/** 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;
}
@Override
public Clustering<BiclusterWithInversionsModel> biclustering() {
double[][] mat = RelationUtil.relationAsMatrix(relation, rowIDs);
BiclusterCandidate cand = new BiclusterCandidate(getRowDim(), getColDim());
Clustering<BiclusterWithInversionsModel> result =
new Clustering<>("Cheng-and-Church", "Cheng and Church Biclustering");
ModifiableDBIDs noise = DBIDUtil.newHashSet(relation.getDBIDs());
FiniteProgress prog = LOG.isVerbose() ? new FiniteProgress("Extracting Cluster", n, LOG) : null;
for (int i = 0; i < n; i++) {
cand.reset();
multipleNodeDeletion(mat, cand);
if (LOG.isVeryVerbose()) {
LOG.veryverbose(
"Residue after Alg 2: " + cand.residue + " " + cand.rowcard + "x" + cand.colcard);
}
singleNodeDeletion(mat, cand);
if (LOG.isVeryVerbose()) {
LOG.veryverbose(
"Residue after Alg 1: " + cand.residue + " " + cand.rowcard + "x" + cand.colcard);
}
nodeAddition(mat, cand);
if (LOG.isVeryVerbose()) {
LOG.veryverbose(
"Residue after Alg 3: " + cand.residue + " " + cand.rowcard + "x" + cand.colcard);
}
cand.maskMatrix(mat, dist);
BiclusterWithInversionsModel model =
new BiclusterWithInversionsModel(colsBitsetToIDs(cand.cols), rowsBitsetToIDs(cand.irow));
final ArrayDBIDs cids = rowsBitsetToIDs(cand.rows);
noise.removeDBIDs(cids);
result.addToplevelCluster(new Cluster<>(cids, model));
if (LOG.isVerbose()) {
LOG.verbose("Score of bicluster " + (i + 1) + ": " + cand.residue + "\n");
LOG.verbose("Number of rows: " + cand.rowcard + "\n");
LOG.verbose("Number of columns: " + cand.colcard + "\n");
// LOG.verbose("Total number of masked values: " + maskedVals.size() +
// "\n");
}
LOG.incrementProcessed(prog);
}
// Add a noise cluster, full-dimensional.
if (!noise.isEmpty()) {
long[] allcols = BitsUtil.ones(getColDim());
BiclusterWithInversionsModel model =
new BiclusterWithInversionsModel(colsBitsetToIDs(allcols), DBIDUtil.EMPTYDBIDS);
result.addToplevelCluster(new Cluster<>(noise, true, model));
}
LOG.ensureCompleted(prog);
return result;
}
@Override
public Clustering<KMeansModel> run(Database database, Relation<V> relation) {
if (relation.size() <= 0) {
return new Clustering<>("k-Means Clustering", "kmeans-clustering");
}
// Choose initial means
if (LOG.isStatistics()) {
LOG.statistics(new StringStatistic(KEY + ".initialization", initializer.toString()));
}
double[][] means = initializer.chooseInitialMeans(database, relation, k, getDistanceFunction());
// Setup cluster assignment store
List<ModifiableDBIDs> clusters = new ArrayList<>();
for (int i = 0; i < k; i++) {
clusters.add(DBIDUtil.newHashSet((int) (relation.size() * 2. / k)));
}
WritableIntegerDataStore assignment =
DataStoreUtil.makeIntegerStorage(
relation.getDBIDs(), DataStoreFactory.HINT_TEMP | DataStoreFactory.HINT_HOT, -1);
double[] varsum = new double[k];
IndefiniteProgress prog =
LOG.isVerbose() ? new IndefiniteProgress("K-Means iteration", LOG) : null;
DoubleStatistic varstat =
LOG.isStatistics()
? new DoubleStatistic(this.getClass().getName() + ".variance-sum")
: null;
int iteration = 0;
for (; maxiter <= 0 || iteration < maxiter; iteration++) {
LOG.incrementProcessed(prog);
boolean changed = assignToNearestCluster(relation, means, clusters, assignment, varsum);
logVarstat(varstat, varsum);
// Stop if no cluster assignment changed.
if (!changed) {
break;
}
// Recompute means.
means = means(clusters, means, relation);
}
LOG.setCompleted(prog);
if (LOG.isStatistics()) {
LOG.statistics(new LongStatistic(KEY + ".iterations", iteration));
}
// Wrap result
Clustering<KMeansModel> result = new Clustering<>("k-Means Clustering", "kmeans-clustering");
for (int i = 0; i < clusters.size(); i++) {
DBIDs ids = clusters.get(i);
if (ids.size() == 0) {
continue;
}
KMeansModel model = new KMeansModel(means[i], varsum[i]);
result.addToplevelCluster(new Cluster<>(ids, model));
}
return result;
}
/**
* Performs the SUBCLU algorithm on the given database.
