metaheuristic_designer.parent_selection package

Submodules

• metaheuristic_designer.parent_selection.parent_selection module
  • ParentSelectionDef
    • ParentSelectionDef.selection_fn
    • ParentSelectionDef.params
    • ParentSelectionDef.forced_params
  • create_parent_selection()
  • add_parent_selection_entry()
  • list_parent_selection_methods()
• metaheuristic_designer.parent_selection.parent_selection_functions module
  • fitness_proportional()
  • sigma_scaling()
  • linear_ranking()
  • exponential_ranking()
  • flat_ranking()
  • create_scaling_fn()
  • repeating_selection()
  • select_best()
  • prob_tournament()
  • uniform_selection()
  • shuffle_population()
  • roulette()
  • sus()

Module contents

Parent selection registry and factory.

class NullParentSelection(name='Nothing', **kwargs)

Bases: ParentSelection

Null parent selection, returns the whole population unchanged.

This is the identity element: no individuals are filtered out. Useful when the algorithm does not require a parent selection step (e.g., random search or certain evolution strategies).

Parameters:

namestr, optional

Display name. Default "Nothing".

**kwargs

Keyword arguments forwarded to ParentSelection.

Attributes:

params

Access parameter values by attribute-style lookup.

Parameters:

name (Optional[str])

Methods

__call__(population[, amount])	Shorthand for select().
gather_params()	Return the current parameter dictionary (thin wrapper around get_params()).
get_params()	Return a copy of the current parameter dictionary.
get_state()	Return a dictionary with the selection method's configuration.
select(population[, amount])	Takes a population with its offspring and returns the individuals that survive to produce the next generation.
store_kwargs([progress])	Store keyword arguments and evaluate them at the given progress.
update(progress)	Re-evaluate all stored parameters at the current progress.
update_kwargs([progress])	Add or replace parameters and immediately evaluate them.

select(population, amount=None)

Takes a population with its offspring and returns the individuals that survive to produce the next generation.

Return type:

Population

Parameters:

population: Population

Population of individuals that will be selected.

offspring: Population

Newly generated individuals to be selected.

Returns:

selected: Population

List of selected individuals.

Parameters:

• population (Population)

• amount (int | None)

class ParentSelection(name=None, amount=None, rng=None, **kwargs)

Bases: ParametrizableMixin, ABC

Abstract base for all parent selection methods.

A parent selection chooses which individuals from the current population will be used to generate offspring. Subclasses must implement select(), which returns a new Population containing only the selected individuals.

Parameters:

namestr, optional

Display name for this selection method.

amountint, optional

Default number of individuals to select. Can be overridden at call time.

rngRNGLike, optional

Random number generator.

**kwargs

Additional keyword arguments stored as schedulable parameters.

Attributes:

params

Access parameter values by attribute-style lookup.

Parameters:

• name (Optional[str])

• amount (Optional[int])

• rng (Optional[RNGLike])

Methods

__call__(population[, amount])	Shorthand for select().
gather_params()	Return the current parameter dictionary (thin wrapper around get_params()).
get_params()	Return a copy of the current parameter dictionary.
get_state()	Return a dictionary with the selection method's configuration.
select(population[, amount])	Takes a population with its offspring and returns the individuals that survive to produce the next generation.
store_kwargs([progress])	Store keyword arguments and evaluate them at the given progress.
update(progress)	Re-evaluate all stored parameters at the current progress.
update_kwargs([progress])	Add or replace parameters and immediately evaluate them.

gather_params()

Return the current parameter dictionary (thin wrapper around get_params()).

Return type:

dict

abstract select(population, amount=None)

Takes a population with its offspring and returns the individuals that survive to produce the next generation.

Return type:

Population

Parameters:

population: Population

Population of individuals that will be selected.

offspring: Population

Newly generated individuals to be selected.

Returns:

selected: Population

List of selected individuals.

Parameters:

• population (Population)

• amount (int | None)

get_state()

Return a dictionary with the selection method’s configuration.

