gum::learning::ScoringCache Class Reference

a cache for caching scores and independence tests results More...

#include <agrum/base/database/scoringCache.h>

Public Member Functions
Constructors / Destructors
	ScoringCache ()
	default constructor
	ScoringCache (const ScoringCache &from)
	copy constructor
	ScoringCache (ScoringCache &&from)
	move constructor
virtual ScoringCache *	clone () const
	virtual copy constructor
virtual	~ScoringCache ()
	destructor
Operators
ScoringCache &	operator= (const ScoringCache &from)
	copy operator
ScoringCache &	operator= (ScoringCache &&from)
	move operator
Accessors / Modifiers
void	insert (const IdCondSet &idset, double score)
	insert a new score into the cache
void	insert (IdCondSet &&idset, double score)
	insert a new score into the cache
void	erase (const IdCondSet &idset)
	removes a score (if it exists)
bool	exists (const IdCondSet &idset)
	indicates whether a given score exists
double	score (const IdCondSet &idset)
	returns a given score
void	clear ()
	removes all the stored scores
std::size_t	size () const
	returns the number of scores saved in the cache

Detailed Description

a cache for caching scores and independence tests results

Caching previously computed scores or the results of conditional independence tests is very important for learning algorithms because computing a score or an independence test requires parsing the database and this is the most time consuming operation in learning. This class provides an efficient cache that can significantly alleviate the learning computational burden.

Definition at line 79 of file scoringCache.h.

Constructor & Destructor Documentation

ScoringCache() [1/3]

gum::learning::ScoringCache::ScoringCache

(

)

default constructor

Referenced by ScoringCache(), ScoringCache(), clone(), operator=(), and operator=().

Here is the caller graph for this function:

ScoringCache() [2/3]

gum::learning::ScoringCache::ScoringCache

(

const ScoringCache &

from

)

copy constructor

References ScoringCache().

Here is the call graph for this function:

ScoringCache() [3/3]

gum::learning::ScoringCache::ScoringCache

(

ScoringCache &&

from

)

move constructor

References ScoringCache().

Here is the call graph for this function:

~ScoringCache()

virtual gum::learning::ScoringCache::~ScoringCache ( )

virtual

destructor

Member Function Documentation

clear()

void gum::learning::ScoringCache::clear

(

)

removes all the stored scores

clone()

virtual ScoringCache * gum::learning::ScoringCache::clone ( ) const

virtual

virtual copy constructor

References ScoringCache().

Here is the call graph for this function:

erase()

void gum::learning::ScoringCache::erase

(

const IdCondSet &

idset

)

removes a score (if it exists)

Parameters

idset

the IdCondSet storing the sets of variables

Warning

If the score does not exist, nothing is done. In particular, no exception is raised

exists()

bool gum::learning::ScoringCache::exists

(

const IdCondSet &

idset

)

indicates whether a given score exists

Parameters

idset

the IdCondSet storing the sets of variables

insert() [1/2]

void gum::learning::ScoringCache::insert	(	const IdCondSet &	idset,
		double	score )

insert a new score into the cache

Parameters

idset	the IdCondSet storing the sets of variables
score	the score assigned to the IdCondSet

Exceptions

DuplicateElement

exception is raised if a score for the same variables already exists

References score().

Here is the call graph for this function:

insert() [2/2]

void gum::learning::ScoringCache::insert	(	IdCondSet &&	idset,
		double	score )

insert a new score into the cache

Parameters

idset	the IdCondSet storing the sets of variables
score	the score assigned to the IdCondSet

Exceptions

DuplicateElement

exception is raised if a score for the same variables already exists

References score().

Here is the call graph for this function:

operator=() [1/2]

ScoringCache & gum::learning::ScoringCache::operator=

(

const ScoringCache &

from

)

copy operator

References ScoringCache().

Here is the call graph for this function:

operator=() [2/2]

ScoringCache & gum::learning::ScoringCache::operator=

(

ScoringCache &&

from

)

move operator

References ScoringCache().

Here is the call graph for this function:

score()

double gum::learning::ScoringCache::score

(

const IdCondSet &

idset

)

returns a given score

Parameters

idset

the IdCondSet storing the sets of variables

Exceptions

NotFound

is raised if the score is not cached

Referenced by insert(), and insert().

Here is the caller graph for this function:

size()

std::size_t gum::learning::ScoringCache::size

(

)

const

returns the number of scores saved in the cache

---

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

• agrum/base/stattests/scoringCache.h