com.chemaxon.clustering.common

Interface HierarchicClustering<T,C extends HierarchicCluster<T>>

Type Parameters:

C - Type of clusters represented

T - Type of items contained by the clusters

Please note that this interface is marked with @Beta annotation, so it can be subject of incompatible changes or removal in later releases.

All Known Subinterfaces:

IDBasedHierarchicClustering

@Beta
 @PublicAPI
public interface HierarchicClustering<T,C extends HierarchicCluster<T>>

A grouping of structures into disjunct hierarchical groups.

Instances of this interface represent unbalanced multifurcating trees.

Nested Class Summary

Nested Classes

Modifier and Type	Interface and Description
static class	HierarchicClustering.Alignment Level interpretation.

Method Summary

Modifier and Type	Method and Description
Optional<C>	clusterOf(T item) Identify the lowest level cluster containing the given item.
LevelAssigner<T,C>	getPreferredAssigner() Preferred assigner.
int	maxHeight() Maximal height of the clustering.
HierarchicClustering.Alignment	preferredAlignment() Preferred alignment of the represented clustering.
List<C>	roots() Highest level cluster(s).
LevelAssigner<T,C>	unitPathAssigner() Assigner which consider parent-child edges as unit length.

Method Detail

roots

List<C> roots()

Highest level cluster(s).

Returns:

List of highest level clusters. The returned list contains at least one element.

clusterOf

Optional<C> clusterOf(T item)

Identify the lowest level cluster containing the given item.

Parameters:

item - Item to look up.

Returns:

The lowest level cluster containing the given element. This cluster contains the given item as a leaf.

preferredAlignment

HierarchicClustering.Alignment preferredAlignment()

Preferred alignment of the represented clustering.

Returns:

Preferred alignment

unitPathAssigner

LevelAssigner<T,C> unitPathAssigner()

Assigner which consider parent-child edges as unit length.

Returns:

The unit path assigner.

getPreferredAssigner

LevelAssigner<T,C> getPreferredAssigner()

Preferred assigner.

Some clustering algorithms may assign meaningful levels for clusters/leaves. If no such assignment s done the implementations should fall back the unit path assigner.

Returns:

The preferred assigner

maxHeight

int maxHeight()

Maximal height of the clustering.

Returns:

Maximum of HierarchicCluster.height() of roots()