Return type:

dict

Returns:

dict

Keys include class_name, name, and all current parameters.

class ParentSelectionDef(selection_fn, params=<factory>, forced_params=<factory>)

Bases: object

Wrapper that turns a raw parent-selection function into a callable.

Parameters:

selection_fncallable

Function (fitness, amount, rng, **kwargs) -> indices.

paramsdict, optional

Default keyword arguments merged with user-supplied ones.

forced_paramsdict, optional

Keyword arguments that always override user-supplied ones.

Parameters:

• selection_fn (callable)

• params (dict)

• forced_params (dict)

Methods

__call__(population[, amount, rng])

Call self as a function.

selection_fn: callable

params: dict

forced_params: dict

class ParentSelectionFromLambda(selection_fn, name=None, amount=None, rng=None, **kwargs)

Bases: ParentSelection

Parent selection that wraps a user-supplied function.

The function receives the population, the number of individuals to select, a random state, and any stored keyword arguments, and must return an array of selected indices.

Parameters:

selection_fncallable

A function (population, amount, rng, **kwargs) -> indices.

namestr, optional

Display name (defaults to the function’s __name__).

amountint, optional

Default number of individuals to select.

rngRNGLike, optional

Random number generator.

**kwargs

Keyword arguments forwarded to ParentSelection.

Attributes:

params

Access parameter values by attribute-style lookup.

Parameters:

• selection_fn (Callable)

• name (Optional[str])

• amount (Optional[int])

• rng (Optional[RNGLike])

Methods

__call__(population[, amount])	Shorthand for select().
gather_params()	Return the current parameter dictionary (thin wrapper around get_params()).
get_params()	Return a copy of the current parameter dictionary.
get_state()	Return a dictionary with the selection method's configuration.
select(population[, amount])	Takes a population with its offspring and returns the individuals that survive to produce the next generation.
store_kwargs([progress])	Store keyword arguments and evaluate them at the given progress.
update(progress)	Re-evaluate all stored parameters at the current progress.
update_kwargs([progress])	Add or replace parameters and immediately evaluate them.

select(population, amount=None)

Takes a population with its offspring and returns the individuals that survive to produce the next generation.

Return type:

Population

Parameters:

population: Population

Population of individuals that will be selected.

offspring: Population

Newly generated individuals to be selected.

Returns:

selected: Population

List of selected individuals.

Parameters:

• population (Population)

• amount (int | None)

list_parent_selection_methods()

Return a list of all registered parent selection method names.

Return type:

list[str]

Returns:

list of str

add_parent_selection_entry(selection_fn, selection_method_name)

Register a new parent selection method.

Parameters:

selection_fncallable

A function with the parent selection signature.

selection_method_namestr

Name under which to register the method. If it already exists, a warning is logged.

Parameters:

• selection_fn (callable)

• selection_method_name (str)

create_parent_selection(method, name=None, amount=None, rng=None, **kwargs)

Create a parent selection method by name.

Return type:

ParentSelection

Parameters:

methodstr

Key into parent_sel_map, or a null alias.

namestr, optional

Display name for the selection method.

amountint, optional

Default number of parents to select.

rngRNGLike, optional

Random number generator.

**kwargs

Additional parameters forwarded to the selection function.

Returns:

ParentSelectionFromLambda or NullParentSelection

The wrapped selection method.

Parameters:

• method (str)

• name (str | None)

• amount (int | None)

• rng (int | Generator | None)

create_scaling_fn(method, scaling_factor=2)

Create a callable that computes normalized selection weights.

Return type:

Callable

Parameters:

methodstr

Key into scaling_map (e.g., "fitness_proportional").

scaling_factorfloat, optional

Factor forwarded to the underlying scaling function.

Returns:

callable

A function (fitness) -> weights that returns a normalized probability vector.

Parameters:

• method (str)

• scaling_factor (number | float | int)

select_best(fitness, amount, rng=None)

Selects the best parent of the population as parents.

Return type:

ndarray[tuple[int, ...], integer] | ndarray[tuple[int, ...], uint8 | bool]

Parameters:

population: ndarray

List of individuals from which the parents will be selected.

amount: int

Amount of individuals to be chosen as parents.

