Strategies

The galactic.strategies module defines

• the galactic.strategies.Strategy class which is the super-class of all strategies classes;

• the galactic.strategies.Explorer class for representing list of strategies;

• the galactic.strategies.BasicStrategy class which must be inherited to implement a new strategy;

• the galactic.strategies.AbsurdStrategy class which generates no predecessors;

• the galactic.strategies.MetaStrategy class which is the base class for all the meta strategies (strategies that use other strategies);

• the galactic.strategies.LimitFilter class which is the a meta strategy which limits the predecessors using a threshold measure;

• the galactic.strategies.SelectionFilter class which is the a meta strategy which keeps the predecessors having the best (or the worst) measure;

• the galactic.strategies.Measure class which is the base class for all measures. A measure can be called on a set of individuals and must a return a comparable value;

• the galactic.strategies.Cardinality which measures the cardinality of a concept;

• the galactic.strategies.PredecessorCardinality which measures the cardinality of the predecessor;

• the galactic.strategies.Support which measures the support of an concept;

• the galactic.strategies.PredecessorSupport which measures the support of the predecessor;

• the galactic.strategies.Confidence which measures the ratio between the confidence of a concept.

class galactic.strategies.Strategy

Bases: collections.abc.Hashable

The Strategy class produces, for a collection of individuals, a collection of candidate predicates.

descriptions

An iterator over the description spaces linked to this strategy.

Type

Iterator[Description]

selection(concept: galactic.concepts.main.Concept) → Iterator[galactic.descriptions.main.Predicate]

Compute an iterator over the selectors of a collection of individuals.

Parameters

concept (Concept) – A concept.

Returns

An iterator over a collection of selectors.

Return type

Iterator[Predicate]

abstract selectors(concept: galactic.concepts.main.Concept) → Iterator[galactic.descriptions.main.Predicate]

The selectors() method must return an iterator or selectors.

Parameters

concept (Concept) – The concept whose selectors are requested.

Returns

Return type

Iterator[Predicate]

abstract descriptions() → Iterator[galactic.descriptions.main.Description]

Get an iterator over the descriptions.

Returns

Return type

Iterator[Description]

class galactic.strategies.Explorer

Bases: list

The Explorer class implements the NextPriorityConcept algorithm to compute a mapping from concepts to their predecessors and their successors.

classmethod from_file(file: TextIO) → galactic.strategies.main.Explorer

Create a list of strategies from a readable opened file.

Keyword Arguments

file (TextIOBase) – File to read

Returns

A new list of strategies

Return type

Explorer

run(population: galactic.population.main.Population) → Iterator[Tuple[galactic.concepts.main.Concept, Tuple[Iterator[galactic.concepts.main.Concept], Iterator[galactic.concepts.main.Concept]]]]

Produce a collection of couples (Concept, (Iterator[Concept], Iterator[Concept]))

Returns

An iterator of all concepts and their couple (successors, predecessors).

Return type

Iterator[(Concept, (Iterator[Concept], Iterator[Concept]))]

class galactic.strategies.BasicStrategy(description: galactic.descriptions.main.Description)

Bases: galactic.strategies.main.Strategy

The BasicStrategy class is used for classical strategies. This class is designed for sub-classing. Sub-classes must set the _description slot in their constructor.

descriptions

An iterator over the description spaces linked to this strategy. This iterator iterate over one value.

Type

Iterator[Description]

description

The description owned by this strategy.

Type

Description

space

The description space of this strategy. This is a proxy to self.description.space.

Type

Tuple[Characteristic]

descriptions() → Iterator[galactic.descriptions.main.Description]

Get an iterator over the descriptions.

Returns

Return type

Iterator[Description]

abstract selectors(concept: galactic.concepts.main.Concept) → Iterator[galactic.descriptions.main.Predicate]

The selectors() method must return an iterator or selectors.

Parameters

concept (Concept) – The concept whose selectors are requested.

Returns

Return type

Iterator[Predicate]

class galactic.strategies.MetaStrategy(*args: galactic.strategies.main.Strategy)

Bases: galactic.strategies.main.Strategy

The MetaStrategy class is used for strategy that own their proper inner strategies.

descriptions

An iterator over the description spaces linked to this strategy.

Type

Iterator[Description]

strategies

The tuple of strategies owned by this meta-strategy.

Type

Tuple[Strategy]

__init__(*args: galactic.strategies.main.Strategy) → None

Initialise a MetaStrategy instance.

Raises

TypeError – If an argument is not an instance of Strategy

descriptions() → Iterator[galactic.descriptions.main.Description]

Get an iterator over the descriptions.

Returns

Return type

Iterator[Description]

selectors(concept: galactic.concepts.main.Concept) → Iterator[galactic.descriptions.main.Predicate]

The selectors() method must return an iterator or selectors.

Parameters

concept (Concept) – The concept whose selectors are requested.

Returns

Return type

Iterator[Predicate]

class galactic.strategies.AbsurdStrategy(*args: galactic.descriptions.main.Description)

Bases: galactic.strategies.main.Strategy

The AbsurdStrategy has been designed to describe individuals using predicates that must not be used for producing concepts.

__init__(*args: galactic.descriptions.main.Description) → None

Initialize an AbsurdStrategy instance.

Keyword Arguments

*args (Collection[Description]) – A collection of description spaces

selectors(concept: galactic.concepts.main.Concept) → Iterator[galactic.descriptions.main.Predicate]

The selectors() method must return an iterator or selectors.

