keepsteep ? new ArrayList<SteepArea>() : null;
    List<SteepDownArea> sdaset = new ArrayList<>();
    final Clustering<OPTICSModel> clustering = new Clustering<>("OPTICS Xi-Clusters", "optics");
    HashSet<Cluster<OPTICSModel>> curclusters = new HashSet<>();
    HashSetModifiableDBIDs unclaimedids = DBIDUtil.newHashSet(relation.getDBIDs());
    FiniteProgress scanprog = LOG.isVerbose() ? new FiniteProgress("OPTICS Xi cluster extraction", clusterOrder.size(), LOG) : null;
    for (SteepScanPosition scan = new SteepScanPosition(clusterOrderResult); scan.hasNext(); ) {
        if (scanprog != null) {
            scanprog.setProcessed(scan.index, LOG);
        }
        // Update maximum-inbetween
        mib = MathUtil.max(mib, scan.getReachability());
        // The last point cannot be the start of a steep area.
        if (!scan.next.valid()) {
            break;
        }
        // Xi-steep down area
        if (scan.steepDown(ixi)) {
            // Update mib values with current mib and filter
            updateFilterSDASet(mib, sdaset, ixi);
            final double startval = scan.getReachability();
            mib = 0.;
            int startsteep = scan.index, endsteep = scan.index;
            for (scan.next(); scan.hasNext(); scan.next()) {
                // still steep - continue.
                if (scan.steepDown(ixi)) {
                    endsteep = scan.index;
                    continue;
                }
                // Always stop looking after minpts "flat" steps.
                if (!scan.steepDown(1.0) || scan.index - endsteep > minpts) {
                    break;
                }
            }
            final SteepDownArea sda = new SteepDownArea(startsteep, endsteep, startval, 0);
            if (LOG.isDebuggingFinest()) {
                LOG.debugFinest("New steep down area: " + sda.toString());
            }
            sdaset.add(sda);
            if (salist != null) {
                salist.add(sda);
            }
            continue;
        }
        // Xi-steep up area
        if (scan.steepUp(ixi)) {
            // Update mib values with current mib and filter
            updateFilterSDASet(mib, sdaset, ixi);
            final SteepUpArea sua;
            // Compute steep-up area
            {
                int startsteep = scan.index, endsteep = scan.index;
                mib = scan.getReachability();
                double esuccr = scan.getNextReachability();
                // Find end of steep-up-area, eventually updating mib again
                while (!Double.isInfinite(esuccr) && scan.hasNext()) {
                    scan.next();
                    // still steep - continue.
                    if (scan.steepUp(ixi)) {
                        endsteep = scan.index;
                        mib = scan.getReachability();
                        esuccr = scan.getNextReachability();
                        continue;
                    }
                    // Stop looking after minpts non-up steps.
                    if (!scan.steepUp(1.0) || scan.index - endsteep > minpts) {
                        break;
                    }
                }
                if (Double.isInfinite(esuccr)) {
                    scan.next();
                }
                sua = new SteepUpArea(startsteep, endsteep, esuccr);
                if (LOG.isDebuggingFinest()) {
                    LOG.debugFinest("New steep up area: " + sua.toString());
                }
                if (salist != null) {
                    salist.add(sua);
                }
            }
            // Validate and computer clusters
            // LOG.debug("SDA size:"+sdaset.size()+" "+sdaset);
            ListIterator<SteepDownArea> sdaiter = sdaset.listIterator(sdaset.size());
            // Iterate backwards for correct hierarchy generation.
