public List<Polygon> compute() {
// Compute delaunay triangulation:
delaunay = (new SweepHullDelaunay2D(points)).getDelaunay();
List<Polygon> polys = new ArrayList<>();
// Working data
long[] used = BitsUtil.zero(delaunay.size());
List<double[]> cur = new ArrayList<>();
for (int i = 0 /* = used.nextClearBit(0) */;
i < delaunay.size() && i >= 0;
i = BitsUtil.nextClearBit(used, i + 1)) {
if (!BitsUtil.get(used, i)) {
BitsUtil.setI(used, i);
SweepHullDelaunay2D.Triangle tri = delaunay.get(i);
if (tri.r2 <= alpha2) {
// Check neighbors
processNeighbor(cur, used, i, tri.ab, tri.b);
processNeighbor(cur, used, i, tri.bc, tri.c);
processNeighbor(cur, used, i, tri.ca, tri.a);
}
if (cur.size() > 0) {
polys.add(new Polygon(cur));
cur = new ArrayList<>();
}
}
}
return polys;
}
/**
* Select or deselect a row.
*
* @param rnum Row to select
* @param set Value to set
*/
protected void selectRow(int rnum, boolean set) {
if (set) {
BitsUtil.setI(rows, rnum);
rowcard++;
} else {
BitsUtil.clearI(rows, rnum);
rowcard--;
}
}
/**
* Select or deselect a column.
*
* @param cnum Column to select
* @param set Value to set
*/
protected void selectColumn(int cnum, boolean set) {
if (set) {
BitsUtil.setI(cols, cnum);
colcard++;
} else {
BitsUtil.clearI(cols, cnum);
colcard--;
}
}
@Override
public long[] getVisibleDimensions2D() {
final int dim = proj.getDimensionality();
long[] actDim = BitsUtil.zero(dim);
double[] vScale = new double[dim];
for (int d = 0; d < dim; d++) {
Arrays.fill(vScale, 0);
vScale[d] = 1;
double[] vRender = fastProjectScaledToRenderSpace(vScale);
// TODO: Can't we do this by inspecting the projection matrix directly?
if (vRender[0] > 0.0 || vRender[0] < 0.0 || vRender[1] != 0) {
BitsUtil.setI(actDim, d);
}
}
return actDim;
}
/**
* Main loop of OUTRES. Run for each object
*
* @param s start dimension
* @param subspace Current subspace
* @param id Current object ID
* @param kernel Kernel
* @return Score
*/
public double outresScore(
final int s, long[] subspace, DBIDRef id, KernelDensityEstimator kernel) {
double score = 1.0; // Initial score is 1.0
final SubspaceEuclideanDistanceFunction df = new SubspaceEuclideanDistanceFunction(subspace);
MeanVariance meanv = new MeanVariance();
for (int i = s; i < kernel.dim; i++) {
if (BitsUtil.get(subspace, i)) { // TODO: needed? Or should we always start
// with i=0?
continue;
}
BitsUtil.setI(subspace, i);
df.setSelectedDimensions(subspace);
final double adjustedEps = kernel.adjustedEps(kernel.dim);
// Query with a larger window, to also get neighbors of neighbors
// Subspace euclidean is metric!
final double range = adjustedEps * 2.;
RangeQuery<V> rq = QueryUtil.getRangeQuery(kernel.relation, df, range);
DoubleDBIDList neighc = rq.getRangeForDBID(id, range);
DoubleDBIDList neigh = refineRange(neighc, adjustedEps);
if (neigh.size() > 2) {
// Relevance test
if (relevantSubspace(subspace, neigh, kernel)) {
final double density = kernel.subspaceDensity(subspace, neigh);
// Compute mean and standard deviation for densities of neighbors.
meanv.reset();
for (DoubleDBIDListIter neighbor = neigh.iter(); neighbor.valid(); neighbor.advance()) {
DoubleDBIDList n2 = subsetNeighborhoodQuery(neighc, neighbor, df, adjustedEps, kernel);
meanv.put(kernel.subspaceDensity(subspace, n2));
}
final double deviation = (meanv.getMean() - density) / (2. * meanv.getSampleStddev());
// High deviation:
if (deviation >= 1) {
score *= (density / deviation);
}
// Recursion
score *= outresScore(i + 1, subspace, id, kernel);
}
}
BitsUtil.clearI(subspace, i);
}
return score;
}
private void processNeighbor(List<double[]> cur, long[] used, int i, int ab, int b) {
if (ab >= 0) {
if (BitsUtil.get(used, ab)) {
return;
}
BitsUtil.setI(used, ab);
final SweepHullDelaunay2D.Triangle next = delaunay.get(ab);
if (next.r2 < alpha2) {
// Continue where we left off...
if (next.ab == i) {
processNeighbor(cur, used, ab, next.bc, next.c);
processNeighbor(cur, used, ab, next.ca, next.a);
} else if (next.bc == i) {
processNeighbor(cur, used, ab, next.ca, next.a);
processNeighbor(cur, used, ab, next.ab, next.b);
} else if (next.ca == i) {
processNeighbor(cur, used, ab, next.ab, next.b);
processNeighbor(cur, used, ab, next.bc, next.c);
}
return;
}
}
cur.add(points.get(b));
}
protected void invertRow(int rnum, boolean b) {
BitsUtil.setI(irow, rnum);
}
/**
* Performs a single run of FastDOC, finding a single cluster.
*
* @param database Database context
* @param relation used to get actual values for DBIDs.
* @param S The set of points we're working on.
* @param d Dimensionality of the data set we're currently working on.
* @param r Size of random samples.
* @param m Number of inner iterations (per seed point).
* @param n Number of outer iterations (seed points).
* @return a cluster, if one is found, else <code>null</code>.
