saealib.Archive¶

class saealib.Archive(attrs, init_capacity=100, key_attr='x', atol=0.0, rtol=0.0, **kwargs)[source]¶

Bases: ArchiveMixin, Population

Concrete archive: ArchiveMixin mixed into Population.

Parameters:

attrs (list[PopulationAttribute])
init_capacity (int)
key_attr (str)
atol (float)
rtol (float)

Methods

`__init__`	Initialize a Population.
`add`	Add a new solution to the archive.
`append`	Append a new individual to the population.
`argsort`	Get the indices that would sort the population by a specific attribute.
`clear`	Clear the population.
`delete`	Delete individuals from the population.
`empty_like`	Create an empty Population with the same schema.
`extend`	Extend this population with another population.
`extract`	Extract individuals with indices, and return new Population.
`get`	Get the array of a specific attribute.
`get_array`	Get the array of a specific attribute.
`get_cache`	Get a cached value.
`get_duplicated_population`	Return a Population object without removing duplicates.
`get_knn`	Get k-nearest neighbors of the given solution from the archive.
`get_readonly_array`	Return a read only view of the specified key.
`mod_structure`	Public method to call when the structure changes.
`mod_value`	Public method to call when the value changes.
`reorder`	Reorder individuals in the population.
`set_cache`	Set a cache value.
`truncate`	Cut the population to a new size.
`update_array`	Update array in place and bump the value version.

Method Details

Archive.__init__(attrs, init_capacity=100, key_attr='x', atol=0.0, rtol=0.0, **kwargs)¶

Initialize a Population.

Parameters:

attrs (List[PopulationAttribute]) – List of population attributes. Each attribute defines a column in the population.
init_capacity (int, optional) – Initial capacity of the population, by default 100.
key_attr (str)
atol (float)
rtol (float)

Archive.add(element=None, **kwargs)¶

Add a new solution to the archive. Duplicate solutions are ignored.

Parameters:

element (Individual | dict | None) – Data for the additional individual
**kwargs – Set attribute values individually and add them. Alternatively, overwrite based on the element’s value and add it.

Returns:

idx – Destination Index

Return type:

int

Examples

>>> arcv.add(ind)
>>> arcv.add({"x": x_val})
>>> arcv.add(x=x_val, f=0.1)
>>> arcv.add(ind, f=0.1)

Archive.append(element=None, **kwargs)¶

Append a new individual to the population.

Parameters:

element (Individual | dict | None) – Data for the additional individual
**kwargs – Set attribute values individually and add them. Alternatively, overwrite based on the element’s value and add it.

Return type:

None

Examples

>>> pop.append(ind)
>>> pop.append({"x": x_val})
>>> pop.append(x=x_val, f=0.1)
>>> pop.append(ind, f=0.1)

Archive.argsort(name, reverse=False)¶

Get the indices that would sort the population by a specific attribute.

Parameters:

name (str) – The attribute name to sort by.
reverse (bool, optional) – Whether to sort in descending order, by default False.

Return type:

ndarray

Archive.clear()¶

Clear the population.

Return type:: None

Archive.delete(index)¶

Delete individuals from the population.

Parameters:: index (int, slice, list[int], np.ndarray) – The index or indices of individuals to delete.
Return type:: None

Archive.empty_like(capacity=None)¶

Create an empty Population with the same schema.

Parameters:: capacity (int) – Initial capacity of the new Population. Defaults to self._capacity.

Archive.extend(other)¶

Extend this population with another population.

Parameters:: other (Population | dict) – The other population to extend from.
Return type:: None

Archive.extract(indices)¶

Extract individuals with indices, and return new Population.

Parameters:: indices (np.ndarray | List[int] | slice) – Indices to extract
Return type:: Self

Archive.get(key, default=None)¶

Get the array of a specific attribute.

Parameters:

key (str) – The attribute name to get the array for.
default (Any) – Returned when the key is absent.

Return type:

ndarray

Archive.get_array(key)¶

Get the array of a specific attribute.

Parameters:: key (str) – The attribute name to get the array for.
Return type:: ndarray

Archive.get_cache(key)¶

Get a cached value.

Returns None if the key is not found.

Parameters:: key (str) – The key of the cache.
Returns:: The cached value, or None if not found.
Return type:: Any | None

Archive.get_duplicated_population()¶

Return a Population object without removing duplicates.

Return type:: Population without removing duplicates.

Archive.get_knn(x, k)¶

Get k-nearest neighbors of the given solution from the archive.

Parameters:

x (np.ndarray) – The solution to find neighbors for.
k (int) – The number of neighbors to retrieve.

Returns:

The k-nearest neighbors’ solutions and their objective values.

Return type:

tuple[np.ndarray, np.ndarray]

Archive.get_readonly_array(key)¶

Return a read only view of the specified key.

Parameters:: key (str)
Return type:: ndarray

Archive.mod_structure()¶

Public method to call when the structure changes.

Return type:: None

Archive.mod_value()¶

Public method to call when the value changes.

Return type:: None

Archive.reorder(order)¶

Reorder individuals in the population.

Parameters:: order (np.ndarray) – The new order of individuals.
Return type:: None

Archive.set_cache(key, value)¶

Set a cache value.

The cache is automatically cleared when the population is modified (via mod_value or mod_structure).

Parameters:

key (str) – The key of the cache.
value (Any) – The value to be cached.

Return type:

None

Archive.truncate(new_size)¶

Cut the population to a new size.

Parameters:: new_size (int) – The new size of the population.
Return type:: None

Archive.update_array(key, value)¶

Update array in place and bump the value version.

Parameters:

key (str)
value (Any)

Return type:

ndarray