            while (sdaiter.hasPrevious()) {
                SteepDownArea sda = sdaiter.previous();
                if (LOG.isDebuggingFinest()) {
                    LOG.debugFinest("Comparing: eU=" + mib + " SDA: " + sda.toString());
                }
                // Condition 3b: end-of-steep-up > maximum-in-between lower
                if (mib * ixi < sda.getMib()) {
                    if (LOG.isDebuggingFinest()) {
                        LOG.debugFinest("mib * ixi = " + mib * ixi + " >= sda.getMib() = " + sda.getMib());
                    }
                    continue;
                }
                // By default, clusters cover both the steep up and steep down area
                int cstart = sda.getStartIndex(), cend = MathUtil.min(sua.getEndIndex(), clusterOrder.size() - 1);
                // However, we sometimes have to adjust this (Condition 4):
                {
                    // Case b)
                    if (sda.getMaximum() * ixi >= sua.getMaximum()) {
                        while (// 
                        cstart < cend && reach.doubleValue(tmp.seek(cstart + 1)) > sua.getMaximum()) {
                            cstart++;
                        }
                    } else // Case c)
                    if (sua.getMaximum() * ixi >= sda.getMaximum()) {
                        while (// 
                        cend > cstart && reach.doubleValue(tmp.seek(cend - 1)) > sda.getMaximum()) {
                            cend--;
                        }
                    }
                // Case a) is the default
                }
                // removes common artifacts from the Xi method
                if (!nocorrect) {
                    simplify: while (cend > cstart) {
                        clusterOrderResult.predecessor.assignVar(tmp.seek(cend), tmp2);
                        for (int i = cstart; i < cend; i++) {
                            if (DBIDUtil.equal(tmp2, tmp.seek(i))) {
                                break simplify;
                            }
                        }
                        // Not found.
                        --cend;
                    }
                }
                // Condition 3a: obey minpts
                if (cend - cstart + 1 < minpts) {
                    if (LOG.isDebuggingFinest()) {
                        LOG.debugFinest("MinPts not satisfied.");
                    }
                    continue;
                }
                // Build the cluster
                ModifiableDBIDs dbids = DBIDUtil.newArray();
                for (int idx = cstart; idx <= cend; idx++) {
                    tmp.seek(idx);
                    // Collect only unclaimed IDs.
                    if (unclaimedids.remove(tmp)) {
                        dbids.add(tmp);
                    }
                }
                if (LOG.isDebuggingFine()) {
                    LOG.debugFine("Found cluster with " + dbids.size() + " new objects, length " + (cend - cstart + 1));
                }
                OPTICSModel model = new OPTICSModel(cstart, cend);
                Cluster<OPTICSModel> cluster = new Cluster<>("Cluster_" + cstart + "_" + cend, dbids, model);
                // Build the hierarchy
                {
                    Iterator<Cluster<OPTICSModel>> iter = curclusters.iterator();
                    while (iter.hasNext()) {
                        Cluster<OPTICSModel> clus = iter.next();
                        OPTICSModel omodel = clus.getModel();
                        if (model.getStartIndex() <= omodel.getStartIndex() && omodel.getEndIndex() <= model.getEndIndex()) {
                            clustering.addChildCluster(cluster, clus);
                            iter.remove();
                        }
                    }
                }
                curclusters.add(cluster);
            }
            continue;
        }
        // Flat - advance anyway.
        scan.next();
    }
    if (scanprog != null) {
        scanprog.setProcessed(clusterOrder.size(), LOG);
    }
    if (!unclaimedids.isEmpty()) {
        boolean noise = reach.doubleValue(tmp.seek(clusterOrder.size() - 1)) >= Double.POSITIVE_INFINITY;
        Cluster<OPTICSModel> allcluster = new Cluster<>(noise ? "Noise" : "Cluster", unclaimedids, noise, new OPTICSModel(0, clusterOrder.size() - 1));
        for (Cluster<OPTICSModel> cluster : curclusters) {
            clustering.addChildCluster(allcluster, cluster);
        }
        clustering.addToplevelCluster(allcluster);
    } else {
        for (Cluster<OPTICSModel> cluster : curclusters) {
            clustering.addToplevelCluster(cluster);
        }
    }
    clustering.addChildResult(clusterOrderResult);
    if (salist != null) {
        clusterOrderResult.addChildResult(new SteepAreaResult(salist));
    }
    return clustering;
}