lemur::cluster::Cluster Class Reference

Cluster representation, a vector of cluster elements. More...

#include <Cluster.hpp>

Inheritance diagram for lemur::cluster::Cluster:

List of all members.


Public Member Functions
	Cluster (int cid, const lemur::api::Index &ind, const SimilarityMethod &sim)
	create empty cluster with specific id.
virtual	~Cluster ()
	delete cluster
void	setId (int cid)
	set cluster id.
void	setName (const string &newName)
	set cluster symbolic name.
int	getId () const
	get cluster id.
const string &	getName () const
	get cluster symbolic name.
const vector< ClusterElt > *	getIds () const
	get vector of elements in this cluster.
vector< lemur::api::DOCID_T >	getDocIds () const
	get vector of doc ids in this cluster.
virtual ClusterRep *	getClusterRep () const =0
	Get the ClusterRep for this Cluster for scoring. The Rep will have been weighted by the SimilarityMethod. Caller responsible for deleting.
virtual double	score (const ClusterRep *rep) const =0
	score a document against this cluster, given the rep.
virtual void	add (const ClusterElt &elt)
	add the element to this cluster
virtual void	add (const vector< lemur::api::DOCID_T > docids)
	Add a list of documents to a cluster.
virtual void	remove (const ClusterElt &elt)
	remove the element from this cluster
virtual vector< Cluster * >	split (int numParts=2)
	Split this cluster into subclusters.
virtual void	merge (const Cluster *c)
	merge in a cluster
virtual bool	read (ifstream &in)
	read a cluster in from the cluster db file.
virtual void	write (ofstream &out)
	write a cluster to the cluster db file.
void	print () const
	pretty print to stdout.
int	getSize () const
	How many elements.
virtual double	sum2 () const
	Sum of squared values in the cluster's term vector.
virtual string	getKeyWords (int numTerms=10) const
	Return the top numTerms terms in the cluster (tf.idf scores).
Protected Attributes
int	id
	internal id
string	name
	external symbolic name.
vector< ClusterElt >	ids
	vector of cluster elements in this cluster.
const SimilarityMethod &	similarity
	The SimilarityMethod to use for weighting.
int	size
	size of the cluster
double	weight
const lemur::api::Index &	ind
fstream *	datFile
long	offset

Detailed Description

Cluster representation, a vector of cluster elements.

Constructor & Destructor Documentation

lemur::cluster::Cluster::Cluster ( int cid,

const lemur::api::Index & ind,

const SimilarityMethod & sim

)

create empty cluster with specific id.

lemur::cluster::Cluster::~Cluster ( ) [virtual]

delete cluster

Member Function Documentation

void lemur::cluster::Cluster::add ( const vector< lemur::api::DOCID_T > docids ) [virtual]

Add a list of documents to a cluster.

Reimplemented in lemur::cluster::CentroidCluster.

void lemur::cluster::Cluster::add ( const ClusterElt & elt ) [virtual]

add the element to this cluster

Reimplemented in lemur::cluster::CentroidCluster.

virtual ClusterRep* lemur::cluster::Cluster::getClusterRep ( ) const [pure virtual]

Get the ClusterRep for this Cluster for scoring. The Rep will have been weighted by the SimilarityMethod. Caller responsible for deleting.

Implemented in lemur::cluster::AgglomCluster, and lemur::cluster::CentroidCluster.

vector< DOCID_T > lemur::cluster::Cluster::getDocIds ( ) const

get vector of doc ids in this cluster.

int lemur::cluster::Cluster::getId ( ) const

get cluster id.

const vector< lemur::cluster::ClusterElt > * lemur::cluster::Cluster::getIds ( ) const

get vector of elements in this cluster.

string lemur::cluster::Cluster::getKeyWords ( int numTerms = 10 ) const [virtual]

Return the top numTerms terms in the cluster (tf.idf scores).

const string & lemur::cluster::Cluster::getName ( ) const

get cluster symbolic name.

int lemur::cluster::Cluster::getSize ( ) const [inline]

How many elements.

void lemur::cluster::Cluster::merge ( const Cluster * c ) [virtual]

merge in a cluster

void lemur::cluster::Cluster::print ( ) const

pretty print to stdout.

bool lemur::cluster::Cluster::read ( ifstream & in ) [virtual]

read a cluster in from the cluster db file.

Reimplemented in lemur::cluster::CentroidCluster.

void lemur::cluster::Cluster::remove ( const ClusterElt & elt ) [virtual]

remove the element from this cluster

Reimplemented in lemur::cluster::CentroidCluster.

virtual double lemur::cluster::Cluster::score ( const ClusterRep * rep ) const [pure virtual]

score a document against this cluster, given the rep.

Implemented in lemur::cluster::AgglomCluster, and lemur::cluster::CentroidCluster.

void lemur::cluster::Cluster::setId ( int cid )

set cluster id.

void lemur::cluster::Cluster::setName ( const string & newName )

set cluster symbolic name.

vector< lemur::cluster::Cluster * > lemur::cluster::Cluster::split ( int numParts = 2 ) [virtual]

Split this cluster into subclusters.

virtual double lemur::cluster::Cluster::sum2 ( ) const [inline, virtual]

Sum of squared values in the cluster's term vector.

Reimplemented in lemur::cluster::AgglomCluster, and lemur::cluster::CentroidCluster.