MAP strategy for classification. More...

#include <MAP.h>

Classes
class	Parameters
	Classifier Parameters. More...

Public Member Functions
bool	classify (const InputAdaptor< double > &input, const std::vector< unsigned int > &attributesIndices, const std::vector< double > &inputNoDataValues, OutputAdaptor< unsigned int > &output, const unsigned int outputIndex, const double outputNoDataValue, const bool enableProgressInterface) throw (te::cl::Exception)
	Classify an input iterated data and save the result on the output iterated data. More...

bool	initialize (const Parameters &params) throw (te::cl::Exception)
	Initialize this classifier instance with new parameters. More...

	MAP ()

bool	train (const InputAdaptor< double > &samples, const std::vector< unsigned int > &attributesIndices, const std::vector< unsigned int > &sampleLabels, const bool enableProgressInterface) throw (te::cl::Exception)
	Train this classifier instance using the initialization parameters and the suppied train data. More...

	~MAP ()

Protected Member Functions
bool	getPrioriProbabilities (const InputAdaptor< double > &input, const std::vector< unsigned int > &attributesIndices, std::vector< double > &prioriProbs) const
	Calculate priori probabilities by pre-classifying the input data. More...

void	reset ()
	Reset this instance to its initial state. More...

Protected Attributes
std::vector< boost::numeric::ublas::matrix< double > >	m_classesCovarianceInvMatrixes
	Classes covariance inverse matrixes. More...

std::vector< boost::numeric::ublas::matrix< double > >	m_classesCovarianceMatrixes
	Classes covariance matrixes. More...

std::vector< std::vector< double > >	m_classesMeans
	Classes means;. More...

std::vector< double >	m_classesOptizedMAPDiscriminantTerm
	An optimized portion of the MAP discriminant function. More...

std::vector< unsigned int >	m_classLabels
	class labels More...

bool	m_isInitialized
	True if this instance is initialized. More...

Parameters	m_parameters
	Internal execution parameters. More...

Detailed Description

MAP strategy for classification.

Definition at line 54 of file MAP.h.

Constructor & Destructor Documentation

te::cl::MAP::MAP ( )

Definition at line 67 of file MAP.cpp.

References te::cl::MAP::Parameters::reset(), and ~MAP().

te::cl::MAP::~MAP ( )

default

Referenced by MAP().

Member Function Documentation

bool te::cl::MAP::classify	(	const InputAdaptor< double > &	input,
		const std::vector< unsigned int > &	attributesIndices,
		const std::vector< double > &	inputNoDataValues,
		OutputAdaptor< unsigned int > &	output,
		const unsigned int	outputIndex,
		const double	outputNoDataValue,
		const bool	enableProgressInterface
	)
throw	(	te::cl::Exception
	)

Classify an input iterated data and save the result on the output iterated data.

Parameters

input	Input data to be classified.
attributesIndices	The attributes indexes to processe from the iterated train data.
inputNoDataValues	A vector of no-data values for each attribute dimension or an empty vector if no-data values are not used.
output	Output classified data.
outputIndex	The output attribute index.
outputNoDataValue	A output label value to use when dealing with input no-data.
enableProgressInterface	Enable/disable the use of a proress interfece.

Definition at line 346 of file MAP.cpp.

References te::cl::InputAdaptor< DataType >::getElementsCount(), te::cl::OutputAdaptor< DataType >::getElementsCount(), te::cl::InputAdaptor< DataType >::getFeature(), te::cl::InputAdaptor< DataType >::getFeaturesCount(), te::cl::OutputAdaptor< DataType >::getFeaturesCount(), getPrioriProbabilities(), m_classesCovarianceInvMatrixes, m_classesCovarianceMatrixes, m_classesMeans, m_classesOptizedMAPDiscriminantTerm, m_classLabels, m_isInitialized, m_parameters, te::cl::MAP::Parameters::m_prioriProbs, and te::cl::OutputAdaptor< DataType >::setFeature().

Referenced by BOOST_AUTO_TEST_SUITE(), and te::rp::ClassifierMAPStrategy::execute().

bool te::cl::MAP::getPrioriProbabilities	(	const InputAdaptor< double > &	input,
		const std::vector< unsigned int > &	attributesIndices,
		std::vector< double > &	prioriProbs
	)		const

protected

Calculate priori probabilities by pre-classifying the input data.

Parameters

input	Input data to be classified.
attributesIndices	The attributes indexes to processe from the iterated train data.
prioriProbs	Calculated priori-probabilities.

Definition at line 477 of file MAP.cpp.

References te::cl::InputAdaptor< DataType >::getElementsCount(), te::cl::InputAdaptor< DataType >::getFeature(), te::cl::InputAdaptor< DataType >::getFeaturesCount(), m_classesCovarianceInvMatrixes, m_classesMeans, m_classesOptizedMAPDiscriminantTerm, m_parameters, and te::cl::MAP::Parameters::m_prioriCalcSampleStep.

Referenced by classify().

bool te::cl::MAP::initialize	(	const Parameters &	params	)
throw	(	te::cl::Exception
	)

Initialize this classifier instance with new parameters.

Parameters

params New initialization parameters.

Definition at line 74 of file MAP.cpp.

References m_isInitialized, m_parameters, and te::cl::MAP::Parameters::reset().

Referenced by BOOST_AUTO_TEST_SUITE(), and te::rp::ClassifierMAPStrategy::initialize().

void te::cl::MAP::reset ( )

protected

Reset this instance to its initial state.

Definition at line 115 of file MAP.cpp.

References m_classesCovarianceInvMatrixes, m_classesCovarianceMatrixes, m_classesMeans, m_classesOptizedMAPDiscriminantTerm, m_classLabels, m_isInitialized, m_parameters, and te::cl::MAP::Parameters::reset().

bool te::cl::MAP::train	(	const InputAdaptor< double > &	samples,
		const std::vector< unsigned int > &	attributesIndices,
		const std::vector< unsigned int > &	sampleLabels,
		const bool	enableProgressInterface
	)
throw	(	te::cl::Exception
	)

Train this classifier instance using the initialization parameters and the suppied train data.

Parameters

samples	Train data samples.
attributesIndices	The attributes indexes to processe from the iterated train data.
sampleLabels	The sample lables for each iterated train data element.
enableProgressInterface	Enable/disable the use of a proress interfece.

Definition at line 126 of file MAP.cpp.

References te::common::GetDeterminant(), te::common::GetInverseMatrix(), m_classesCovarianceInvMatrixes, m_classesCovarianceMatrixes, m_classesMeans, m_classesOptizedMAPDiscriminantTerm, m_classLabels, m_isInitialized, m_parameters, and te::cl::MAP::Parameters::m_prioriProbs.

Referenced by BOOST_AUTO_TEST_SUITE(), and te::rp::ClassifierMAPStrategy::initialize().