*/
private Cluster<SubspaceModel> runFastDOC(
Database database, Relation<V> relation, ArrayModifiableDBIDs S, int d, int n, int m, int r) {
// Relevant attributes of highest cardinality.
long[] D = null;
// The seed point for the best dimensions.
DBIDVar dV = DBIDUtil.newVar();
// Inform the user about the progress in the current iteration.
FiniteProgress iprogress =
LOG.isVerbose()
? new FiniteProgress("Iteration progress for current cluster", m * n, LOG)
: null;
Random random = rnd.getSingleThreadedRandom();
DBIDArrayIter iter = S.iter();
outer:
for (int i = 0; i < n; ++i) {
// Pick a random seed point.
iter.seek(random.nextInt(S.size()));
for (int j = 0; j < m; ++j) {
// Choose a set of random points.
DBIDs randomSet = DBIDUtil.randomSample(S, r, random);
// Initialize cluster info.
long[] nD = BitsUtil.zero(d);
// Test each dimension.
for (int k = 0; k < d; ++k) {
if (dimensionIsRelevant(k, relation, randomSet)) {
BitsUtil.setI(nD, k);
}
}
if (D == null || BitsUtil.cardinality(nD) > BitsUtil.cardinality(D)) {
D = nD;
dV.set(iter);
if (BitsUtil.cardinality(D) >= d_zero) {
if (iprogress != null) {
iprogress.setProcessed(iprogress.getTotal(), LOG);
}
break outer;
}
}
LOG.incrementProcessed(iprogress);
}
}
LOG.ensureCompleted(iprogress);
// If no relevant dimensions were found, skip it.
if (D == null || BitsUtil.cardinality(D) == 0) {
return null;
}
// Get all points in the box.
SubspaceMaximumDistanceFunction df = new SubspaceMaximumDistanceFunction(D);
DistanceQuery<V> dq = database.getDistanceQuery(relation, df);
RangeQuery<V> rq = database.getRangeQuery(dq, DatabaseQuery.HINT_SINGLE);
// TODO: add filtering capabilities into query API!
DBIDs C = DBIDUtil.intersection(S, rq.getRangeForDBID(dV, w));
// If we have a non-empty cluster, return it.
return (C.size() > 0) ? makeCluster(relation, C, D) : null;
}
/**
* Performs a single run of DOC, finding a single cluster.
*
* @param database Database context
* @param relation used to get actual values for DBIDs.
* @param S The set of points we're working on.
* @param d Dimensionality of the data set we're currently working on.
* @param r Size of random samples.
* @param m Number of inner iterations (per seed point).
* @param n Number of outer iterations (seed points).
* @param minClusterSize Minimum size a cluster must have to be accepted.
* @return a cluster, if one is found, else <code>null</code>.
*/
private Cluster<SubspaceModel> runDOC(
Database database,
Relation<V> relation,
ArrayModifiableDBIDs S,
final int d,
int n,
int m,
int r,
int minClusterSize) {
// Best cluster for the current run.
DBIDs C = null;
// Relevant attributes for the best cluster.
long[] D = null;
// Quality of the best cluster.
double quality = Double.NEGATIVE_INFINITY;
// Bounds for our cluster.
// ModifiableHyperBoundingBox bounds = new ModifiableHyperBoundingBox(new
// double[d], new double[d]);
// Weights for distance (= rectangle query)
SubspaceMaximumDistanceFunction df = new SubspaceMaximumDistanceFunction(BitsUtil.zero(d));
DistanceQuery<V> dq = database.getDistanceQuery(relation, df);
RangeQuery<V> rq = database.getRangeQuery(dq);
// Inform the user about the progress in the current iteration.
FiniteProgress iprogress =
LOG.isVerbose()
? new FiniteProgress("Iteration progress for current cluster", m * n, LOG)
: null;
Random random = rnd.getSingleThreadedRandom();
DBIDArrayIter iter = S.iter();
for (int i = 0; i < n; ++i) {
// Pick a random seed point.
iter.seek(random.nextInt(S.size()));
for (int j = 0; j < m; ++j) {
// Choose a set of random points.
DBIDs randomSet = DBIDUtil.randomSample(S, r, random);
// Initialize cluster info.
long[] nD = BitsUtil.zero(d);
// Test each dimension and build bounding box.
for (int k = 0; k < d; ++k) {
if (dimensionIsRelevant(k, relation, randomSet)) {
BitsUtil.setI(nD, k);
}
}
if (BitsUtil.cardinality(nD) > 0) {
// Get all points in the box.
df.setSelectedDimensions(nD);
// TODO: add filtering capabilities into query API!
DBIDs nC = DBIDUtil.intersection(S, rq.getRangeForDBID(iter, w));
if (LOG.isDebuggingFiner()) {
LOG.finer(
"Testing a cluster candidate, |C| = "
+ nC.size()
+ ", |D| = "
+ BitsUtil.cardinality(nD));
}
// Is the cluster large enough?
if (nC.size() < minClusterSize) {
// Too small.
if (LOG.isDebuggingFiner()) {
LOG.finer("... but it's too small.");
}
} else {
// Better cluster than before?
double nQuality = computeClusterQuality(nC.size(), BitsUtil.cardinality(nD));
if (nQuality > quality) {
if (LOG.isDebuggingFiner()) {
LOG.finer("... and it's the best so far: " + nQuality + " vs. " + quality);
}
C = nC;
D = nD;
quality = nQuality;
} else {
if (LOG.isDebuggingFiner()) {
LOG.finer("... but we already have a better one.");
}
}
}
}
LOG.incrementProcessed(iprogress);
}
}
LOG.ensureCompleted(iprogress);
return (C != null) ? makeCluster(relation, C, D) : null;
}