mlpack
Public Member Functions | List of all members
KDEWrapperBase Class Referenceabstract

KDEWrapperBase is a base wrapper class for holding all KDE types supported by KDEModel. More...

Inheritance diagram for KDEWrapperBase:
Inheritance graph
[legend]

Public Member Functions

 KDEWrapperBase ()
 Create the KDEWrapperBase object. More...

 
virtual ~KDEWrapperBase ()
 Destruct the KDEWrapperBase (nothing to do). More...

 
virtual void AbsoluteError (const double absError)=0
 Modify the absolute error tolerance. More...

 
virtual void Bandwidth (const double bw)=0
 Modify the bandwidth of the kernel. More...

 
virtual KDEWrapperBase * Clone () const =0
 Create a new KDEWrapperBase that is the same as this one. More...

 
virtual void Evaluate (util::Timers &timers, arma::mat &&querySet, arma::vec &estimates)=0
 Perform bichromatic KDE (i.e. KDE with a separate query set). More...

 
virtual void Evaluate (util::Timers &timers, arma::vec &estimates)=0
 Perform monochromatic KDE (i.e. with the reference set as the query set). More...

 
virtual void MCBreakCoef (const double breakCoef)=0
 Modify the Monte Carlo break coefficient. More...

 
virtual void MCEntryCoef (const double entryCoef)=0
 Modify the Monte Carlo entry coefficient. More...

 
virtual size_t MCInitialSampleSize () const =0
 Get the Monte Carlo sample size. More...

 
virtual size_t & MCInitialSampleSize ()=0
 Modify the Monte Carlo sample size. More...

 
virtual void MCProb (const double mcProb)=0
 Modify the Monte Carlo probability. More...

 
virtual KDEMode Mode () const =0
 Get the search mode. More...

 
virtual KDEMode & Mode ()=0
 Modify the search mode. More...

 
virtual bool MonteCarlo () const =0
 Get whether Monte Carlo search is being used. More...

 
virtual bool & MonteCarlo ()=0
 Modify whether Monte Carlo search is being used. More...

 
virtual void RelativeError (const double relError)=0
 Modify the relative error tolerance. More...

 
virtual void Train (util::Timers &timers, arma::mat &&referenceSet)=0
 Train the model (build the tree). More...

 

Detailed Description

KDEWrapperBase is a base wrapper class for holding all KDE types supported by KDEModel.

All KDE type wrappers inheirt from this class, allowing a simple interface via inheritance for all the different types we want to support.

Definition at line 71 of file kde_model.hpp.

Constructor & Destructor Documentation

◆ KDEWrapperBase()

KDEWrapperBase ( )
inline

Create the KDEWrapperBase object.

The base class does not hold anything, so this constructor does nothing.

Definition at line 76 of file kde_model.hpp.

◆ ~KDEWrapperBase()

virtual ~KDEWrapperBase ( )
inlinevirtual

Destruct the KDEWrapperBase (nothing to do).

Definition at line 83 of file kde_model.hpp.

Member Function Documentation

◆ AbsoluteError()

virtual void AbsoluteError ( const double  absError)
pure virtual

Modify the absolute error tolerance.

Implemented in KDEWrapper< KernelType, TreeType >.

◆ Bandwidth()

virtual void Bandwidth ( const double  bw)
pure virtual

Modify the bandwidth of the kernel.

Implemented in KDEWrapper< KernelType, TreeType >.

◆ Clone()

virtual KDEWrapperBase* Clone ( ) const
pure virtual

Create a new KDEWrapperBase that is the same as this one.

This function will properly handle polymorphism.

Implemented in KDEWrapper< KernelType, TreeType >.

◆ Evaluate() [1/2]

virtual void Evaluate ( util::Timers &  timers,
arma::mat &&  querySet,
arma::vec &  estimates 
)
pure virtual

Perform bichromatic KDE (i.e. KDE with a separate query set).

Implemented in KDEWrapper< KernelType, TreeType >.

◆ Evaluate() [2/2]

virtual void Evaluate ( util::Timers &  timers,
arma::vec &  estimates 
)
pure virtual

Perform monochromatic KDE (i.e. with the reference set as the query set).

Implemented in KDEWrapper< KernelType, TreeType >.

◆ MCBreakCoef()

virtual void MCBreakCoef ( const double  breakCoef)
pure virtual

Modify the Monte Carlo break coefficient.

Implemented in KDEWrapper< KernelType, TreeType >.

◆ MCEntryCoef()

virtual void MCEntryCoef ( const double  entryCoef)
pure virtual

Modify the Monte Carlo entry coefficient.

Implemented in KDEWrapper< KernelType, TreeType >.

◆ MCInitialSampleSize() [1/2]

virtual size_t MCInitialSampleSize ( ) const
pure virtual

Get the Monte Carlo sample size.

Implemented in KDEWrapper< KernelType, TreeType >.

◆ MCInitialSampleSize() [2/2]

virtual size_t& MCInitialSampleSize ( )
pure virtual

Modify the Monte Carlo sample size.

Implemented in KDEWrapper< KernelType, TreeType >.

◆ MCProb()

virtual void MCProb ( const double  mcProb)
pure virtual

Modify the Monte Carlo probability.

Implemented in KDEWrapper< KernelType, TreeType >.

◆ Mode() [1/2]

virtual KDEMode Mode ( ) const
pure virtual

Get the search mode.

Implemented in KDEWrapper< KernelType, TreeType >.

Referenced by KDEModel::Mode().

◆ Mode() [2/2]

virtual KDEMode& Mode ( )
pure virtual

Modify the search mode.

Implemented in KDEWrapper< KernelType, TreeType >.

◆ MonteCarlo() [1/2]

virtual bool MonteCarlo ( ) const
pure virtual

Get whether Monte Carlo search is being used.

Implemented in KDEWrapper< KernelType, TreeType >.

◆ MonteCarlo() [2/2]

virtual bool& MonteCarlo ( )
pure virtual

Modify whether Monte Carlo search is being used.

Implemented in KDEWrapper< KernelType, TreeType >.

◆ RelativeError()

virtual void RelativeError ( const double  relError)
pure virtual

Modify the relative error tolerance.

Implemented in KDEWrapper< KernelType, TreeType >.

◆ Train()

virtual void Train ( util::Timers &  timers,
arma::mat &&  referenceSet 
)
pure virtual

Train the model (build the tree).

Implemented in KDEWrapper< KernelType, TreeType >.

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