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

Example 46 with DBIDArrayIter

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

the class MatrixParadigm method initializeWithDistances.

/**
 * Initialize a distance matrix.
 *
 * @param dq Distance query
 * @return this
 */
public MatrixParadigm initializeWithDistances(DistanceQuery<?> dq) {
    final DBIDArrayIter ix = this.ix, iy = this.iy;
    final double[] matrix = this.matrix;
    int pos = 0;
    for (ix.seek(0); ix.valid(); ix.advance()) {
        final int x = ix.getOffset();
        assert (pos == triangleSize(x));
        for (iy.seek(0); iy.getOffset() < x; iy.advance()) {
            matrix[pos++] = dq.distance(ix, iy);
        }
    }
    return this;
}

Example 47 with DBIDArrayIter

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

the class CLINK method clinkstep4567.

/**
 * Fourth to seventh step of CLINK: find best insertion
 *
 * @param id Current objct
 * @param ids All objects
 * @param it Iterator
 * @param n Index threshold
 * @param pi Parent data store
 * @param lambda Height data store
 * @param m Distance data store
 */
private void clinkstep4567(DBIDRef id, ArrayDBIDs ids, DBIDArrayIter it, int n, WritableDBIDDataStore pi, WritableDoubleDataStore lambda, WritableDoubleDataStore m) {
    // step 4: a = n
    DBIDArrayIter a = ids.iter().seek(n - 1);
    // step 5:
    {
        DBIDVar p_i = DBIDUtil.newVar();
        for (it.seek(n - 1); it.valid(); it.retract()) {
            double l_i = lambda.doubleValue(it);
            double mp_i = m.doubleValue(p_i.from(pi, it));
            if (l_i >= mp_i) {
                if (m.doubleValue(it) < m.doubleValue(a)) {
                    a.seek(it.getOffset());
                }
            } else {
                m.putDouble(it, Double.POSITIVE_INFINITY);
            }
        }
    }
    // step 6
    // b = pi[a]
    DBIDVar b = DBIDUtil.newVar().from(pi, a);
    double c = lambda.doubleValue(a);
    pi.putDBID(a, id);
    lambda.putDouble(a, m.doubleValue(a));
    // step 7
    if (a.getOffset() < n - 1) {
        // Used below
        DBIDRef last = DBIDUtil.newVar(it.seek(n - 1));
        DBIDVar d = DBIDUtil.newVar();
        // if b < n: (then goto 7)
        while (!DBIDUtil.equal(b, id)) {
            if (DBIDUtil.equal(b, last)) {
                pi.putDBID(b, id);
                lambda.putDouble(b, c);
                break;
            }
            // d = pi[b]
            d.from(pi, b);
            // pi[b] = n + 1
            pi.putDBID(b, id);
            // c = old l[b], l[b] = c
            c = lambda.putDouble(b, c);
            // b = d = old pi[b]
            b.set(d);
        }
    }
}

Example 48 with DBIDArrayIter

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

the class SLINK method run.

/**
 * Performs the SLINK algorithm on the given database.
 *
 * @param database Database to process
 * @param relation Data relation to use
 */
public PointerHierarchyRepresentationResult run(Database database, Relation<O> relation) {
    DBIDs ids = relation.getDBIDs();
    WritableDBIDDataStore pi = DataStoreUtil.makeDBIDStorage(ids, DataStoreFactory.HINT_HOT | DataStoreFactory.HINT_STATIC);
    WritableDoubleDataStore lambda = DataStoreUtil.makeDoubleStorage(ids, DataStoreFactory.HINT_HOT | DataStoreFactory.HINT_STATIC, Double.POSITIVE_INFINITY);
    // Temporary storage for m.
    WritableDoubleDataStore m = DataStoreUtil.makeDoubleStorage(ids, DataStoreFactory.HINT_HOT | DataStoreFactory.HINT_TEMP);
    // To allow CLINK logger override
    final Logging log = getLogger();
    FiniteProgress progress = log.isVerbose() ? new FiniteProgress("Running SLINK", ids.size(), log) : null;
    ArrayDBIDs aids = DBIDUtil.ensureArray(ids);
    // First element is trivial/special:
    DBIDArrayIter id = aids.iter(), it = aids.iter();
    // Step 1: initialize
    for (; id.valid(); id.advance()) {
        // P(n+1) = n+1:
        pi.put(id, id);
    // L(n+1) = infinity already.
    }
    // First element is finished already (start at seek(1) below!)
    log.incrementProcessed(progress);
    // Optimized branch
    if (getDistanceFunction() instanceof PrimitiveDistanceFunction) {
        PrimitiveDistanceFunction<? super O> distf = (PrimitiveDistanceFunction<? super O>) getDistanceFunction();
        for (id.seek(1); id.valid(); id.advance()) {
            step2primitive(id, it, id.getOffset(), relation, distf, m);
            // SLINK or CLINK
            process(id, aids, it, id.getOffset(), pi, lambda, m);
            log.incrementProcessed(progress);
        }
    } else {
        // Fallback branch
        DistanceQuery<O> distQ = database.getDistanceQuery(relation, getDistanceFunction());
        for (id.seek(1); id.valid(); id.advance()) {
            step2(id, it, id.getOffset(), distQ, m);
            // SLINK or CLINK
            process(id, aids, it, id.getOffset(), pi, lambda, m);
            log.incrementProcessed(progress);
        }
    }
    log.ensureCompleted(progress);
    // We don't need m anymore.
    m.destroy();
    m = null;
    return new PointerHierarchyRepresentationResult(ids, pi, lambda, getDistanceFunction().isSquared());
}

Example 49 with DBIDArrayIter

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

the class DistanceBasedInitializationWithMedian method getSimilarityMatrix.

@Override
public double[][] getSimilarityMatrix(Database db, Relation<O> relation, ArrayDBIDs ids) {
    final int size = ids.size();
    DistanceQuery<O> dq = db.getDistanceQuery(relation, distance);
    double[][] mat = new double[size][size];
    double[] flat = new double[(size * (size - 1)) >> 1];
    DBIDArrayIter i1 = ids.iter(), i2 = ids.iter();
    for (int i = 0, j = 0; i < size; i++, i1.advance()) {
        double[] mati = mat[i];
        i2.seek(i + 1);
        for (int k = i + 1; k < size; k++, i2.advance()) {
            mati[k] = -dq.distance(i1, i2);
            // symmetry.
            mat[k][i] = mati[k];
            flat[j] = mati[k];
            j++;
        }
    }
    double median = QuickSelect.quantile(flat, quantile);
    // On the diagonal, we place the median
    for (int i = 0; i < size; i++) {
        mat[i][i] = median;
    }
    return mat;
}

Example 50 with DBIDArrayIter

use of de.lmu.ifi.dbs.elki.database.ids.DBIDArrayIter 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;
}