lti::dunnIndex Class Reference

computes the Dunn Index and its generalisations described in Bezdek, J.C.,Pal,N.R., 1998. More...

#include <ltiClusteringValidity.h>

Inheritance diagram for lti::dunnIndex:

[legend]

Collaboration diagram for lti::dunnIndex:

[legend]

List of all members.

Public Member Functions
	dunnIndex ()
	dunnIndex (const dunnIndex &other)
virtual	~dunnIndex ()
virtual const char *	getTypeName () const
virtual bool	apply (const std::vector< dmatrix > &clusteredData, double &index, const dmatrix &centroids) const
const parameters &	getParameters () const
dunnIndex &	copy (const dunnIndex &other)
virtual functor *	clone () const
dunnIndex &	operator= (const dunnIndex &other)

---

Detailed Description

computes the Dunn Index and its generalisations described in Bezdek, J.C.,Pal,N.R., 1998.

"Some new indexes of cluster validity." IEEE Transaction on Systems,Man, and cybernetics (Part B) 28, 301-315 the distance and diameter functions are implemented in the parent class so they can be used for other computations of validity indexes.

To find the best possible clustering look for the maximum value of this indices

Valid values for the measure of the diameters are: standard: the largest distance between to points in a cluster average: the average distance between all points in the cluster centroid: twice the average distance between each point and the centroid

valid values for the distance measure are minimum: the minimal distance between the points in the two clusters maximum: the maximum distance between the points in the two clusters mean: the average distance between all points in the clusters centroids: the distance between the centroids of the clusters interpoint: combination of mean and centroids

---

Constructor & Destructor Documentation

lti::dunnIndex::dunnIndex

(

)

standard contructor

lti::dunnIndex::dunnIndex

(

const dunnIndex &

other

)

standard contructor

virtual lti::dunnIndex::~dunnIndex

(

)

[virtual]

destructor

---

Member Function Documentation

virtual bool lti::dunnIndex::apply	(	const std::vector< dmatrix > &	clusteredData,
		double &	index,
		const dmatrix &	centroids
	)			const [virtual]

calculates the Dunn Index of the clustered Data

Parameters:

	clusteredData	std::vector<dmatrix> with the source data.
	index	the clustering validity result
	centroids	dmatrix with each row representing a centroid of the corresponding distribution in clusteredData

Returns:

true if apply successful or false otherwise.

Implements lti::clusteringValidity.

virtual functor* lti::dunnIndex::clone

(

)

const [virtual]

returns a pointer to a clone of this functor.

Implements lti::functor.

dunnIndex& lti::dunnIndex::copy

(

const dunnIndex &

other

)

copy data of "other" functor.

Parameters:

other

the functor to be copied

Returns:

a reference to this functor object

Reimplemented from lti::clusteringValidity.

const parameters& lti::dunnIndex::getParameters

(

)

const

returns current parameters.

Reimplemented from lti::functor.

virtual const char* lti::dunnIndex::getTypeName

(

)

const [virtual]

returns the name of this type

Reimplemented from lti::clusteringValidity.

dunnIndex& lti::dunnIndex::operator=

(

const dunnIndex &

other

)

alias for copy member

Parameters:

other

the functor to be copied

Returns:

a reference to this functor object

Reimplemented from lti::clusteringValidity.

---

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

• ltiClusteringValidity.h