The KDEModel provides an abstraction for the KDE class, abstracting away the KernelType and TreeType parameters and allowing those to be specified at runtime. More...

Public Types
enum	KernelTypes { GAUSSIAN_KERNEL , EPANECHNIKOV_KERNEL , LAPLACIAN_KERNEL , SPHERICAL_KERNEL , TRIANGULAR_KERNEL }

enum	TreeTypes { KD_TREE , BALL_TREE , COVER_TREE , OCTREE , R_TREE }

Public Member Functions
	KDEModel (const double bandwidth=1.0, const double relError=KDEDefaultParams::relError, const double absError=KDEDefaultParams::absError, const KernelTypes kernelType=KernelTypes::GAUSSIAN_KERNEL, const TreeTypes treeType=TreeTypes::KD_TREE, const bool monteCarlo=KDEDefaultParams::mode, const double mcProb=KDEDefaultParams::mcProb, const size_t initialSampleSize=KDEDefaultParams::initialSampleSize, const double mcEntryCoef=KDEDefaultParams::mcEntryCoef, const double mcBreakCoef=KDEDefaultParams::mcBreakCoef)
	Initialize KDEModel. More...

	KDEModel (const KDEModel &other)
	Copy constructor of the given model. More...

	KDEModel (KDEModel &&other)
	Move constructor of the given model. Takes ownership of the model. More...

	~KDEModel ()
	Destroy the KDEModel object. More...

double	AbsoluteError () const
	Get the absolute error tolerance. More...

void	AbsoluteError (const double newAbsError)
	Modify the absolute error tolerance. More...

double	Bandwidth () const
	Get the bandwidth of the kernel. More...

void	Bandwidth (const double newBandwidth)
	Modify the bandwidth of the kernel. More...

void	BuildModel (util::Timers &timers, arma::mat &&referenceSet)
	Build the KDE model with the given parameters and then trains it with the given reference data. More...

void	Evaluate (util::Timers &timers, arma::mat &&querySet, arma::vec &estimations)
	Perform kernel density estimation on the given query set. More...

void	Evaluate (util::Timers &timers, arma::vec &estimations)
	Perform kernel density estimation on the reference set. More...

void	InitializeModel ()
	Initialize the KDE model. More...

KernelTypes	KernelType () const
	Get the kernel type of the model. More...

KernelTypes &	KernelType ()
	Modify the kernel type of the model. More...

double	MCBreakCoefficient () const
	Get Monte Carlo break coefficient. More...

void	MCBreakCoefficient (const double newBreakCoef)
	Modify Monte Carlo break coefficient. More...

double	MCEntryCoefficient () const
	Get Monte Carlo entry coefficient. More...

void	MCEntryCoefficient (const double newEntryCoef)
	Modify Monte Carlo entry coefficient. More...

size_t	MCInitialSampleSize () const
	Get the initial sample size for Monte Carlo estimations. More...

void	MCInitialSampleSize (const size_t newSampleSize)
	Modify the initial sample size for Monte Carlo estimations. More...

double	MCProbability () const
	Get Monte Carlo probability of error being bounded by relative error. More...

void	MCProbability (const double newMCProb)
	Modify Monte Carlo probability of error being bounded by relative error. More...

KDEMode	Mode () const
	Get the mode of the model. More...

KDEMode &	Mode ()
	Modify the mode of the model. More...

bool	MonteCarlo () const
	Get whether the model is using Monte Carlo estimations or not. More...

void	MonteCarlo (const bool newMonteCarlo)
	Modify whether the model is using Monte Carlo estimations or not. More...

KDEModel &	operator= (const KDEModel &other)
	Copy the given model. More...

KDEModel &	operator= (KDEModel &&other)
	Take ownership of the contents of the given model. More...

double	RelativeError () const
	Get the relative error tolerance. More...

void	RelativeError (const double newRelError)
	Modify the relative error tolerance. More...

template < typename Archive >
void	serialize (Archive &ar, const uint32_t version)
	Serialize the KDE model. More...

TreeTypes	TreeType () const
	Get the tree type of the model. More...

TreeTypes &	TreeType ()
	Modify the tree type of the model. More...

Detailed Description

The KDEModel provides an abstraction for the KDE class, abstracting away the KernelType and TreeType parameters and allowing those to be specified at runtime.

This class is written for the sake of the kde binding, but it is not necessarily restricted to that usage.

Definition at line 231 of file kde_model.hpp.

Member Enumeration Documentation

◆ KernelTypes

enum KernelTypes

Enumerator
GAUSSIAN_KERNEL
EPANECHNIKOV_KERNEL
LAPLACIAN_KERNEL
SPHERICAL_KERNEL
TRIANGULAR_KERNEL

Definition at line 243 of file kde_model.hpp.

