culebra.solution.feature_selection.Solution class

class Solution(species: Species, fitness_cls: Type[Fitness], features: Sequence[int] | None = None)

Construct a default solution.

Parameters:

  • species (species_cls) – The species the solution will belong to

  • fitness (Fitness) – The solution’s fitness class

  • features (Sequence of int) – Initial features

Raises:

  • TypeError – If species is not a valid species

  • TypeError – If fitness_cls is not a valid fitness class

Class attributes

Solution.species_cls = <class 'culebra.solution.feature_selection.Species'>

Class for the species used by the Solution class to constrain all its instances.

Class methods

classmethod Solution.load_pickle(filename: str) → Base

Load a pickled object from a file.

Parameters:

filename (str) – The file name.

Raises:

Properties

property Solution.species: Species

Get the solution’s species.

Returns:

The species

Return type:

Species

property Solution.fitness: Fitness

Get and set the solution’s fitness.

Getter:

Return the current fitness

Setter:

Set a new Fitness

Type:

Fitness

abstract property Solution.features: Sequence[int]

Get and set the indices of the features selected by the solution.

This property must be overridden by subclasses to return a correct value.

Getter:

Return an ordered sequence with the indices of the selected features.

Setter:

Set the new feature indices. An array-like object of feature indices is expected

Type:

Sequence of int

Raises:

NotImplementedError – if has not been overridden

abstract property Solution.num_feats: int

Get the number of features selected by the solution.

This property must be overridden by subclasses to return a correct value.

Raises:

NotImplementedError – if has not been overridden

Type:

int

abstract property Solution.min_feat: int | None

Minimum feature index selected by the solution.

This property must be overridden by subclasses to return a correct value.

Raises:

NotImplementedError – if has not been overridden

Type:

int or None if no feature has been selected

abstract property Solution.max_feat: int | None

Maximum feature index selected by the solution.

This property must be overridden by subclasses to return a correct value.

Raises:

NotImplementedError – if has not been overridden

Type:

int or None if no feature has been selected

Methods

Solution.save_pickle(filename: str) → None

Pickle this object and save it to a file.

Parameters:

filename (str) – The file name.

Raises:
Solution.dominates(other: Solution) → bool

Dominate operator.

Parameters:

other (Solution) – Other solution

Returns:

True if each objective of the solution is not strictly worse than the corresponding objective of other and at least one objective is strictly better.

Return type:

bool

Solution.delete_fitness() → None

Delete the solution’s fitness.

Private methods

abstract Solution._setup() → None

Init the features of this solution randomly.

This method must be overridden by subclasses.

Raises:

NotImplementedError – if has not been overridden

Dunder methods

Solution.__hash__() → int

Return the hash number for this solution.

The hash number is used for equality comparisons. Currently is implemented as the hash of the solution’s string representation.

Solution.__eq__(other: Solution) → bool

Equality test.

Parameters:

other (Solution) – Other solution

Returns:

True if other codes the same solution, or False otherwise

Return type:

bool

Solution.__ne__(other: Solution) → bool

Not equality test.

Parameters:

other (Solution) – Other solution

Returns:

False if other codes the same solutions, or True otherwise

Return type:

bool

Solution.__lt__(other: Solution) → bool

Less than operator.

Parameters:

other (Solution) – Other solution

Returns:

True if the solution’s fitness is less than the other’s fitness

Return type:

bool

Solution.__gt__(other: Solution) → bool

Greater than operator.

Parameters:

other (Solution) – Other solution

Returns:

True if the solution’s fitness is greater than the other’s fitness

Return type:

bool

Solution.__le__(other: Solution) → bool

Less than or equal to operator.

Parameters:

other (Solution) – Other solution

Returns:

True if the solution’s fitness is less than or equal to the other’s fitness

Return type:

bool

Solution.__ge__(other: Solution) → bool

Greater than or equal to operator.

Parameters:

other (Solution) – Other solution

Returns:

True if the solution’s fitness is greater than or equal to the other’s fitness

Return type:

bool

Solution.__str__() → str

Return the solution as a string.