IMP::statistics::PartitionalClustering Class Reference

---

Detailed Description

The base class for clusterings of data sets.

Data items are represented by an index. In a partitional clustering each item can only be contained on one cluster. The mapping between data items and the information needed by the clustering algorithm is maintained by a helper object such as Embedding.

Inheritance diagram for IMP::statistics::PartitionalClustering:

[legend]

Public Member Functions
virtual const Ints &	get_cluster (unsigned int i) const =0
virtual int	get_cluster_representative (unsigned int i) const =0
virtual unsigned int	get_number_of_clusters () const =0
	PartitionalClustering (std::string name)
Friends
template<class T >
void	IMP::internal::unref (T *)

---

Member Function Documentation

virtual const Ints& IMP::statistics::PartitionalClustering::get_cluster

(

unsigned int

i

)

const [pure virtual]

Return the list of indexes in the ith cluster.

virtual int IMP::statistics::PartitionalClustering::get_cluster_representative

(

unsigned int

i

)

const [pure virtual]

Return the index of an item that "typifies" the ith cluster.

---

The documentation for this class was generated from the following files:

• PartitionalClustering.h
• statistics/__init__.py