latest version v1.9 - last update 24 Nov 2005

lti::clustering Class Reference

Base class for all clustering algorithms. More...

#include <ltiClustering.h>

Inheritance diagram for lti::clustering:

[legend]Collaboration diagram for lti::clustering:

[legend]List of all members.

Public Member Functions
	clustering ()
	clustering (const clustering &other)
virtual	~clustering ()
virtual const char *	getTypeName () const
clustering &	copy (const clustering &other)
const parameters &	getParameters () const
virtual bool	train (const dmatrix &input)=0
virtual bool	train (const dmatrix &input, ivector &ids)
Classes
class	parameters
	parameters for clustering functors. More...

---

Detailed Description

Base class for all clustering algorithms.

Clustering algorithms can follow different training strategies as indicated by the parameter clusterMode. Representations of the clusters are modelled in subclasses of this class, e.g. centroidClustering.

---

Constructor & Destructor Documentation

lti::clustering::clustering (   )

default constructor

lti::clustering::clustering (  const clustering &  other  )

copy constructor Parameters: other  the object to be copied

virtual lti::clustering::~clustering (   )  [virtual]

destructor

---

Member Function Documentation

clustering& lti::clustering::copy (  const clustering &  other  )

copy data of "other" functor. Parameters: other  the functor to be copied Returns: a reference to this functor object

const parameters& lti::clustering::getParameters (   )  const

returns current parameters. Reimplemented from lti::unsupervisedClassifier. Reimplemented in lti::adaptiveKMeans, lti::centroidClustering, lti::competitiveAgglomeration, lti::DBScan< T >, lti::fuzzyCMeans, lti::kMeansClustering, and lti::MSTClustering< U >.

virtual const char* lti::clustering::getTypeName (   )  const [virtual]

returns the name of this type ("clustering") Reimplemented from lti::unsupervisedClassifier. Reimplemented in lti::adaptiveKMeans, lti::centroidClustering, lti::competitiveAgglomeration, lti::DBScan< T >, lti::fuzzyCMeans, lti::kMeansClustering, and lti::MSTClustering< U >.

virtual bool lti::clustering::train (  const dmatrix &  input, ivector &  ids )  [virtual]

train the clusterer with the vectors at the rows of input, and return the cluster id for each of that vectors. Parameters: input  the input data ids  output vector where the cluster id per input vector will be stored. Returns: true if successful, false otherwise. Reimplemented from lti::unsupervisedClassifier. Reimplemented in lti::adaptiveKMeans, lti::centroidClustering, lti::competitiveAgglomeration, lti::DBScan< T >, lti::fuzzyCMeans, lti::kMeansClustering, and lti::MSTClustering< U >.

virtual bool lti::clustering::train (  const dmatrix &  input  )  [pure virtual]

train the clusterer with the vectors at the rows of input Parameters: input  the input data Returns: true if successful, false otherwise. Implements lti::unsupervisedClassifier. Implemented in lti::adaptiveKMeans, lti::centroidClustering, lti::competitiveAgglomeration, lti::DBScan< T >, lti::fuzzyCMeans, lti::kMeansClustering, and lti::MSTClustering< U >.

---

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

• ltiClustering.h

---