metaheuristic_designer.population module#

Base class for the Population module.

This module implements a data structure to hold the collection of solutions we are considering.

class Population(genotype_matrix, encoding=None)[source]#

Bases: object

Container for a set of candidate solutions and their fitness.

A Population holds the genotype matrix, fitness and objective values, historical bests, and the current best individual. It is the central data structure passed between components of the optimization loop.

Parameters:

objfuncObjectiveFunc: The objective function that will evaluate the population.
genotype_matrixndarray: 2-D array of shape (N, M) containing the genotypes.
encodingEncoding, optional: The encoding used to translate between genotype and phenotype. Defaults to DefaultEncoding.

Parameters:

genotype_matrix (MatrixLike)
encoding (Optional[Encoding])

Methods

`apply_encoding`([encoding])	Return the population passed through the decoding function defined in the encoding.
`apply_selection`(selected_pop, selection_idx)	Replaces the chosen individuals from the input population to the current population.
`apply_slice`(sliced_pop, mask)	Apply the values of the population to a subset of the components of the population vectors.
`best_individual`()	Return the best genotype and its maximized fitness value.
`best_solution`()	Return the best decoded solution and its raw objective value.
`debug_repr`([max_solutions, max_vars])	Return a compact string representation for debugging.
`decode`([encoding])	Return the population matrix passed through the decoding function defined in the encoding.
`decode_params`([encoding])	Decode the auxiliary parameters stored in the genotype.
`encode`([encoding])	Encode the current population matrix using the given encoding.
`get_state`()	Return a dictionary with the current population state.
`join`(other_population)	Adds to the current population the individuals of the input population.
`join_populations`(population1, population2)	Concatenate two populations into a new one.
`repeat`([amount])	Duplicates the individuals of the population.
`sort_population`()	Sorts the individuals by fitness.
`step`([_progress])	Updates the best solution in the population.
`take_selection`(selection_idx)	Takes a subset of the population given a mask.
`take_slice`(mask)	Takes a subset of the components in the population vectors.
`update_best_from_parents`(parents)	Update the best solution if a better one exists in parents.
`update_genotype`(genotype_source)	Replace the genotype matrix.

best_individual()[source]#

Return the best genotype and its maximized fitness value.

Return type:

Tuple[ndarray[tuple[int, int], floating] | ndarray[tuple[int, int], integer] | ndarray[tuple[int, int], uint8 | bool], float]

Returns:

best_genotypeMatrixLike: The genotype vector of the best individual.
best_fitnessfloat: The internal fitness (always maximized).

best_solution()[source]#

Return the best decoded solution and its raw objective value.

Return type:

Tuple[Any, float]

Returns:

solutionAny: The decoded phenotype of the best individual.
objectivefloat: The raw objective value.

update_genotype(genotype_source)[source]#

Replace the genotype matrix.

Return type:

Population

Parameters:

genotype_sourcendarray or Population: New genotypes. If a Population is given, its genotype matrix is used.

Returns:

Population: self, with updated genotypes and, if the size changed, re-initialized fitness and historical bests.

Parameters:

genotype_source (ndarray[tuple[int, int], floating] | ndarray[tuple[int, int], integer] | ndarray[tuple[int, int], uint8 | bool] | Population)

take_selection(selection_idx)[source]#

Takes a subset of the population given a mask.

Return type:

Population

Parameters:

selection_idx: ndarray: An array of indices or a mask that indicate which individuals to take from the population.

Returns:

selected_population: Population: A copy of the population containing only the chosen individuals.

Parameters:

selection_idx (ndarray[tuple[int, ...], integer] | ndarray[tuple[int, ...], uint8 | bool])

apply_selection(selected_pop, selection_idx)[source]#

Replaces the chosen individuals from the input population to the current population.

Return type:

Population

Parameters:

selected_pop: Population: Population where to take the individuals that will replace the ones in the population.
selection_idx: ndarray: An array of indices or a mask that indicate which individuals to take from the population.