Parameters

concept (Concept) – The concept whose selectors are requested.

Returns

Return type

Iterator[Predicate]

descriptions() → Iterator[galactic.descriptions.main.Description]

Get an iterator over the descriptions.

Returns

Return type

Iterator[Description]

class galactic.strategies.LimitFilter(*args: galactic.strategies.main.Strategy, limit: SupportsFloat = 0.0, strict: bool = False, lower: bool = True, **kwargs: Any)

Bases: galactic.strategies.filters.Filter

The LimitFilter class limits the possible predecessors by choosing those whose measure is greater (or less than a threshold).

__init__(*args: galactic.strategies.main.Strategy, limit: SupportsFloat = 0.0, strict: bool = False, lower: bool = True, **kwargs: Any) → None

Initialize a LimitFilter class.

Keyword Arguments

• limit (SupportsFloat) – The limit value

• strict (bool) – Is the limit strict?

• lower (bool) – Is it a lower limit?

selectors(concept: galactic.concepts.main.Concept) → Iterator[galactic.descriptions.main.Predicate]

The selectors() method must return an iterator or selectors.

Parameters

concept (Concept) – The concept whose selectors are requested.

Returns

Return type

Iterator[Predicate]

class galactic.strategies.SelectionFilter(*args: galactic.strategies.main.Strategy, keep: SupportsInt = 1, maximize: bool = True, decrease: bool = True, strict: bool = False, rate: SupportsFloat = 1.0, **kwargs: Any)

Bases: galactic.strategies.filters.Filter

The SelectionFilter class limits the possible predecessors by choosing those whose measure is among the greatest (or smallest).

Keyword Arguments

• keep (SupportsInt) – The number of group having the same value kept by this strategy

• maximize (bool) – Does this measure keep the maximum or the minimum predecessors?

• decrease (bool) – Does this strategy have to decrease the measure value between a concept and its predecessors.

• strict (bool) – Is the comparison strict between the concept and its predecessors.

• rate (SupportsFloat) – The rate applied to the concept measure that the predecessors have to be lesser or greater than.

selectors(concept: galactic.concepts.main.Concept) → Iterator[galactic.descriptions.main.Predicate]

The selectors() method must return an iterator or selectors.

Parameters

concept (Concept) – The concept whose selectors are requested.

Returns

Return type

Iterator[Predicate]

class galactic.strategies.Measure

Bases: object

The Measure class is an abstract class. Its subclasses must implement the __call__() method.

abstract __call__(concept: galactic.concepts.main.Concept, predicate: galactic.descriptions.main.Predicate) → float

The __call__() method evaluate the individuals present in the concept whose call to predicate is true.

Parameters

concept (Concept) – The concept for which individuals will be tested.

Keyword Arguments

predicate (Predicate) – The predicate to be tested.

Returns

The computed measure.

Return type

float

class galactic.strategies.Cardinality

Bases: galactic.strategies.measures.Measure

The Cardinality class computes the cardinality of the predecessor.

class galactic.strategies.Support

Bases: galactic.strategies.measures.Measure

The Support class computes the support of the predecessor.

class galactic.strategies.Confidence

Bases: galactic.strategies.measures.Measure

The Confidence class computes the cardinality ratio between the predecessor and the successor.

class galactic.strategies.Lattice(population: galactic.population.main.Population, explorer: galactic.strategies.main.Explorer)

Bases: galactic.algebras.lattice.lattices.CompactLattice

The Lattice class implements the GeneratedBasicLattice class.

__init__(population: galactic.population.main.Population, explorer: galactic.strategies.main.Explorer)

Initialise a Lattice instance.

Parameters

• population (Population) – The underlying population

• explorer (Explorer) – An explorer

maximum() → galactic.concepts.main.Concept

Get the maximum element of this join semi-lattice.

Returns

The maximum element

Return type

J

index(concept: galactic.concepts.main.Concept) → int

Get the index of a concept.

Returns

Return type

The index of a concept

new_predicates(concept: galactic.concepts.main.Concept) → Iterator[galactic.descriptions.main.Predicate]

Get the new predicates given by the concept.

Parameters

concept (Concept) – The concept whose new predicates are requested.

Returns

An iterator over the new predicates.

Return type

Iterator[Predicate]

new_individuals(concept: galactic.concepts.main.Concept) → Iterator[str]

Get the new individuals given by the concept.

Parameters

concept (Concept) – The concept whose new individuals are requested.

Returns

An iterator over the individual keys.

Return type

Iterator[str]

population() → galactic.population.main.Population

Get the population

Returns

The population

Return type

Population

explorer() → galactic.strategies.main.Explorer

Get the explorer

Returns

The explorer

Return type

Explorer

class galactic.strategies.Table(lattice: galactic.strategies.lattice.Lattice, **options: Any)

Bases: object

The Table class is used to represent lattice in jupyter notebooks.

__init__(lattice: galactic.strategies.lattice.Lattice, **options: Any)

Initialize a Table class.

Parameters

• lattice (Lattice) – The lattice whose table representation is requested

• options (dict <python.dict>`) –

  A collection of options

  • all_individuals is a boolean flag for displaying all individuals for each concept

  • all_predicates is a boolean flag for displaying all predicates for each concept

  • concept_width the concept width

  • individual_width the individual width

  • predicate_width the predicate width

  By default only new predicates and new individuals are displayed. The values of the given widths are compared with each other to allocate relative column sizes.