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

Example 11 with Model

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

the class OPTICSCut method makeOPTICSCut.

/**
 * Compute an OPTICS cut clustering
 *
 * @param co Cluster order result
 * @param epsilon Epsilon value for cut
 * @return New partitioning clustering
 */
public static <E extends ClusterOrder> Clustering<Model> makeOPTICSCut(E co, double epsilon) {
    // Clustering model we are building
    Clustering<Model> clustering = new Clustering<>("OPTICS Cut Clustering", "optics-cut");
    // Collects noise elements
    ModifiableDBIDs noise = DBIDUtil.newHashSet();
    double lastDist = Double.MAX_VALUE;
    double actDist = Double.MAX_VALUE;
    // Current working set
    ModifiableDBIDs current = DBIDUtil.newHashSet();
    // TODO: can we implement this more nicely with a 1-lookahead?
    DBIDVar prev = DBIDUtil.newVar();
    for (DBIDIter it = co.iter(); it.valid(); prev.set(it), it.advance()) {
        lastDist = actDist;
        actDist = co.getReachability(it);
        if (actDist <= epsilon) {
            // the last element before the plot drops belongs to the cluster
            if (lastDist > epsilon && prev.isSet()) {
                // So un-noise it
                noise.remove(prev);
                // Add it to the cluster
                current.add(prev);
            }
            current.add(it);
        } else {
            // 'Finish' the previous cluster
            if (!current.isEmpty()) {
                // TODO: do we want a minpts restriction?
                // But we get have only core points guaranteed anyway.
                clustering.addToplevelCluster(new Cluster<Model>(current, ClusterModel.CLUSTER));
                current = DBIDUtil.newHashSet();
            }
            // Add to noise
            noise.add(it);
        }
    }
    // Any unfinished cluster will also be added
    if (!current.isEmpty()) {
        clustering.addToplevelCluster(new Cluster<Model>(current, ClusterModel.CLUSTER));
    }
    // Add noise
    clustering.addToplevelCluster(new Cluster<Model>(noise, true, ClusterModel.CLUSTER));
    return clustering;
}

Example 12 with Model

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

the class NaiveAgglomerativeHierarchicalClustering2 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.");
    }
    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;
    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);
            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);
        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. Note: miny < minx
        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;
            }
            scratch[ybase + j] = Math.min(scratch[xbase + j], scratch[ybase + j]);
        }
        // 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);
            scratch[jbase + miny] = Math.min(scratch[xbase + j], scratch[jbase + miny]);
        }
        // Write to (j, y), with y < x < j
        for (int j = minx + 1; j < size; j++) {
            if (height[j] < Double.POSITIVE_INFINITY) {
                continue;
            }
            final int jbase = triangleSize(j);
            scratch[jbase + miny] = Math.min(scratch[jbase + minx], scratch[jbase + miny]);
        }
        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 Model

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

the class LMCLUS method run.

