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

Example 21 with Clustering

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

the class RepresentativeUncertainClustering method run.

/**
 * This run method will do the wrapping.
 *
 * Its called from {@link AbstractAlgorithm#run(Database)} and performs the
 * call to the algorithms particular run method as well as the storing and
 * comparison of the resulting Clusterings.
 *
 * @param database Database
 * @param relation Data relation of uncertain objects
 * @return Clustering result
 */
public Clustering<?> run(Database database, Relation<? extends UncertainObject> relation) {
    ResultHierarchy hierarchy = database.getHierarchy();
    ArrayList<Clustering<?>> clusterings = new ArrayList<>();
    final int dim = RelationUtil.dimensionality(relation);
    DBIDs ids = relation.getDBIDs();
    // To collect samples
    Result samples = new BasicResult("Samples", "samples");
    // Step 1: Cluster sampled possible worlds:
    Random rand = random.getSingleThreadedRandom();
    FiniteProgress sampleP = LOG.isVerbose() ? new FiniteProgress("Clustering samples", numsamples, LOG) : null;
    for (int i = 0; i < numsamples; i++) {
        WritableDataStore<DoubleVector> store = DataStoreUtil.makeStorage(ids, DataStoreFactory.HINT_DB, DoubleVector.class);
        for (DBIDIter iter = ids.iter(); iter.valid(); iter.advance()) {
            store.put(iter, relation.get(iter).drawSample(rand));
        }
        clusterings.add(runClusteringAlgorithm(hierarchy, samples, ids, store, dim, "Sample " + i));
        LOG.incrementProcessed(sampleP);
    }
    LOG.ensureCompleted(sampleP);
    // Step 2: perform the meta clustering (on samples only).
    DBIDRange rids = DBIDFactory.FACTORY.generateStaticDBIDRange(clusterings.size());
    WritableDataStore<Clustering<?>> datastore = DataStoreUtil.makeStorage(rids, DataStoreFactory.HINT_DB, Clustering.class);
    {
        Iterator<Clustering<?>> it2 = clusterings.iterator();
        for (DBIDIter iter = rids.iter(); iter.valid(); iter.advance()) {
            datastore.put(iter, it2.next());
        }
    }
    assert (rids.size() == clusterings.size());
    // Build a relation, and a distance matrix.
    Relation<Clustering<?>> crel = new MaterializedRelation<Clustering<?>>(Clustering.TYPE, rids, "Clusterings", datastore);
    PrecomputedDistanceMatrix<Clustering<?>> mat = new PrecomputedDistanceMatrix<>(crel, rids, distance);
    mat.initialize();
    ProxyDatabase d = new ProxyDatabase(rids, crel);
    d.getHierarchy().add(crel, mat);
    Clustering<?> c = metaAlgorithm.run(d);
    // Detach from database
    d.getHierarchy().remove(d, c);
    // Evaluation
    Result reps = new BasicResult("Representants", "representative");
    hierarchy.add(relation, reps);
    DistanceQuery<Clustering<?>> dq = mat.getDistanceQuery(distance);
    List<? extends Cluster<?>> cl = c.getAllClusters();
    List<DoubleObjPair<Clustering<?>>> evaluated = new ArrayList<>(cl.size());
    for (Cluster<?> clus : cl) {
        double besttau = Double.POSITIVE_INFINITY;
        Clustering<?> bestc = null;
        for (DBIDIter it1 = clus.getIDs().iter(); it1.valid(); it1.advance()) {
            double tau = 0.;
            Clustering<?> curc = crel.get(it1);
            for (DBIDIter it2 = clus.getIDs().iter(); it2.valid(); it2.advance()) {
                if (DBIDUtil.equal(it1, it2)) {
                    continue;
                }
                double di = dq.distance(curc, it2);
                tau = di > tau ? di : tau;
            }
            // Cluster member with the least maximum distance.
            if (tau < besttau) {
                besttau = tau;
                bestc = curc;
            }
        }
        if (bestc == null) {
            // E.g. degenerate empty clusters
            continue;
        }
        // Global tau:
        double gtau = 0.;
        for (DBIDIter it2 = crel.iterDBIDs(); it2.valid(); it2.advance()) {
            double di = dq.distance(bestc, it2);
            gtau = di > gtau ? di : gtau;
        }
        final double cprob = computeConfidence(clus.size(), crel.size());
        // Build an evaluation result
        hierarchy.add(bestc, new RepresentativenessEvaluation(gtau, besttau, cprob));
        evaluated.add(new DoubleObjPair<Clustering<?>>(cprob, bestc));
    }
    // Sort evaluated results by confidence:
    Collections.sort(evaluated, Collections.reverseOrder());
    for (DoubleObjPair<Clustering<?>> pair : evaluated) {
        // Attach parent relation (= sample) to the representative samples.
        for (It<Relation<?>> it = hierarchy.iterParents(pair.second).filter(Relation.class); it.valid(); it.advance()) {
            hierarchy.add(reps, it.get());
        }
    }
    // Add the random samples below the representative results only:
    if (keep) {
        hierarchy.add(relation, samples);
    } else {
        hierarchy.removeSubtree(samples);
    }
    return c;
}

Example 22 with Clustering

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

the class Leader method run.