◆ TreeTypes

enum TreeTypes

Enumerator
KD_TREE
BALL_TREE
COVER_TREE
OCTREE
R_TREE

Definition at line 234 of file kde_model.hpp.

Constructor & Destructor Documentation

◆ KDEModel() [1/3]

KDEModel	(	const double	bandwidth = `1.0`,
		const double	relError = `KDEDefaultParams::relError`,
		const double	absError = `KDEDefaultParams::absError`,
		const KernelTypes	kernelType = `KernelTypes::GAUSSIAN_KERNEL`,
		const TreeTypes	treeType = `TreeTypes::KD_TREE`,
		const bool	monteCarlo = `KDEDefaultParams::mode`,
		const double	mcProb = `KDEDefaultParams::mcProb`,
		const size_t	initialSampleSize = `KDEDefaultParams::initialSampleSize`,
		const double	mcEntryCoef = `KDEDefaultParams::mcEntryCoef`,
		const double	mcBreakCoef = `KDEDefaultParams::mcBreakCoef`
	)

Initialize KDEModel.

Parameters

bandwidth	Bandwidth to use for the kernel.
relError	Maximum relative error tolerance for each point in the model. For example, 0.05 means that each value must be within 5% of the true KDE value.
absError	Maximum absolute error tolerance for each point in the model. For example, 0.1 means that for each point the value can have a maximum error of 0.1 units.
kernelType	Type of kernel to use.
treeType	Type of tree to use.
monteCarlo	Whether to use Monte Carlo estimations when possible.
mcProb	of a Monte Carlo estimation to be bounded by relative error tolerance.
initialSampleSize	Initial sample size for Monte Carlo estimations.
mcEntryCoef	Coefficient to control how much larger does the amount of node descendants has to be compared to the initial sample size in order for it to be a candidate for Monte Carlo estimations.
mcBreakCoef	Coefficient to control what fraction of the node's descendants evaluated is the limit before Monte Carlo estimation recurses.

◆ KDEModel() [2/3]

KDEModel ( const KDEModel & other )

Copy constructor of the given model.

◆ KDEModel() [3/3]

KDEModel ( KDEModel && other )

Move constructor of the given model. Takes ownership of the model.

◆ ~KDEModel()

~KDEModel ( )

Destroy the KDEModel object.

Member Function Documentation

◆ AbsoluteError() [1/2]

double AbsoluteError ( ) const

inline

Get the absolute error tolerance.

Definition at line 366 of file kde_model.hpp.

◆ AbsoluteError() [2/2]

void AbsoluteError ( const double newAbsError )

Modify the absolute error tolerance.

◆ Bandwidth() [1/2]

double Bandwidth ( ) const

inline

Get the bandwidth of the kernel.

Definition at line 354 of file kde_model.hpp.

◆ Bandwidth() [2/2]

void Bandwidth ( const double newBandwidth )

Modify the bandwidth of the kernel.

◆ BuildModel()

void BuildModel	(	util::Timers &	timers,
		arma::mat &&	referenceSet
	)

Build the KDE model with the given parameters and then trains it with the given reference data.

Takes possession of the reference set to avoid a copy, so the reference set will not be usable after this.

Parameters

timers	Object to hold timing information in.
referenceSet	Set of reference points.

◆ Evaluate() [1/2]

void Evaluate	(	util::Timers &	timers,
		arma::mat &&	querySet,
		arma::vec &	estimations
	)

Perform kernel density estimation on the given query set.

Takes possession of the query set to avoid a copy, so the query set will not be usable after this. If possible, it returns normalized estimations.

Precondition: The model has to be previously created with BuildModel.

Parameters

timers	Object to hold timing information in.
querySet	Set of query points.
estimations	Vector where the results will be stored in the same order as the query points.

◆ Evaluate() [2/2]

void Evaluate	(	util::Timers &	timers,
		arma::vec &	estimations
	)

Perform kernel density estimation on the reference set.

If possible, it returns normalized estimations.

Precondition: The model has to be previously created with BuildModel.

Parameters

timers	Object to hold timing information in.
estimations	Vector where the results will be stored in the same order as the query points.

◆ InitializeModel()

void InitializeModel ( )

Initialize the KDE model.

◆ KernelType() [1/2]

KernelTypes KernelType ( ) const

inline

Get the kernel type of the model.

Definition at line 378 of file kde_model.hpp.

◆ KernelType() [2/2]

KernelTypes& KernelType ( )

inline

Modify the kernel type of the model.

Definition at line 381 of file kde_model.hpp.

◆ MCBreakCoefficient() [1/2]

double MCBreakCoefficient ( ) const

inline

Get Monte Carlo break coefficient.