Returns:

parents: ndarray

List of individuals chosen as parents.

Parameters:

• fitness (ndarray[tuple[int], floating] | ndarray[tuple[int], integer] | ndarray[tuple[int], uint8 | bool])

• amount (int)

• rng (int | Generator | None)

shuffle_population(fitness, amount, rng=None)

Chooses a number of individuals from the population at random without replacement if amount < population_size. If we cannot pick without replacement, we at least make sure we pick every individual at least \(\left\lceil \frac{\text{amount}}{\text{population\_size}} \right\rceil\) times

Return type:

ndarray[tuple[int, ...], integer] | ndarray[tuple[int, ...], uint8 | bool]

Parameters:

population: ndarray

List of individuals from which the parents will be selected.

amount: int

Amount of individuals to be chosen as parents.

Returns:

parents: ndarray

List of individuals chosen as parents.

Parameters:

• fitness (ndarray[tuple[int], floating] | ndarray[tuple[int], integer] | ndarray[tuple[int], uint8 | bool])

• amount (int)

• rng (int | Generator | None)

prob_tournament(fitness, amount, rng=None, tournament_size=3, prob=1)

Selects the parents for the next generation by tournament.

Return type:

ndarray[tuple[int, ...], integer] | ndarray[tuple[int, ...], uint8 | bool]

Parameters:

population: ndarray

List of individuals from which the parents will be selected.

tournament_size: int

Amount of individuals that will be chosen for each tournament.

prob: float

Probability that a parent with low fitness will win the tournament.

Returns:

parents: ndarray

List of individuals chosen as parents.

Parameters:

• fitness (ndarray[tuple[int], floating] | ndarray[tuple[int], integer] | ndarray[tuple[int], uint8 | bool])

• amount (int)

• rng (int | Generator | None)

• tournament_size (int)

• prob (float)

uniform_selection(fitness, amount, rng=None)

Chooses a number of individuals from the population at random with replacement.

Return type:

ndarray[tuple[int, ...], integer] | ndarray[tuple[int, ...], uint8 | bool]

Parameters:

population: ndarray

List of individuals from which the parents will be selected.

amount: int

Amount of individuals to be chosen as parents.

Returns:

parents: ndarray

List of individuals chosen as parents.

Parameters:

• fitness (ndarray[tuple[int], floating] | ndarray[tuple[int], integer] | ndarray[tuple[int], uint8 | bool])

• amount (int)

• rng (int | Generator | None)

roulette(fitness, amount, rng=None, method='flat_scaling', scaling_factor=None)

Fitness proportionate parent selection.

Return type:

ndarray[tuple[int, ...], integer] | ndarray[tuple[int, ...], uint8 | bool]

Parameters:

population: ndarray

List of individuals from which the parents will be selected.

amount: int

Amount of individuals to be chosen as parents.

method: str, optional

Indicates how the roulette will be generated.

f: float, optional

Parameter passed to some of the roulette generating methods.

Returns:

parents: ndarray

List of individuals chosen as parents.

Parameters:

• fitness (ndarray[tuple[int], floating] | ndarray[tuple[int], integer] | ndarray[tuple[int], uint8 | bool])

• amount (int)

• rng (int | Generator | None)

• method (str)

• scaling_factor (float | None)

sus(fitness, amount, rng=None, method='flat_scaling', scaling_factor=None)

Stochastic universal sampling parent selection method.

Return type:

ndarray[tuple[int, ...], integer] | ndarray[tuple[int, ...], uint8 | bool]

Parameters:

population: ndarray

List of individuals from which the parents will be selected.

amount: int

Amount of individuals to be chosen as parents.

method: str, optional

Indicates how the roulette will be generated.

f: float, optional

Parameter passed to some of the roulette generating methods.

Returns:

parents: ndarray

List of individuals chosen as parents.

Parameters:

• fitness (ndarray[tuple[int], floating] | ndarray[tuple[int], integer] | ndarray[tuple[int], uint8 | bool])

• amount (int)

• rng (int | Generator | None)

• method (str)

• scaling_factor (float | None)