/**
* Run the Eclat algorithm
*
* @param db Database to process
* @param relation Bit vector relation
* @return Frequent patterns found
*/
public FrequentItemsetsResult run(Database db, final Relation<BitVector> relation) {
// TODO: implement with resizable arrays, to not need dim.
final int dim = RelationUtil.dimensionality(relation);
final VectorFieldTypeInformation<BitVector> meta = RelationUtil.assumeVectorField(relation);
// Compute absolute minsupport
final int minsupp = getMinimumSupport(relation.size());
LOG.verbose("Build 1-dimensional transaction lists.");
Duration ctime = LOG.newDuration(STAT + "eclat.transposition.time").begin();
DBIDs[] idx = buildIndex(relation, dim, minsupp);
LOG.statistics(ctime.end());
FiniteProgress prog =
LOG.isVerbose() ? new FiniteProgress("Building frequent itemsets", idx.length, LOG) : null;
Duration etime = LOG.newDuration(STAT + "eclat.extraction.time").begin();
final List<Itemset> solution = new ArrayList<>();
for (int i = 0; i < idx.length; i++) {
LOG.incrementProcessed(prog);
extractItemsets(idx, i, minsupp, solution);
}
LOG.ensureCompleted(prog);
Collections.sort(solution);
LOG.statistics(etime.end());
LOG.statistics(new LongStatistic(STAT + "frequent-itemsets", solution.size()));
return new FrequentItemsetsResult("Eclat", "eclat", solution, meta);
}
@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 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;
}
public Result run(Database database, Relation<O> rel) {
DistanceQuery<O> dq = rel.getDistanceQuery(getDistanceFunction());
int size = rel.size();
long pairs = (size * (long) size) >> 1;
final long ssize = sampling <= 1 ? (long) Math.ceil(sampling * pairs) : (long) sampling;
if (ssize > Integer.MAX_VALUE) {
throw new AbortException("Sampling size too large.");
}
final int qsize = quantile <= 0 ? 1 : (int) Math.ceil(quantile * ssize);
DoubleMaxHeap heap = new DoubleMaxHeap(qsize);
ArrayDBIDs ids = DBIDUtil.ensureArray(rel.getDBIDs());
DBIDArrayIter i1 = ids.iter(), i2 = ids.iter();
Random r = rand.getSingleThreadedRandom();
FiniteProgress prog = LOG.isVerbose() ? new FiniteProgress("Sampling", (int) ssize, LOG) : null;
for (long i = 0; i < ssize; i++) {
int x = r.nextInt(size - 1) + 1, y = r.nextInt(x);
double dist = dq.distance(i1.seek(x), i2.seek(y));
// Skip NaN, and/or zeros.
if (dist != dist || (nozeros && dist < Double.MIN_NORMAL)) {
continue;
}
heap.add(dist, qsize);
LOG.incrementProcessed(prog);
}
LOG.statistics(new DoubleStatistic(PREFIX + ".quantile", quantile));
LOG.statistics(new LongStatistic(PREFIX + ".samplesize", ssize));
LOG.statistics(new DoubleStatistic(PREFIX + ".distance", heap.peek()));
LOG.ensureCompleted(prog);
Collection<String> header = Arrays.asList(new String[] {"Distance"});
Collection<Vector> data = Arrays.asList(new Vector[] {new Vector(heap.peek())});
return new CollectionResult<Vector>("Distances sample", "distance-sample", data, header);
}
/**
* Evaluate a single clustering.
*
* @param db Database
* @param rel Data relation
* @param c Clustering
* @return Gamma index
*/
public double evaluateClustering(
Database db, Relation<? extends NumberVector> rel, Clustering<?> c) {
List<? extends Cluster<?>> clusters = c.getAllClusters();
int ignorednoise = 0, withinPairs = 0;
for (Cluster<?> cluster : clusters) {
if ((cluster.size() <= 1 || cluster.isNoise())) {
switch (noiseHandling) {
case IGNORE_NOISE:
ignorednoise += cluster.size();
continue;
case TREAT_NOISE_AS_SINGLETONS:
continue; // No concordant distances.
case MERGE_NOISE:
break; // Treat like a cluster below.
