ultra::src::binary_evaluator< P > Class Template Reference

#include <evaluator.h>

Inheritance diagram for ultra::src::binary_evaluator< P >:

Public Member Functions
	binary_evaluator (multi_dataset< dataframe > &)
double	operator() (const P &) const
auto	predictor (const P &) const

Additional Inherited Members
Static Public Attributes inherited from ultra::src::evaluator< multi_dataset< dataframe > >
static constexpr std::size_t	default_min_samples_per_thread
Protected Member Functions inherited from ultra::src::evaluator< multi_dataset< dataframe > >
	evaluator (D &) noexcept
bool	set_parallel_evaluation (unsigned, std::size_t=0) noexcept
const auto &	data () const noexcept
std::size_t	min_samples_per_thread () const noexcept
unsigned	parallel_helpers () const noexcept

Detailed Description

template<Individual P>
class ultra::src::binary_evaluator< P >

Evaluator for binary classification problems.

Template Parameters

P	individual type

Incorrect predictions are penalised proportionally to the model's confidence.

Constructor & Destructor Documentation

binary_evaluator()

template<Individual P>

binary_evaluator::binary_evaluator ( multi_dataset< dataframe > & d )

explicit

Constructs the evaluator.

Parameters

[in]

d

training dataset

Member Function Documentation

operator()()

template<Individual P>

double binary_evaluator::operator() ( const P & prg ) const

nodiscard

Computes the binary classification fitness.

Parameters

[in]

prg

program to evaluate

Returns

fitness value (greater is better, max is 0)

Precondition

the dataset must contain exactly two classes

predictor()

template<Individual P>

auto binary_evaluator::predictor ( const P & prg ) const

nodiscard

Builds a binary classification oracle.

Parameters

[in]

prg

program to transform into an oracle

Returns

oracle object associated with prg

---

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

• gp/src/evaluator.h
• gp/src/evaluator.tcc