Returns:

self: Population

Parameters:

selected_pop (Population)
selection_idx (ndarray[tuple[int, ...], integer] | ndarray[tuple[int, ...], uint8 | bool])

take_slice(mask)[source]#

Takes a subset of the components in the population vectors.

Return type:

Population

Parameters:

mask: ndarray: An array of indices or a mask that indicate which components to take from each vector in the population.

Returns:

sliced_population: Population: A copy of the population containing the masked individuals.

Parameters:

mask (ndarray[tuple[int, ...], integer] | ndarray[tuple[int, ...], uint8 | bool])

apply_slice(sliced_pop, mask)[source]#

Apply the values of the population to a subset of the components of the population vectors.

Return type:

Population

Parameters:

sliced_pop: Population: Population where to take the individuals from which we will take the components that will replace the ones in the current population.
mask: ndarray: An array of indices or a mask that indicate which components to take from each vector in the population.

Returns:

self: Population

Parameters:

sliced_pop (Population)
mask (ndarray[tuple[int, ...], integer] | ndarray[tuple[int, ...], uint8 | bool])

static join_populations(population1, population2)[source]#

Concatenate two populations into a new one.

Return type:

Population

Parameters:

population1Population: First population.
population2Population: Second population.

Returns:

Population: A new population containing all individuals from both inputs.

Parameters:

population1 (Population)
population2 (Population)

join(other_population)[source]#

Adds to the current population the individuals of the input population.

Return type:

Population

Parameters:

other_population: Population: Population that will be concatenated with the current one.

Returns:

joined_populations: Population: A population containing both the individuals from the current population and the ones from the input population.

Parameters:

other_population (Population)

sort_population()[source]#

Sorts the individuals by fitness.

Return type:

Population

Returns:

self: Population

update_best_from_parents(parents)[source]#

Update the best solution if a better one exists in parents.

Return type:

Population

Parameters:

parentsPopulation: Population whose best individual may improve the current one.

Returns:

Population: self, with possibly updated best, best_fitness, and best_objective.

Parameters:

parents (Population)

step(_progress=0)[source]#

Updates the best solution in the population.

Return type:

Population

Returns:

self: Population

Parameters:

_progress (float)

repeat(amount=2)[source]#

Duplicates the individuals of the population.

Return type:

Population

Parameters:

amount: int, optional: The amount of times to repeat the individuals in the population.

Returns:

repeated_population: Population

Parameters:

amount (int)

apply_encoding(encoding=None)[source]#

Return the population passed through the decoding function defined in the encoding.

Return type:

Population

Returns:

decoded_population: Any

Parameters:

encoding (Encoding | None)

decode(encoding=None)[source]#

Return the population matrix passed through the decoding function defined in the encoding.

Return type:

Iterable

Returns:

MatrixLike: The decoded genotype matrix.

Parameters:

encoding (Encoding | None)

decode_params(encoding=None)[source]#

Decode the auxiliary parameters stored in the genotype.

Only works with ParameterExtendingEncoding.

Return type:

Iterable

Parameters:

encodingEncoding, optional: Encoding to use; defaults to self.encoding.

Returns:

dict or None: Dictionary of parameter arrays, or None if the encoding does not support extended parameters.

Parameters:

encoding (Encoding | None)

encode(encoding=None)[source]#

Encode the current population matrix using the given encoding.

Return type:

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

Parameters:

encodingEncoding, optional: Encoding to use; defaults to self.encoding.

Returns:

MatrixLike: The encoded genotype matrix.

Parameters:

encoding (Encoding | None)

get_state()[source]#

Return a dictionary with the current population state.

Return type:

dict

Returns:

dict: Keys include genotype_matrix, fitness, objective, historical bests, and the best individual.

debug_repr(max_solutions=5, max_vars=5)[source]#

Return a compact string representation for debugging.

Return type:

str

Parameters:

max_solutionsint, optional: Maximum number of rows to include in the preview.
max_varsint, optional: Maximum number of columns to include in the preview.

Returns:

str

Parameters:

max_solutions (int)
max_vars (int)