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

Example 11 with Cluster

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

the class CanopyPreClustering method run.

/**
 * Run the algorithm
 *
 * @param database Database
 * @param relation Relation to process
 */
public Clustering<PrototypeModel<O>> run(Database database, Relation<O> relation) {
    if (!(t1 >= t2)) {
        throw new AbortException("T1 must be at least as large as T2.");
    }
    DistanceQuery<O> dq = database.getDistanceQuery(relation, getDistanceFunction());
    ModifiableDBIDs ids = DBIDUtil.newHashSet(relation.getDBIDs());
    ArrayList<Cluster<PrototypeModel<O>>> clusters = new ArrayList<>();
    final int size = relation.size();
    FiniteProgress prog = LOG.isVerbose() ? new FiniteProgress("Canopy clustering", size, LOG) : null;
    DBIDVar first = DBIDUtil.newVar();
    while (!ids.isEmpty()) {
        // Remove first element:
        ids.pop(first);
        // Start a new cluster:
        ModifiableDBIDs cids = DBIDUtil.newArray();
        cids.add(first);
        // Compare to remaining objects:
        for (DBIDMIter iter = ids.iter(); iter.valid(); iter.advance()) {
            double dist = dq.distance(first, iter);
            // Inclusion threshold:
            if (dist > t1) {
                continue;
            }
            cids.add(iter);
            // Removal threshold:
            if (dist <= t2) {
                iter.remove();
            }
        }
        // TODO: remember the central object using a CanopyModel?
        // Construct cluster:
        clusters.add(new Cluster<>(cids, new SimplePrototypeModel<>(relation.get(first))));
        if (prog != null) {
            prog.setProcessed(size - ids.size(), LOG);
        }
    }
    LOG.ensureCompleted(prog);
    return new Clustering<>("Canopy clustering", "canopy-clustering", clusters);
}

Example 12 with Cluster

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

the class NaiveAgglomerativeHierarchicalClustering3 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();
    if (size > 0x10000) {
        throw new AbortException("This implementation does not scale to data sets larger than " + 0x10000 + " instances (~17 GB RAM), which results in an integer overflow.");
    }
    if (Linkage.SINGLE.equals(linkage)) {
        LOG.verbose("Notice: SLINK is a much faster algorithm for single-linkage clustering!");
    }
    // Compute the initial (lower triangular) distance matrix.
    double[] scratch = new double[triangleSize(size)];
    DBIDArrayIter ix = ids.iter(), iy = ids.iter();
    // Position counter - must agree with computeOffset!
    int pos = 0;
    boolean square = Linkage.WARD.equals(linkage) && !getDistanceFunction().isSquared();
    for (int x = 0; ix.valid(); x++, ix.advance()) {
        iy.seek(0);
        for (int y = 0; y < x; y++, iy.advance()) {
            scratch[pos] = dq.distance(ix, iy);
            // Ward uses variances -- i.e. squared values
            if (square) {
                scratch[pos] *= scratch[pos];
            }
            pos++;
        }
    }
    // 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;
            }
            final int xbase = triangleSize(x);
            for (int y = 0; y < x; y++) {
                if (height[y] < Double.POSITIVE_INFINITY) {
                    continue;
                }
                final int idx = xbase + y;
                if (scratch[idx] < min) {
                    min = scratch[idx];
                    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);
        // cluster sizes, for averaging
        int sizex = 1, sizey = 1;
        if (cy == null) {
            cy = DBIDUtil.newHashSet();
            cy.add(iy);
        } else {
            sizey = cy.size();
        }
        if (cx == null) {
            cy.add(ix);
        } else {
            sizex = cx.size();
            cy.addDBIDs(cx);
            clusters.remove(minx);
        }
        clusters.put(miny, cy);
        // Update distance matrix. Note: miny < minx
        // Implementation note: most will not need sizej, and could save the
        // hashmap lookup.
        final int xbase = triangleSize(minx), ybase = triangleSize(miny);
        // Write to (y, j), with j < y
        for (int j = 0; j < miny; j++) {
            if (height[j] < Double.POSITIVE_INFINITY) {
                continue;
            }
            final DBIDs idsj = clusters.get(j);
            final int sizej = (idsj == null) ? 1 : idsj.size();
            scratch[ybase + j] = linkage.combine(sizex, scratch[xbase + j], sizey, scratch[ybase + j], sizej, min);
        }
        // Write to (j, y), with y < j < x
        for (int j = miny + 1; j < minx; j++) {
            if (height[j] < Double.POSITIVE_INFINITY) {
                continue;
            }
            final int jbase = triangleSize(j);
            final DBIDs idsj = clusters.get(j);
            final int sizej = (idsj == null) ? 1 : idsj.size();
            scratch[jbase + miny] = linkage.combine(sizex, scratch[xbase + j], sizey, scratch[jbase + miny], sizej, min);
        }
        // Write to (j, y), with y < x < j
        for (int j = minx + 1; j < size; j++) {
            if (height[j] < Double.POSITIVE_INFINITY) {
                continue;
            }
            final DBIDs idsj = clusters.get(j);
            final int sizej = (idsj == null) ? 1 : idsj.size();
            final int jbase = triangleSize(j);
            scratch[jbase + miny] = linkage.combine(sizex, scratch[jbase + minx], sizey, scratch[jbase + miny], sizej, min);
        }
        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 13 with Cluster

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

the class ByModelClustering method run.