*
* @param relation Relation to process
* @return Clustering result
*/
public Clustering<SubspaceModel> run(Relation<V> relation) {
final int dimensionality = RelationUtil.dimensionality(relation);
StepProgress stepprog = LOG.isVerbose() ? new StepProgress(dimensionality) : null;
// Generate all 1-dimensional clusters
LOG.beginStep(stepprog, 1, "Generate all 1-dimensional clusters.");
// mapping of dimensionality to set of subspaces
HashMap<Integer, List<Subspace>> subspaceMap = new HashMap<>();
// list of 1-dimensional subspaces containing clusters
List<Subspace> s_1 = new ArrayList<>();
subspaceMap.put(0, s_1);
// mapping of subspaces to list of clusters
TreeMap<Subspace, List<Cluster<Model>>> clusterMap =
new TreeMap<>(new Subspace.DimensionComparator());
for (int d = 0; d < dimensionality; d++) {
Subspace currentSubspace = new Subspace(d);
List<Cluster<Model>> clusters = runDBSCAN(relation, null, currentSubspace);
if (LOG.isDebuggingFiner()) {
StringBuilder msg = new StringBuilder();
msg.append('\n')
.append(clusters.size())
.append(" clusters in subspace ")
.append(currentSubspace.dimensonsToString())
.append(": \n");
for (Cluster<Model> cluster : clusters) {
msg.append(" " + cluster.getIDs() + "\n");
}
LOG.debugFiner(msg.toString());
}
if (!clusters.isEmpty()) {
s_1.add(currentSubspace);
clusterMap.put(currentSubspace, clusters);
}
}
// Generate (d+1)-dimensional clusters from d-dimensional clusters
for (int d = 0; d < dimensionality - 1; d++) {
if (stepprog != null) {
stepprog.beginStep(
d + 2,
"Generate "
+ (d + 2)
+ "-dimensional clusters from "
+ (d + 1)
+ "-dimensional clusters.",
LOG);
}
List<Subspace> subspaces = subspaceMap.get(d);
if (subspaces == null || subspaces.isEmpty()) {
if (stepprog != null) {
for (int dim = d + 1; dim < dimensionality - 1; dim++) {
stepprog.beginStep(
dim + 2,
"Generation of"
+ (dim + 2)
+ "-dimensional clusters not applicable, because no more "
+ (d + 2)
+ "-dimensional subspaces found.",
LOG);
}
}
break;
}
List<Subspace> candidates = generateSubspaceCandidates(subspaces);
List<Subspace> s_d = new ArrayList<>();
for (Subspace candidate : candidates) {
Subspace bestSubspace = bestSubspace(subspaces, candidate, clusterMap);
if (LOG.isDebuggingFine()) {
LOG.debugFine(
"best subspace of "
+ candidate.dimensonsToString()
+ ": "
+ bestSubspace.dimensonsToString());
}
List<Cluster<Model>> bestSubspaceClusters = clusterMap.get(bestSubspace);
List<Cluster<Model>> clusters = new ArrayList<>();
for (Cluster<Model> cluster : bestSubspaceClusters) {
List<Cluster<Model>> candidateClusters = runDBSCAN(relation, cluster.getIDs(), candidate);
if (!candidateClusters.isEmpty()) {
clusters.addAll(candidateClusters);
}
}
if (LOG.isDebuggingFine()) {
StringBuilder msg = new StringBuilder();
msg.append(clusters.size() + " cluster(s) in subspace " + candidate + ": \n");
for (Cluster<Model> c : clusters) {
msg.append(" " + c.getIDs() + "\n");
}
LOG.debugFine(msg.toString());
}
if (!clusters.isEmpty()) {
s_d.add(candidate);
clusterMap.put(candidate, clusters);
}
}
if (!s_d.isEmpty()) {
subspaceMap.put(d + 1, s_d);
}
}
// build result
int numClusters = 1;
result = new Clustering<>("SUBCLU clustering", "subclu-clustering");
for (Subspace subspace : clusterMap.descendingKeySet()) {
List<Cluster<Model>> clusters = clusterMap.get(subspace);
for (Cluster<Model> cluster : clusters) {
Cluster<SubspaceModel> newCluster = new Cluster<>(cluster.getIDs());
newCluster.setModel(new SubspaceModel(subspace, Centroid.make(relation, cluster.getIDs())));
newCluster.setName("cluster_" + numClusters++);
result.addToplevelCluster(newCluster);
}
}
LOG.setCompleted(stepprog);
return result;
}
/**
* 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;
}