The Engine class represents the core engine of the brush library. More...

#include <engine.h>

Collaboration diagram for Brush::Engine< T >:

[legend]

Public Member Functions
	Engine (const Parameters &p=Parameters())

	~Engine ()

void	print_progress (float percentage)

void	calculate_stats ()

void	print_stats (std::ofstream &log, float fraction)

void	log_stats (std::ofstream &log)

Parameters &	get_params ()

void	set_params (Parameters &p)

bool	get_is_fitted ()

bool	update_best (const Dataset &data, bool val=false)
	updates best score by searching in the population for the individual that best fits the given data

Individual< T > &	get_best_ind ()

Engine< T > &	fit (Dataset &data)

Engine< T > &	fit (const Ref< const ArrayXXf > &X, const Ref< const ArrayXf > &y)

auto	predict (const Dataset &data)

auto	predict (const Ref< const ArrayXXf > &X)

template<ProgramType P = T> requires ((P == PT::BinaryClassifier) \|\| (P == PT::MulticlassClassifier))
auto	predict_proba (const Dataset &d)

template<ProgramType P = T> requires ((P == PT::BinaryClassifier) \|\| (P == PT::MulticlassClassifier))
auto	predict_proba (const Ref< const ArrayXXf > &X)

int	get_archive_size ()
	return archive size

vector< json >	get_archive (bool front)
	return population as string

auto	predict_archive (int id, const Dataset &data)
	predict on unseen data from the archive

auto	predict_archive (int id, const Ref< const ArrayXXf > &X)

template<ProgramType P = T> requires ((P == PT::BinaryClassifier) \|\| (P == PT::MulticlassClassifier))
auto	predict_proba_archive (int id, const Dataset &data)

template<ProgramType P = T> requires ((P == PT::BinaryClassifier) \|\| (P == PT::MulticlassClassifier))
auto	predict_proba_archive (int id, const Ref< const ArrayXXf > &X)

void	run (Dataset &d)
	train the model

Public Attributes
float	best_score

int	best_complexity

Parameters	params
	hyperparameters of brush, which the user can interact

Individual< T >	best_ind

Archive< T >	archive
	pareto front archive

Private Member Functions
void	init ()
	initialize Feat object for fitting.

void	set_is_fitted (bool f)
	set flag indicating whether fit has been called

Private Attributes
SearchSpace	ss

Population< T >	pop
	population of programs

Selection< T >	selector
	selection algorithm

Evaluation< T >	evaluator
	evaluation code

Variation< T >	variator
	variation operators

Selection< T >	survivor
	survival algorithm

Log_Stats	stats
	runtime stats

Timer	timer
	start time of training

bool	is_fitted
	keeps track of whether fit was called.

Detailed Description

template<ProgramType T>
class Brush::Engine< T >

The Engine class represents the core engine of the brush library.

It encapsulates the functionality for training and predicting with programs in a genetic programming framework. The Engine class manages the population of programs, selection algorithms, evaluation code, variation operators, and survival algorithms. It also provides methods for training the model, making predictions, and accessing runtime statistics.

The Engine class is parameterized by the program type T, which determines the type of programs that can be evolved and evaluated by the engine.

Definition at line 43 of file engine.h.

Constructor & Destructor Documentation

◆ Engine()

template<ProgramType T>

Brush::Engine< T >::Engine ( const Parameters & p = Parameters() )

inline

Definition at line 45 of file engine.h.

◆ ~Engine()

template<ProgramType T>

Brush::Engine< T >::~Engine ( )

inline

Definition at line 51 of file engine.h.

Member Function Documentation

◆ calculate_stats()

template<ProgramType T>

void Brush::Engine< T >::calculate_stats ( )

Definition at line 62 of file engine.cpp.

Here is the caller graph for this function:

◆ fit() [1/2]

template<ProgramType T>

Engine< T > & Brush::Engine< T >::fit	(	const Ref< const ArrayXXf > &	X,
		const Ref< const ArrayXf > &	y )

inline

Definition at line 79 of file engine.h.

◆ fit() [2/2]

template<ProgramType T>

Engine< T > & Brush::Engine< T >::fit ( Dataset & data )

inline

Definition at line 75 of file engine.h.