/**
 * Run the actual clustering algorithm.
 *
 * @param relation The data input we use
 */
public Clustering<Model> run(Relation<Model> relation) {
    // Build model mapping
    HashMap<Model, ModifiableDBIDs> modelMap = new HashMap<>();
    for (DBIDIter iditer = relation.iterDBIDs(); iditer.valid(); iditer.advance()) {
        Model model = relation.get(iditer);
        ModifiableDBIDs modelids = modelMap.get(model);
        if (modelids == null) {
            modelids = DBIDUtil.newHashSet();
            modelMap.put(model, modelids);
        }
        modelids.add(iditer);
    }
    Clustering<Model> result = new Clustering<>("By Model Clustering", "bymodel-clustering");
    for (Entry<Model, ModifiableDBIDs> entry : modelMap.entrySet()) {
        final Model model = entry.getKey();
        final ModifiableDBIDs ids = entry.getValue();
        final String name = (model instanceof GeneratorInterface) ? ((GeneratorInterface) model).getName() : model.toString();
        Cluster<Model> c = new Cluster<>(name, ids, model);
        if (noisepattern != null && noisepattern.matcher(name).find()) {
            c.setNoise(true);
        }
        result.addToplevelCluster(c);
    }
    return result;
}

Example 14 with Cluster

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

the class RankingQualityHistogram method run.

/**
 * Process a database
 *
 * @param database Database to process
 * @param relation Relation to process
 * @return Histogram of ranking qualities
 */
public HistogramResult run(Database database, Relation<O> relation) {
    final DistanceQuery<O> distanceQuery = database.getDistanceQuery(relation, getDistanceFunction());
    final KNNQuery<O> knnQuery = database.getKNNQuery(distanceQuery, relation.size());
    if (LOG.isVerbose()) {
        LOG.verbose("Preprocessing clusters...");
    }
    // Cluster by labels
    Collection<Cluster<Model>> split = (new ByLabelOrAllInOneClustering()).run(database).getAllClusters();
    DoubleStaticHistogram hist = new DoubleStaticHistogram(numbins, 0.0, 1.0);
    if (LOG.isVerbose()) {
        LOG.verbose("Processing points...");
    }
    FiniteProgress progress = LOG.isVerbose() ? new FiniteProgress("Computing ROC AUC values", relation.size(), LOG) : null;
    ROCEvaluation roc = new ROCEvaluation();
    MeanVariance mv = new MeanVariance();
    // sort neighbors
    for (Cluster<?> clus : split) {
        for (DBIDIter iter = clus.getIDs().iter(); iter.valid(); iter.advance()) {
            KNNList knn = knnQuery.getKNNForDBID(iter, relation.size());
            double result = EvaluateClustering.evaluateRanking(roc, clus, knn);
            mv.put(result);
            hist.increment(result, 1. / relation.size());
            LOG.incrementProcessed(progress);
        }
    }
    LOG.ensureCompleted(progress);
    // Transform Histogram into a Double Vector array.
    Collection<double[]> res = new ArrayList<>(relation.size());
    for (DoubleStaticHistogram.Iter iter = hist.iter(); iter.valid(); iter.advance()) {
        res.add(new double[] { iter.getCenter(), iter.getValue() });
    }
    HistogramResult result = new HistogramResult("Ranking Quality Histogram", "ranking-histogram", res);
    result.addHeader("Mean: " + mv.getMean() + " Variance: " + mv.getSampleVariance());
    return result;
}

Example 15 with Cluster

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

the class KMLOutputHandler method buildHullsRecursively.

/**
 * Recursively step through the clusters to build the hulls.
 *
 * @param clu Current cluster
 * @param hier Clustering hierarchy
 * @param hulls Hull map
 */
private DoubleObjPair<Polygon> buildHullsRecursively(Cluster<Model> clu, Hierarchy<Cluster<Model>> hier, Map<Object, DoubleObjPair<Polygon>> hulls, Relation<? extends NumberVector> coords) {
    final DBIDs ids = clu.getIDs();
    GrahamScanConvexHull2D hull = new GrahamScanConvexHull2D();
    for (DBIDIter iter = ids.iter(); iter.valid(); iter.advance()) {
        hull.add(coords.get(iter).toArray());
    }
    double weight = ids.size();
    if (hier != null && hulls != null) {
        final int numc = hier.numChildren(clu);
        if (numc > 0) {
            for (It<Cluster<Model>> iter = hier.iterChildren(clu); iter.valid(); iter.advance()) {
                final Cluster<Model> iclu = iter.get();
                DoubleObjPair<Polygon> poly = hulls.get(iclu);
                if (poly == null) {
                    poly = buildHullsRecursively(iclu, hier, hulls, coords);
                }
                // Add inner convex hull to outer convex hull.
                for (ArrayListIter<double[]> vi = poly.second.iter(); vi.valid(); vi.advance()) {
                    hull.add(vi.get());
                }
                weight += poly.first / numc;
            }
        }
    }
    DoubleObjPair<Polygon> pair = new DoubleObjPair<>(weight, hull.getHull());
    hulls.put(clu, pair);
    return pair;
}