/**
 * Run the leader clustering algorithm.
 *
 * @param relation Data set
 * @return Clustering result
 */
public Clustering<PrototypeModel<O>> run(Relation<O> relation) {
    RangeQuery<O> rq = relation.getRangeQuery(getDistanceFunction(), threshold);
    ModifiableDBIDs seen = DBIDUtil.newHashSet(relation.size());
    Clustering<PrototypeModel<O>> clustering = new Clustering<>("Prototype clustering", "prototype-clustering");
    int queries = 0;
    FiniteProgress prog = LOG.isVerbose() ? new FiniteProgress("Leader clustering", relation.size(), LOG) : null;
    for (DBIDIter it = relation.iterDBIDs(); it.valid() && seen.size() < relation.size(); it.advance()) {
        if (seen.contains(it)) {
            continue;
        }
        DoubleDBIDList res = rq.getRangeForDBID(it, threshold);
        ++queries;
        ModifiableDBIDs ids = DBIDUtil.newArray(res.size());
        for (DBIDIter cand = res.iter(); cand.valid(); cand.advance()) {
            if (seen.add(cand)) {
                LOG.incrementProcessed(prog);
                ids.add(cand);
            }
        }
        assert (ids.size() > 0 && ids.contains(it));
        PrototypeModel<O> mod = new SimplePrototypeModel<>(relation.get(it));
        clustering.addToplevelCluster(new Cluster<>(ids, mod));
    }
    LOG.statistics(new LongStatistic(this.getClass().getName() + ".queries", queries));
    LOG.ensureCompleted(prog);
    return clustering;
}

Example 23 with Clustering

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

the class DBSCAN method run.

/**
 * Performs the DBSCAN algorithm on the given database.
 */
public Clustering<Model> run(Relation<O> relation) {
    final int size = relation.size();
    if (size < minpts) {
        Clustering<Model> result = new Clustering<>("DBSCAN Clustering", "dbscan-clustering");
        result.addToplevelCluster(new Cluster<Model>(relation.getDBIDs(), true, ClusterModel.CLUSTER));
        return result;
    }
    RangeQuery<O> rangeQuery = QueryUtil.getRangeQuery(relation, getDistanceFunction());
    resultList = new ArrayList<>();
    noise = DBIDUtil.newHashSet();
    runDBSCAN(relation, rangeQuery);
    double averagen = ncounter / (double) relation.size();
    LOG.statistics(new DoubleStatistic(DBSCAN.class.getName() + ".average-neighbors", averagen));
    if (averagen < 1 + 0.1 * (minpts - 1)) {
        LOG.warning("There are very few neighbors found. Epsilon may be too small.");
    }
    if (averagen > 100 * minpts) {
        LOG.warning("There are very many neighbors found. Epsilon may be too large.");
    }
    Clustering<Model> result = new Clustering<>("DBSCAN Clustering", "dbscan-clustering");
    for (ModifiableDBIDs res : resultList) {
        result.addToplevelCluster(new Cluster<Model>(res, ClusterModel.CLUSTER));
    }
    result.addToplevelCluster(new Cluster<Model>(noise, true, ClusterModel.CLUSTER));
    return result;
}

Example 24 with Clustering

use of de.lmu.ifi.dbs.elki.data.Clustering 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 25 with Clustering

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

the class OutlierThresholdClustering method split.

private Clustering<Model> split(OutlierResult or) {
    DoubleRelation scores = or.getScores();
    if (scaling instanceof OutlierScalingFunction) {
        ((OutlierScalingFunction) scaling).prepare(or);
    }
    ArrayList<ModifiableDBIDs> idlists = new ArrayList<>(threshold.length + 1);
    for (int i = 0; i <= threshold.length; i++) {
        idlists.add(DBIDUtil.newHashSet());
    }
    for (DBIDIter iter = scores.getDBIDs().iter(); iter.valid(); iter.advance()) {
        double score = scores.doubleValue(iter);
        if (scaling != null) {
            score = scaling.getScaled(score);
        }
        int i = 0;
        for (; i < threshold.length; i++) {
            if (score < threshold[i]) {
                break;
            }
        }
        idlists.get(i).add(iter);
    }
    Clustering<Model> c = new Clustering<>("Outlier threshold clustering", "threshold-clustering");
    for (int i = 0; i <= threshold.length; i++) {
        String name = (i == 0) ? "Inlier" : "Outlier_" + threshold[i - 1];
        c.addToplevelCluster(new Cluster<>(name, idlists.get(i), (i > 0)));
    }
    return c;
}