lti::unsupervisedClassifier Class Reference

Abstract class, parent of all unsupervised classifiers. More...

#include <ltiUnsupervisedClassifier.h>

Inheritance diagram for lti::unsupervisedClassifier:

[legend]

Collaboration diagram for lti::unsupervisedClassifier:

[legend]

List of all members.

Classes
class	parameters
	the parameters for the class unsupervisedClassifier are the same as for classifier, except that the default value of mulipleMode is changed to outputTemplate::Ignore. More...
Public Member Functions
	unsupervisedClassifier ()
	unsupervisedClassifier (const unsupervisedClassifier &other)
virtual const char *	getTypeName () const
unsupervisedClassifier &	copy (const unsupervisedClassifier &other)
const parameters &	getParameters () const
virtual bool	train (const dmatrix &input)=0
virtual bool	train (const dmatrix &input, ivector &ids)
virtual bool	classify (const dvector &feature, outputVector &result) const =0
Protected Member Functions
bool	selectRandomPoints (const dmatrix &data, int numberOfPoints, dmatrix &randomPoints)

---

Detailed Description

Abstract class, parent of all unsupervised classifiers.

This class defines the interface for all unsupervised train methods.

---

Constructor & Destructor Documentation

lti::unsupervisedClassifier::unsupervisedClassifier

(

)

default constructor

lti::unsupervisedClassifier::unsupervisedClassifier

(

const unsupervisedClassifier &

other

)

copy constructor

Parameters:

other

the object to be copied

---

Member Function Documentation

virtual bool lti::unsupervisedClassifier::classify	(	const dvector &	feature,
		outputVector &	result
	)			const [pure virtual]

Classification.

Classifies the feature and returns the outputVector with the classification result.

Parameters:

	feature	the vector to be classified
	result	the result of the classification

Returns:

false if an error occurred during classification else true

Implemented in lti::centroidClustering, lti::DBScan< T >, lti::MSTClustering< U >, lti::SOFM, and lti::SOFM2D.

unsupervisedClassifier& lti::unsupervisedClassifier::copy

(

const unsupervisedClassifier &

other

)

copy data of "other" functor.

Parameters:

other

the functor to be copied

Returns:

a reference to this functor object

Reimplemented from lti::classifier.

Reimplemented in lti::adaptiveKMeans, lti::centroidClustering, lti::clustering, lti::competitiveAgglomeration, lti::DBScan< T >, lti::fuzzyCMeans, lti::kMeansClustering, lti::MSTClustering< U >, lti::SOFM, and lti::SOFM2D.

const parameters& lti::unsupervisedClassifier::getParameters

(

)

const

returns used parameters

Reimplemented from lti::classifier.

Reimplemented in lti::adaptiveKMeans, lti::centroidClustering, lti::clustering, lti::competitiveAgglomeration, lti::DBScan< T >, lti::fuzzyCMeans, lti::kMeansClustering, lti::MSTClustering< U >, lti::SOFM, and lti::SOFM2D.

virtual const char* lti::unsupervisedClassifier::getTypeName

(

)

const [virtual]

returns the name of this type ("unsupervisedClassifier")

Reimplemented from lti::classifier.

Reimplemented in lti::adaptiveKMeans, lti::centroidClustering, lti::clustering, lti::competitiveAgglomeration, lti::DBScan< T >, lti::fuzzyCMeans, lti::kMeansClustering, lti::MSTClustering< U >, lti::SOFM, and lti::SOFM2D.

bool lti::unsupervisedClassifier::selectRandomPoints	(	const dmatrix &	data,
		int	numberOfPoints,
		dmatrix &	randomPoints
	)			[protected]

Randomly selects numberOfPoints points (rows) from the data matrix.

If nubmerOfPoints is greater than the number of points in data, points will be multiply selected.

Parameters:

	data	contains points to select from in rows
	numberOfPoints	number of points expected as result
	randomPoints	the points randomly selected from data

Returns:

false if something went wrong, else true

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

Unsupervised training.

The vectors in the input matrix will be put into groups according to the training algorithm. Additionally, an integer indicating the class each point belongs to is returned.

By default this method uses the other train method (see train(const dmatrix&)) and then calls classifier::classify(const dvector&) to get the ids for each train-vector. These ids are then returned.

Parameters:

	input	the matrix with the input vectors (each row is a training vector)
	ids	vector of class ids for each input point

Returns:

true if successful, false otherwise. (if false you can check the error message with getStatusString())

Reimplemented in lti::adaptiveKMeans, lti::centroidClustering, lti::clustering, lti::competitiveAgglomeration, lti::DBScan< T >, lti::fuzzyCMeans, lti::kMeansClustering, lti::MSTClustering< U >, lti::SOFM, and lti::SOFM2D.

virtual bool lti::unsupervisedClassifier::train

(

const dmatrix &

input

)

[pure virtual]

Unsupervised training.

The vectors in the input matrix will be clustered using each specific method.

Parameters:

input

the matrix with the input vectors (each row is a training vector)

Returns:

true if successful, false otherwise. (if false you can check the error message with getStatusString())

Implemented in lti::adaptiveKMeans, lti::centroidClustering, lti::clustering, lti::competitiveAgglomeration, lti::DBScan< T >, lti::fuzzyCMeans, lti::kMeansClustering, lti::MSTClustering< U >, lti::SOFM, and lti::SOFM2D.

---

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

• ltiUnsupervisedClassifier.h