/**
* Constructor.
*
* @param size Size
* @param idmap ID map
*/
public ArrayDBIDStore(int size, DataStoreIDMap idmap) {
super();
this.data = DBIDUtil.newArray(size);
// Initialize
DBIDRef inv = DBIDUtil.invalid();
for (int i = 0; i < size; i++) {
data.add(inv);
}
this.idmap = idmap;
}
/**
* DBSCAN-function expandCluster.
*
* <p>Border-Objects become members of the first possible cluster.
*
* @param relation Database relation to run on
* @param rangeQuery Range query to use
* @param startObjectID potential seed of a new potential cluster
* @param objprog the progress object for logging the current status
*/
protected void expandCluster(
Relation<O> relation,
RangeQuery<O> rangeQuery,
DBIDRef startObjectID,
FiniteProgress objprog,
IndefiniteProgress clusprog) {
DoubleDBIDList neighbors = rangeQuery.getRangeForDBID(startObjectID, epsilon);
ncounter += neighbors.size();
// startObject is no core-object
if (neighbors.size() < minpts) {
noise.add(startObjectID);
processedIDs.add(startObjectID);
if (objprog != null) {
objprog.incrementProcessed(LOG);
}
return;
}
ModifiableDBIDs currentCluster = DBIDUtil.newArray();
currentCluster.add(startObjectID);
processedIDs.add(startObjectID);
// try to expand the cluster
HashSetModifiableDBIDs seeds = DBIDUtil.newHashSet();
processNeighbors(neighbors.iter(), currentCluster, seeds);
DBIDVar o = DBIDUtil.newVar();
while (!seeds.isEmpty()) {
seeds.pop(o);
neighbors = rangeQuery.getRangeForDBID(o, epsilon);
ncounter += neighbors.size();
if (neighbors.size() >= minpts) {
processNeighbors(neighbors.iter(), currentCluster, seeds);
}
if (objprog != null) {
objprog.incrementProcessed(LOG);
}
}
resultList.add(currentCluster);
if (clusprog != null) {
clusprog.setProcessed(resultList.size(), LOG);
}
}
private DBIDs mergeJoin(DBIDs first, DBIDs second) {
assert (!(first instanceof HashSetDBIDs));
assert (!(second instanceof HashSetDBIDs));
ArrayModifiableDBIDs ids = DBIDUtil.newArray();
DBIDIter i1 = first.iter(), i2 = second.iter();
while (i1.valid() && i2.valid()) {
int c = DBIDUtil.compare(i1, i2);
if (c < 0) {
i1.advance();
} else if (c > 0) {
i2.advance();
} else {
ids.add(i1);
i1.advance();
i2.advance();
}
}
return ids;
}
private DBIDs[] buildIndex(Relation<BitVector> relation, int dim, int minsupp) {
ArrayModifiableDBIDs[] idx = new ArrayModifiableDBIDs[dim];
for (int i = 0; i < dim; i++) {
idx[i] = DBIDUtil.newArray();
}
for (DBIDIter iter = relation.iterDBIDs(); iter.valid(); iter.advance()) {
SparseFeatureVector<?> bv = relation.get(iter);
// TODO: only count those which satisfy minlength?
for (int it = bv.iter(); bv.iterValid(it); it = bv.iterAdvance(it)) {
idx[bv.iterDim(it)].add(iter);
}
}
// Forget non-frequent 1-itemsets.
for (int i = 0; i < dim; i++) {
if (idx[i].size() < minsupp) {
idx[i] = null;
} else {
idx[i].sort();
}
}
return idx;
}
/**
* Performs the DOC or FastDOC (as configured) algorithm on the given Database.
*
* <p>This will run exhaustively, i.e. run DOC until no clusters are found anymore / the database
* size has shrunk below the threshold for minimum cluster size.
*
* @param database Database
* @param relation Data relation
*/
public Clustering<SubspaceModel> run(Database database, Relation<V> relation) {
// Dimensionality of our set.
final int d = RelationUtil.dimensionality(relation);
// Get available DBIDs as a set we can remove items from.
ArrayModifiableDBIDs S = DBIDUtil.newArray(relation.getDBIDs());
// Precompute values as described in Figure 2.
double r = Math.abs(Math.log(d + d) / Math.log(beta * .5));
// Outer loop count.
int n = (int) (2. / alpha);
// Inner loop count.
int m = (int) (Math.pow(2. / alpha, r) * Math.log(4));
if (heuristics) {
m = Math.min(m, Math.min(1000000, d * d));
}
// Minimum size for a cluster for it to be accepted.
int minClusterSize = (int) (alpha * S.size());
// List of all clusters we found.
Clustering<SubspaceModel> result = new Clustering<>("DOC Clusters", "DOC");
// Inform the user about the number of actual clusters found so far.
IndefiniteProgress cprogress =
LOG.isVerbose() ? new IndefiniteProgress("Number of clusters", LOG) : null;
// To not only find a single cluster, we continue running until our set
// of points is empty.
while (S.size() > minClusterSize) {
Cluster<SubspaceModel> C;
if (heuristics) {
C = runFastDOC(database, relation, S, d, n, m, (int) r);
} else {
C = runDOC(database, relation, S, d, n, m, (int) r, minClusterSize);
}
if (C == null) {
// Stop trying if we couldn't find a cluster.
break;
}
// Found a cluster, remember it, remove its points from the set.
result.addToplevelCluster(C);
// Remove all points of the cluster from the set and continue.
S.removeDBIDs(C.getIDs());
if (cprogress != null) {
cprogress.setProcessed(result.getAllClusters().size(), LOG);
}
}
// Add the remainder as noise.
if (S.size() > 0) {
long[] alldims = BitsUtil.ones(d);
result.addToplevelCluster(
new Cluster<>(
S,
true,
new SubspaceModel(new Subspace(alldims), Centroid.make(relation, S).getArrayRef())));
}
LOG.setCompleted(cprogress);
return result;
}