/**
 * The main LMCLUS (Linear manifold clustering algorithm) is processed in this
 * method.
 *
 * <PRE>
 * The algorithm samples random linear manifolds and tries to find clusters in it.
 * It calculates a distance histogram searches for a threshold and partitions the
 * points in two groups the ones in the cluster and everything else.
 * Then the best fitting linear manifold is searched and registered as a cluster.
 * The process is started over until all points are clustered.
 * The last cluster should contain all the outliers. (or the whole data if no clusters have been found.)
 * For details see {@link LMCLUS}.
 * </PRE>
 *
 * @param database The database to operate on
 * @param relation Relation
 * @return Clustering result
 */
public Clustering<Model> run(Database database, Relation<NumberVector> relation) {
    Clustering<Model> ret = new Clustering<>("LMCLUS Clustering", "lmclus-clustering");
    FiniteProgress progress = LOG.isVerbose() ? new FiniteProgress("Clustered objects", relation.size(), LOG) : null;
    IndefiniteProgress cprogress = LOG.isVerbose() ? new IndefiniteProgress("Clusters found", LOG) : null;
    ModifiableDBIDs unclustered = DBIDUtil.newHashSet(relation.getDBIDs());
    Random r = rnd.getSingleThreadedRandom();
    final int maxdim = Math.min(maxLMDim, RelationUtil.dimensionality(relation));
    int cnum = 0;
    while (unclustered.size() > minsize) {
        DBIDs current = unclustered;
        int lmDim = 1;
        for (int k = 1; k <= maxdim; k++) {
            // stopping at the appropriate dimensionality either.
            while (true) {
                Separation separation = findSeparation(relation, current, k, r);
                // " threshold: " + separation.threshold);
                if (separation.goodness <= sensitivityThreshold) {
                    break;
                }
                ModifiableDBIDs subset = DBIDUtil.newArray(current.size());
                for (DBIDIter iter = current.iter(); iter.valid(); iter.advance()) {
                    if (deviation(minusEquals(relation.get(iter).toArray(), separation.originV), separation.basis) < separation.threshold) {
                        subset.add(iter);
                    }
                }
                // logger.verbose("size:"+subset.size());
                if (subset.size() < minsize) {
                    break;
                }
                current = subset;
                lmDim = k;
            // System.out.println("Partition: " + subset.size());
            }
        }
        // No more clusters found
        if (current.size() < minsize || current == unclustered) {
            break;
        }
        // New cluster found
        // TODO: annotate cluster with dimensionality
        final Cluster<Model> cluster = new Cluster<>(current);
        cluster.setName("Cluster_" + lmDim + "d_" + cnum);
        cnum++;
        ret.addToplevelCluster(cluster);
        // Remove from main working set.
        unclustered.removeDBIDs(current);
        if (progress != null) {
            progress.setProcessed(relation.size() - unclustered.size(), LOG);
        }
        if (cprogress != null) {
            cprogress.setProcessed(cnum, LOG);
        }
    }
    // Remaining objects are noise
    if (unclustered.size() > 0) {
        ret.addToplevelCluster(new Cluster<>(unclustered, true));
    }
    if (progress != null) {
        progress.setProcessed(relation.size(), LOG);
        progress.ensureCompleted(LOG);
    }
    LOG.setCompleted(cprogress);
    return ret;
}

Example 14 with Model

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

the class PreDeConTest method testPreDeConSubspaceOverlapping.

/**
 * Run PreDeCon with fixed parameters and compare the result to a golden
 * standard.O
 */
@Test
public void testPreDeConSubspaceOverlapping() {
    Database db = makeSimpleDatabase(UNITTEST + "subspace-overlapping-3-4d.ascii", 850);
    Clustering<Model> result = // 
    new ELKIBuilder<PreDeCon<DoubleVector>>(PreDeCon.class).with(DBSCAN.Parameterizer.EPSILON_ID, // 
    0.3).with(DBSCAN.Parameterizer.MINPTS_ID, // 
    10).with(PreDeCon.Settings.Parameterizer.DELTA_ID, // 
    0.012).with(PreDeCon.Settings.Parameterizer.KAPPA_ID, // 
    10.).with(PreDeCon.Settings.Parameterizer.LAMBDA_ID, // 
    2).build().run(db);
    testFMeasure(db, result, 0.74982899);
    testClusterSizes(result, new int[] { 356, 494 });
}

Example 15 with Model

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

the class ClusterContingencyTableTest method testCompareDatabases.

/**
 * Validate {@link ClusterContingencyTable} with respect to its ability to
 * compare data clusterings.
 */
@Test
public void testCompareDatabases() {
    Database db = AbstractSimpleAlgorithmTest.makeSimpleDatabase(dataset, shoulds);
    Clustering<Model> rai = new TrivialAllInOne().run(db);
    Clustering<Model> ran = new TrivialAllNoise().run(db);
    Clustering<?> rbl = new ByLabelClustering().run(db);
    assertEquals(1.0, computeFMeasure(rai, rai, false), Double.MIN_VALUE);
    assertEquals(1.0, computeFMeasure(ran, ran, false), Double.MIN_VALUE);
    assertEquals(1.0, computeFMeasure(rbl, rbl, false), Double.MIN_VALUE);
    assertEquals(0.009950248756218905, computeFMeasure(ran, rbl, true), Double.MIN_VALUE);
    assertEquals(0.0033277870216306157, computeFMeasure(rai, ran, true), Double.MIN_VALUE);
    assertEquals(0.5, /* 0.3834296724470135 */
    computeFMeasure(rai, rbl, false), Double.MIN_VALUE);
}