}
}
withinPairs += (cluster.size() * (cluster.size() - 1)) >>> 1;
if (withinPairs < 0) {
throw new AbortException(
"Integer overflow - clusters too large to compute pairwise distances.");
}
}
// Materialize within-cluster distances (sorted):
double[] withinDistances = computeWithinDistances(rel, clusters, withinPairs);
int[] withinTies = new int[withinDistances.length];
// Count ties within
countTies(withinDistances, withinTies);
long concordantPairs = 0, discordantPairs = 0, betweenPairs = 0;
// Step two, compute discordant distances:
for (int i = 0; i < clusters.size(); i++) {
Cluster<?> ocluster1 = clusters.get(i);
if ((ocluster1.size() <= 1 || ocluster1.isNoise()) //
&& noiseHandling.equals(NoiseHandling.IGNORE_NOISE)) {
continue;
}
for (int j = i + 1; j < clusters.size(); j++) {
Cluster<?> ocluster2 = clusters.get(j);
if ((ocluster2.size() <= 1 || ocluster2.isNoise()) //
&& noiseHandling.equals(NoiseHandling.IGNORE_NOISE)) {
continue;
}
betweenPairs += ocluster1.size() * ocluster2.size();
for (DBIDIter oit1 = ocluster1.getIDs().iter(); oit1.valid(); oit1.advance()) {
NumberVector obj = rel.get(oit1);
for (DBIDIter oit2 = ocluster2.getIDs().iter(); oit2.valid(); oit2.advance()) {
double dist = distanceFunction.distance(obj, rel.get(oit2));
int p = Arrays.binarySearch(withinDistances, dist);
if (p >= 0) { // Tied distances:
while (p > 0 && withinDistances[p - 1] >= dist) {
--p;
}
concordantPairs += p;
discordantPairs += withinDistances.length - p - withinTies[p];
continue;
}
p = -p - 1;
concordantPairs += p;
discordantPairs += withinDistances.length - p;
}
}
}
}
// Total number of pairs possible:
final long t = ((rel.size() - ignorednoise) * (long) (rel.size() - ignorednoise - 1)) >>> 1;
final long tt = (t * (t - 1)) >>> 1;
final double gamma =
(concordantPairs - discordantPairs) / (double) (concordantPairs + discordantPairs);
final double tau =
computeTau(concordantPairs, discordantPairs, tt, withinDistances.length, betweenPairs);
if (LOG.isStatistics()) {
LOG.statistics(new StringStatistic(key + ".pbm.noise-handling", noiseHandling.toString()));
if (ignorednoise > 0) {
LOG.statistics(new LongStatistic(key + ".pbm.ignored", ignorednoise));
}
LOG.statistics(new DoubleStatistic(key + ".gamma", gamma));
LOG.statistics(new DoubleStatistic(key + ".tau", tau));
}
EvaluationResult ev =
EvaluationResult.findOrCreate(
db.getHierarchy(), c, "Internal Clustering Evaluation", "internal evaluation");
MeasurementGroup g = ev.findOrCreateGroup("Concordance-based Evaluation");
g.addMeasure("Gamma", gamma, -1., 1., 0., false);
g.addMeasure("Tau", tau, -1., +1., 0., false);
db.getHierarchy().resultChanged(ev);
return gamma;
}
/**
* Evaluate a single clustering.
*
* @param db Database
* @param rel Data relation
* @param c Clustering
* @return Mean simplified silhouette
*/
public double evaluateClustering(
Database db, Relation<? extends NumberVector> rel, Clustering<?> c) {
List<? extends Cluster<?>> clusters = c.getAllClusters();
NumberVector[] centroids = new NumberVector[clusters.size()];
int ignorednoise = centroids(rel, clusters, centroids, noiseOption);
MeanVariance mssil = new MeanVariance();
Iterator<? extends Cluster<?>> ci = clusters.iterator();
for (int i = 0; ci.hasNext(); i++) {
Cluster<?> cluster = ci.next();
if (cluster.size() <= 1) {
// As suggested in Rousseeuw, we use 0 for singletons.
mssil.put(0., cluster.size());
continue;
}
if (cluster.isNoise()) {
switch (noiseOption) {
case IGNORE_NOISE:
continue; // Ignore elements
case TREAT_NOISE_AS_SINGLETONS:
// As suggested in Rousseeuw, we use 0 for singletons.
mssil.put(0., cluster.size());
continue;
case MERGE_NOISE:
break; // Treat as cluster below
}
}
// Cluster center:
final NumberVector center = centroids[i];
assert (center != null);
for (DBIDIter it = cluster.getIDs().iter(); it.valid(); it.advance()) {
NumberVector obj = rel.get(it);
// a: Distance to own centroid
double a = distance.distance(center, obj);
// b: Distance to other clusters centroids:
double min = Double.POSITIVE_INFINITY;
Iterator<? extends Cluster<?>> cj = clusters.iterator();
for (int j = 0; cj.hasNext(); j++) {
Cluster<?> ocluster = cj.next();
if (i == j) {
continue;
}
NumberVector other = centroids[j];
if (other == null) { // Noise!
switch (noiseOption) {
case IGNORE_NOISE:
continue;
case TREAT_NOISE_AS_SINGLETONS:
// Treat each object like a centroid!
for (DBIDIter it2 = ocluster.getIDs().iter(); it2.valid(); it2.advance()) {
double dist = distance.distance(rel.get(it2), obj);
min = dist < min ? dist : min;
}
continue;
case MERGE_NOISE:
break; // Treat as cluster below, but should not be reachable.
