latest version v1.9 - last update 24 Nov 2005

lti::crossValidator Class Reference

This class does a cross validation on the given dataset and returns the average recognition rates. More...

#include <ltiCrossValidator.h>

Inheritance diagram for lti::crossValidator:

[legend]Collaboration diagram for lti::crossValidator:

[legend]List of all members.

Public Member Functions
	crossValidator ()
	crossValidator (const crossValidator &other)
virtual	~crossValidator ()
virtual const char *	getTypeName () const
double	apply (const dmatrix &data, const ivector &ids) const
bool	apply (const dmatrix &data, const ivector &ids, double &avRecogRate) const
crossValidator &	copy (const crossValidator &other)
crossValidator &	operator= (const crossValidator &other)
virtual functor *	clone () const
const parameters &	getParameters () const
Protected Member Functions
bool	splitData (const dmatrix &data, std::list< ivector > &splittedData) const
Classes
class	parameters
	the parameters for the class crossValidator More...

---

Detailed Description

This class does a cross validation on the given dataset and returns the average recognition rates.

It divides the data at random in nbOfSplits distinct segments. Then the network is trained with nbOfSplits-1 of the segments. Then each data point of the remaining segment is classified. This process is repeated for every possible choice of the the segment which is omited from the classification process. The classifier that is used for validation is expected to delete old results from previous trainings, because the classifier is trained with different training data set during validation.

---

Constructor & Destructor Documentation

lti::crossValidator::crossValidator (   )

default constructor

lti::crossValidator::crossValidator (  const crossValidator &  other  )

copy constructor Parameters: other  the object to be copied

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

destructor

---

Member Function Documentation

bool lti::crossValidator::apply (  const dmatrix &  data, const ivector &  ids, double &  avRecogRate )  const

Computes the average the average recognition rate of the given data using the specified classifier. Parameters: data  dmatrix with the source data. ids  ivector with the ids of each data point in data. avRecogRate  the average recognition rate Returns: true if apply successful or false otherwise.

double lti::crossValidator::apply (  const dmatrix &  data, const ivector &  ids )  const

Computes the average the average recognition rate of the given data using the specified classifier. Parameters: data  dmatrix with the source data. ids  ivector with the ids of each data point in data. Returns: the average recogntion rate

virtual functor* lti::crossValidator::clone (   )  const [virtual]

returns a pointer to a clone of this functor. Implements lti::functor.

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

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

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

returns used parameters Reimplemented from lti::functor.

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

returns the name of this type ("crossValidator") Reimplemented from lti::functor.

crossValidator& lti::crossValidator::operator= (  const crossValidator &  other  )

alias for copy member Parameters: other  the functor to be copied Returns: a reference to this functor object

bool lti::crossValidator::splitData (  const dmatrix &  data, std::list< ivector > &  splittedData )  const [protected]

Splits the given data into parts. The points are randomly drawn from the the src data.

---

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

• ltiCrossValidator.h

---