Here is the caller graph for this function:

◆ get_archive()

template<ProgramType T>

vector< json > Brush::Engine< T >::get_archive ( bool front )

return population as string

Definition at line 191 of file engine.cpp.

Here is the call graph for this function:

◆ get_archive_size()

template<ProgramType T>

int Brush::Engine< T >::get_archive_size ( )

inline

return archive size

Definition at line 106 of file engine.h.

◆ get_best_ind()

template<ProgramType T>

Individual< T > & Brush::Engine< T >::get_best_ind ( )

inline

Definition at line 73 of file engine.h.

◆ get_is_fitted()

template<ProgramType T>

bool Brush::Engine< T >::get_is_fitted ( )

inline

Definition at line 63 of file engine.h.

◆ get_params()

template<ProgramType T>

Parameters & Brush::Engine< T >::get_params ( )

inline

Definition at line 60 of file engine.h.

◆ init()

template<ProgramType T>

void Brush::Engine< T >::init ( )

private

initialize Feat object for fitting.

Definition at line 18 of file engine.cpp.

Here is the call graph for this function:

Here is the caller graph for this function:

◆ log_stats()

template<ProgramType T>

void Brush::Engine< T >::log_stats ( std::ofstream & log )

Definition at line 129 of file engine.cpp.

Here is the caller graph for this function:

◆ predict() [1/2]

template<ProgramType T>

auto Brush::Engine< T >::predict ( const Dataset & data )

inline

Definition at line 87 of file engine.h.

Here is the caller graph for this function:

◆ predict() [2/2]

template<ProgramType T>

auto Brush::Engine< T >::predict ( const Ref< const ArrayXXf > & X )

inline

Definition at line 88 of file engine.h.

◆ predict_archive() [1/2]

template<ProgramType T>

auto Brush::Engine< T >::predict_archive	(	int	id,
		const Dataset &	data )

predict on unseen data from the archive

Definition at line 208 of file engine.cpp.

Here is the call graph for this function:

Here is the caller graph for this function:

◆ predict_archive() [2/2]

template<ProgramType T>

auto Brush::Engine< T >::predict_archive	(	int	id,
		const Ref< const ArrayXXf > &	X )

Definition at line 239 of file engine.cpp.

Here is the call graph for this function:

◆ predict_proba() [1/2]

template<ProgramType T>

template<ProgramType P = T>
requires ((P == PT::BinaryClassifier) || (P == PT::MulticlassClassifier))

auto Brush::Engine< T >::predict_proba ( const Dataset & d )

inline

Definition at line 96 of file engine.h.

Here is the caller graph for this function:

◆ predict_proba() [2/2]

template<ProgramType T>

template<ProgramType P = T>
requires ((P == PT::BinaryClassifier) || (P == PT::MulticlassClassifier))

auto Brush::Engine< T >::predict_proba ( const Ref< const ArrayXXf > & X )

inline

Definition at line 99 of file engine.h.

◆ predict_proba_archive() [1/2]

template<ProgramType T>
requires ((P == PT::BinaryClassifier) || (P == PT::MulticlassClassifier))

template<ProgramType P>
requires ((P == PT::BinaryClassifier) || (P == PT::MulticlassClassifier))

auto Brush::Engine< T >::predict_proba_archive	(	int	id,
		const Dataset &	data )

Definition at line 248 of file engine.cpp.

Here is the call graph for this function:

Here is the caller graph for this function:

◆ predict_proba_archive() [2/2]

template<ProgramType T>
requires ((P == PT::BinaryClassifier) || (P == PT::MulticlassClassifier))

template<ProgramType P>
requires ((P == PT::BinaryClassifier) || (P == PT::MulticlassClassifier))

auto Brush::Engine< T >::predict_proba_archive	(	int	id,
		const Ref< const ArrayXXf > &	X )

Definition at line 281 of file engine.cpp.

Here is the call graph for this function:

◆ print_progress()

template<ProgramType T>

void Brush::Engine< T >::print_progress ( float percentage )

Definition at line 46 of file engine.cpp.

Here is the caller graph for this function:

◆ print_stats()

template<ProgramType T>

void Brush::Engine< T >::print_stats	(	std::ofstream &	log,
		float	fraction )

Definition at line 159 of file engine.cpp.