Definition at line 408 of file kde_model.hpp.

◆ MCBreakCoefficient() [2/2]

void MCBreakCoefficient ( const double newBreakCoef )

Modify Monte Carlo break coefficient.

◆ MCEntryCoefficient() [1/2]

double MCEntryCoefficient ( ) const

inline

Get Monte Carlo entry coefficient.

Definition at line 402 of file kde_model.hpp.

◆ MCEntryCoefficient() [2/2]

void MCEntryCoefficient ( const double newEntryCoef )

Modify Monte Carlo entry coefficient.

◆ MCInitialSampleSize() [1/2]

size_t MCInitialSampleSize ( ) const

inline

Get the initial sample size for Monte Carlo estimations.

Definition at line 396 of file kde_model.hpp.

◆ MCInitialSampleSize() [2/2]

void MCInitialSampleSize ( const size_t newSampleSize )

Modify the initial sample size for Monte Carlo estimations.

◆ MCProbability() [1/2]

double MCProbability ( ) const

inline

Get Monte Carlo probability of error being bounded by relative error.

Definition at line 390 of file kde_model.hpp.

◆ MCProbability() [2/2]

void MCProbability ( const double newMCProb )

Modify Monte Carlo probability of error being bounded by relative error.

◆ Mode() [1/2]

KDEMode Mode ( ) const

inline

Get the mode of the model.

Definition at line 414 of file kde_model.hpp.

References KDEWrapperBase::Mode().

◆ Mode() [2/2]

KDEMode& Mode ( )

inline

Modify the mode of the model.

Definition at line 417 of file kde_model.hpp.

References mlpack::bindings::tests::CleanMemory(), and KDEWrapperBase::Mode().

◆ MonteCarlo() [1/2]

bool MonteCarlo ( ) const

inline

Get whether the model is using Monte Carlo estimations or not.

Definition at line 384 of file kde_model.hpp.

◆ MonteCarlo() [2/2]

void MonteCarlo ( const bool newMonteCarlo )

Modify whether the model is using Monte Carlo estimations or not.

◆ operator=() [1/2]

KDEModel& operator= ( const KDEModel & other )

Copy the given model.

Parameters

other KDEModel to copy.

◆ operator=() [2/2]

KDEModel& operator= ( KDEModel && other )

Take ownership of the contents of the given model.

Parameters

other KDEModel to take ownership of.

◆ RelativeError() [1/2]

double RelativeError ( ) const

inline

Get the relative error tolerance.

Definition at line 360 of file kde_model.hpp.

◆ RelativeError() [2/2]

void RelativeError ( const double newRelError )

Modify the relative error tolerance.

◆ serialize()

void serialize	(	Archive &	ar,
		const uint32_t	version
	)

Serialize the KDE model.

◆ TreeType() [1/2]

TreeTypes TreeType ( ) const

inline

Get the tree type of the model.

Definition at line 372 of file kde_model.hpp.

◆ TreeType() [2/2]

TreeTypes& TreeType ( )

inline

Modify the tree type of the model.

Definition at line 375 of file kde_model.hpp.

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

/home/ryan/src/mlpack.org/_src/mlpack-git/src/mlpack/methods/kde/kde_model.hpp

Public Types

Public Member Functions

Detailed Description

Member Enumeration Documentation

◆ KernelTypes

◆ TreeTypes

Constructor & Destructor Documentation

◆ KDEModel() [1/3]

◆ KDEModel() [2/3]

◆ KDEModel() [3/3]

◆ ~KDEModel()

Member Function Documentation

◆ AbsoluteError() [1/2]

◆ AbsoluteError() [2/2]

◆ Bandwidth() [1/2]

◆ Bandwidth() [2/2]

◆ BuildModel()

◆ Evaluate() [1/2]

◆ Evaluate() [2/2]

◆ InitializeModel()

◆ KernelType() [1/2]

◆ KernelType() [2/2]

◆ MCBreakCoefficient() [1/2]

◆ MCBreakCoefficient() [2/2]

◆ MCEntryCoefficient() [1/2]

◆ MCEntryCoefficient() [2/2]

◆ MCInitialSampleSize() [1/2]

◆ MCInitialSampleSize() [2/2]

◆ MCProbability() [1/2]

◆ MCProbability() [2/2]

◆ Mode() [1/2]

◆ Mode() [2/2]

◆ MonteCarlo() [1/2]

◆ MonteCarlo() [2/2]

◆ operator=() [1/2]

◆ operator=() [2/2]

◆ RelativeError() [1/2]

◆ RelativeError() [2/2]

◆ serialize()

◆ TreeType() [1/2]

◆ TreeType() [2/2]