Rules¶

The galactic.rules module implements basic classes for dealing with basis of rules:

Rule basic class for representing implications;

class galactic.rules.Rule(premises: Collection[galactic.descriptions.Predicate], conclusions: Collection[galactic.descriptions.Predicate], support: SupportsFloat = 1.0, confidence: SupportsFloat = 1.0)¶

Bases: object

The Rule class is used to implement an implication between premises and conclusions.

The support of a rule A -> B is equal to the number of objects that match the rule divided by the total number of objects.

The confidence of a rule A -> B is equal to the support of A union B divided by the support of A.

premises() → Iterator[galactic.descriptions.Predicate]¶

Get an iterator over the premises.

Returns: An iterator over the premises.
Return type: Iterator[Predicate]

conclusions() → Iterator[galactic.descriptions.Predicate]¶

Get an iterator over the conclusions.

Returns: An iterator over the conclusions.
Return type: Iterator[Predicate]

class galactic.rules.Basis¶

Bases: typing.Collection, abc.ABC

The Basis class is the root of all implicational basis classes.

filter(support: Optional[SupportsFloat] = None, confidence: Optional[SupportsFloat] = None) → Iterator[galactic.rules.Rule]¶

Get the rules with a minimum support and minimum confidence.

Keyword Arguments

support (SupportsFloat) – The minimum support
confidence (SupportsFloat) – The minimum confidence

Returns

An iterator over the rules.

Return type

Iterator[Rule]

class galactic.rules.BasicBasis(rules: Collection[galactic.rules.Rule])¶

Bases: galactic.rules.Basis

The BasicBasis class is used to construct implicational basis from a collection of rules.

class galactic.rules.ConceptPredicate(*args, identifier: str, successors: Optional[Collection[galactic.descriptions.Predicate]] = None, **kwargs)¶

Bases: galactic.descriptions.Predicate

The ConceptPredicate class is used to represent the predicate associated to each concept.

successors() → Iterator[galactic.descriptions.Predicate]¶

Get an iterator over the successors.

Returns: An iterator over the successor predicates
Return type: Iterator[Predicate]

abstract generators() → Iterator[galactic.OrderedSet]¶

Get the generators for this predicate concept.

Returns: Get an iterator over the minimal generators.
Return type: Iterator[OrderedSet[Predicate]]

class galactic.rules.MeetPredicate(*args, identifier: str, successors: Optional[Collection[galactic.descriptions.Predicate]] = None, **kwargs)¶

Bases: galactic.rules.ConceptPredicate

The MeetPredicate class is used to define a predicate for each meet concept. The truth value is True when at least 2 successors are true.

generators() → Iterator[galactic.OrderedSet]¶

Get the generators for this predicate concept.

Returns: Get an iterator over the minimal generators.
Return type: Iterator[OrderedSet[Predicate]]

class galactic.rules.IrreduciblePredicate(*args, predicates: Optional[Collection[galactic.descriptions.Predicate]] = None, **kwargs)¶

Bases: galactic.rules.ConceptPredicate

The IrreduciblePredicate class is used to define a predicate for each meet irreducible concept.

predicates() → Iterator[galactic.descriptions.Predicate]¶

Get an iterator over the predicates

Returns: An iterator over the predicates.
Return type: Iterator[Predicate]

generators() → Iterator[galactic.OrderedSet]¶

Get the generators for this predicate concept.

Returns: Get an iterator over the minimal generators.
Return type: Iterator[OrderedSet[Predicate]]

class galactic.rules.GeneratedBasis(*args, lattice: galactic.concepts.lattice.Lattice, prefix: str = '$', **kwargs)¶

Bases: galactic.rules.Basis

The GeneratedBasis is the super class of all basis generated from a concept lattice.

filter(support: Optional[SupportsFloat] = None, confidence: Optional[SupportsFloat] = None) → Iterator[galactic.rules.Rule]¶

Get the rules with a minimum support and minimum confidence.

Keyword Arguments

support (SupportsFloat) – The minimum support
confidence (SupportsFloat) – The minimum confidence

Returns

An iterator over the rules.

Return type

Iterator[Rule]

class galactic.rules.HasseDiagramOrderedBasis(*args, lattice: galactic.concepts.lattice.Lattice, prefix: str = '$', **kwargs)¶

Bases: galactic.rules.GeneratedBasis

The HasseDiagramOrderedBasis class is used to construct implicational basis from a concept lattice using the links from the Hasse diagram.

class galactic.rules.CanonicalDirectBasis(*args, lattice: galactic.concepts.lattice.Lattice, prefix: str = '$', **kwargs)¶

Bases: galactic.rules.GeneratedBasis

The CanonicalDirectBasis is used to manage the canonical direct basis.

class galactic.rules.SimplifiedBasis(basis: galactic.rules.Basis, reduction: bool = False, generalization: bool = False, composition: bool = False)¶

Bases: galactic.rules.BasicBasis

The SimplifiedBasis class is used to manage simplified basis of rules using axioms from Malaga’s team.

class galactic.rules.Table(basis: galactic.rules.Basis, **options)¶

Bases: object

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

__init__(basis: galactic.rules.Basis, **options)¶

Initialize a Table class.

Parameters

basis (Basis) – The implicational basis whose table representation is requested
options (dict <python.dict>`) –
A collection of options
- premise_width the premise width
- conclusion_width the conclusion width
- support_width the support width
- confidence_width the confidence width
- support the minimal support
- confidence the minimal confidence
The values of the given widths are compared with each other to allocate relative column sizes.

galactic.rules.register_classes()¶: Register all classes defined in this module.