Here is the caller graph for this function:

◆ run()

template<ProgramType T>

void Brush::Engine< T >::run ( Dataset & d )

train the model

Definition at line 324 of file engine.cpp.

Here is the call graph for this function:

Here is the caller graph for this function:

◆ set_is_fitted()

template<ProgramType T>

void Brush::Engine< T >::set_is_fitted ( bool f )

inlineprivate

set flag indicating whether fit has been called

Definition at line 149 of file engine.h.

Here is the caller graph for this function:

◆ set_params()

template<ProgramType T>

void Brush::Engine< T >::set_params ( Parameters & p )

inline

Definition at line 61 of file engine.h.

◆ update_best()

template<ProgramType T>

bool Brush::Engine< T >::update_best	(	const Dataset &	data,
		bool	val = false )

updates best score by searching in the population for the individual that best fits the given data

Definition at line 288 of file engine.cpp.

Here is the caller graph for this function:

Member Data Documentation

◆ archive

template<ProgramType T>

Archive<T> Brush::Engine< T >::archive

pareto front archive

Definition at line 130 of file engine.h.

◆ best_complexity

template<ProgramType T>

int Brush::Engine< T >::best_complexity

Definition at line 72 of file engine.h.

◆ best_ind

template<ProgramType T>

Individual<T> Brush::Engine< T >::best_ind

Definition at line 128 of file engine.h.

◆ best_score

template<ProgramType T>

float Brush::Engine< T >::best_score

Definition at line 71 of file engine.h.

◆ evaluator

template<ProgramType T>

Evaluation<T> Brush::Engine< T >::evaluator

private

evaluation code

Definition at line 136 of file engine.h.

◆ is_fitted

template<ProgramType T>

bool Brush::Engine< T >::is_fitted

private

keeps track of whether fit was called.

Definition at line 144 of file engine.h.

◆ params

template<ProgramType T>

Parameters Brush::Engine< T >::params

hyperparameters of brush, which the user can interact

Definition at line 127 of file engine.h.

◆ pop

template<ProgramType T>

Population<T> Brush::Engine< T >::pop

private

population of programs

Definition at line 134 of file engine.h.

◆ selector

template<ProgramType T>

Selection<T> Brush::Engine< T >::selector

private

selection algorithm

Definition at line 135 of file engine.h.

◆ ss

template<ProgramType T>

SearchSpace Brush::Engine< T >::ss

private

Definition at line 132 of file engine.h.

◆ stats

template<ProgramType T>

Log_Stats Brush::Engine< T >::stats

private

runtime stats

Definition at line 140 of file engine.h.

◆ survivor

template<ProgramType T>

Selection<T> Brush::Engine< T >::survivor

private

survival algorithm

Definition at line 138 of file engine.h.

◆ timer

template<ProgramType T>

Timer Brush::Engine< T >::timer

private

start time of training

Definition at line 142 of file engine.h.

◆ variator

template<ProgramType T>

Variation<T> Brush::Engine< T >::variator

private

variation operators

Definition at line 137 of file engine.h.

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

Public Member Functions

Public Attributes

Private Member Functions

Private Attributes

Detailed Description

Constructor & Destructor Documentation

◆ Engine()

◆ ~Engine()

Member Function Documentation

◆ calculate_stats()

◆ fit() [1/2]

◆ fit() [2/2]

◆ get_archive()

◆ get_archive_size()

◆ get_best_ind()

◆ get_is_fitted()

◆ get_params()

◆ init()

◆ log_stats()

◆ predict() [1/2]

◆ predict() [2/2]

◆ predict_archive() [1/2]

◆ predict_archive() [2/2]

◆ predict_proba() [1/2]

◆ predict_proba() [2/2]

◆ predict_proba_archive() [1/2]

◆ predict_proba_archive() [2/2]

◆ print_progress()

◆ print_stats()

◆ run()

◆ set_is_fitted()

◆ set_params()

◆ update_best()

Member Data Documentation

◆ archive

◆ best_complexity

◆ best_ind

◆ best_score

◆ evaluator

◆ is_fitted

◆ params

◆ pop

◆ selector

◆ ss

◆ stats

◆ survivor

◆ timer

◆ variator