}
}
// Clusters: use centroid.
double dist = distance.distance(other, obj);
min = dist < min ? dist : min;
}
// One 'real' cluster only?
min = min < Double.POSITIVE_INFINITY ? min : a;
mssil.put((min - a) / (min > a ? min : a));
}
}
double penalty = 1.;
// Only if {@link NoiseHandling#IGNORE_NOISE}:
if (penalize && ignorednoise > 0) {
penalty = (rel.size() - ignorednoise) / (double) rel.size();
}
final double meanssil = penalty * mssil.getMean();
final double stdssil = penalty * mssil.getSampleStddev();
if (LOG.isStatistics()) {
LOG.statistics(
new StringStatistic(
key + ".simplified-silhouette.noise-handling", noiseOption.toString()));
if (ignorednoise > 0) {
LOG.statistics(new LongStatistic(key + ".simplified-silhouette.ignored", ignorednoise));
}
LOG.statistics(new DoubleStatistic(key + ".simplified-silhouette.mean", meanssil));
LOG.statistics(new DoubleStatistic(key + ".simplified-silhouette.stddev", stdssil));
}
EvaluationResult ev =
EvaluationResult.findOrCreate(
db.getHierarchy(), c, "Internal Clustering Evaluation", "internal evaluation");
MeasurementGroup g = ev.findOrCreateGroup("Distance-based Evaluation");
g.addMeasure(
"Simp. Silhouette +-" + FormatUtil.NF2.format(stdssil), meanssil, -1., 1., 0., false);
db.getHierarchy().resultChanged(ev);
return meanssil;
}
/**
* Evaluate a single clustering.
*
* @param db Database
* @param rel Data relation
* @param c Clustering
* @return C-Index
*/
public double evaluateClustering(
Database db, Relation<? extends O> rel, DistanceQuery<O> dq, Clustering<?> c) {
List<? extends Cluster<?>> clusters = c.getAllClusters();
// theta is the sum, w the number of within group distances
double theta = 0;
int w = 0;
int ignorednoise = 0;
int isize = clusters.size() <= 1 ? rel.size() : rel.size() / (clusters.size() - 1);
DoubleArray pairDists = new DoubleArray(isize);
for (int i = 0; i < clusters.size(); i++) {
Cluster<?> cluster = clusters.get(i);
if (cluster.size() <= 1 || cluster.isNoise()) {
switch (noiseOption) {
case IGNORE_NOISE:
ignorednoise += cluster.size();
continue; // Ignore
case TREAT_NOISE_AS_SINGLETONS:
continue; // No within-cluster distances!
case MERGE_NOISE:
break; // Treat like a cluster
}
}
for (DBIDIter it1 = cluster.getIDs().iter(); it1.valid(); it1.advance()) {
O obj = rel.get(it1);
// Compare object to every cluster, but only once
for (int j = i; j < clusters.size(); j++) {
Cluster<?> ocluster = clusters.get(j);
if (ocluster.size() <= 1 || ocluster.isNoise()) {
switch (noiseOption) {
case IGNORE_NOISE:
continue; // Ignore this cluster.
case TREAT_NOISE_AS_SINGLETONS:
case MERGE_NOISE:
break; // Treat like a cluster
}
}
for (DBIDIter it2 = ocluster.getIDs().iter(); it2.valid(); it2.advance()) {
if (DBIDUtil.compare(it1, it2) <= 0) { // Only once.
continue;
}
double dist = dq.distance(obj, rel.get(it2));
pairDists.add(dist);
if (ocluster == cluster) { // Within-cluster distances.
theta += dist;
w++;
}
}
}
}
}
// Simulate best and worst cases:
pairDists.sort();
double min = 0, max = 0;
for (int i = 0, j = pairDists.size() - 1; i < w; i++, j--) {
min += pairDists.get(i);
max += pairDists.get(j);
}
double cIndex = (max > min) ? (theta - min) / (max - min) : 0.;
if (LOG.isStatistics()) {
LOG.statistics(new StringStatistic(key + ".c-index.noise-handling", noiseOption.toString()));
if (ignorednoise > 0) {
LOG.statistics(new LongStatistic(key + ".c-index.ignored", ignorednoise));
}
LOG.statistics(new DoubleStatistic(key + ".c-index", cIndex));
}
EvaluationResult ev =
EvaluationResult.findOrCreate(
db.getHierarchy(), c, "Internal Clustering Evaluation", "internal evaluation");
MeasurementGroup g = ev.findOrCreateGroup("Distance-based Evaluation");
g.addMeasure("C-Index", cIndex, 0., 1., 0., true);
db.getHierarchy().resultChanged(ev);
return cIndex;
}