ReasonedEvidence
- class ReasonedEvidence(*, evidence_type: Literal['reasoned'] = 'reasoned', justification: NormalizedNamableReference, mappings: list[Mapping], author: NormalizedNamableReference | None = None, confidence_factor: float = 1.0)[source]
Bases:
BaseModel,KeyedMixin[(typing.Union[curies.triples.Triple, ForwardRef(‘Mapping’)],),tuple[StrTriple,ReasonedEvidenceKey]],EvidenceMixin,ConfidenceMixinA complex evidence based on multiple mappings.
Create a new model by parsing and validating input data from keyword arguments.
Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.
self is explicitly positional-only to allow self as a field name.
Attributes Summary
Get a textual explanation for this reasoned evidence.
Return an empty mapping set, since this is a reasoned evidence.
Get a set containing the union of all the mappings' evidences' mapping set names.
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
Methods Summary
Calculate confidence for the reasoned evidence.
key(triple)Get a key suitable for hashing the evidence.
Attributes Documentation
- explanation
Get a textual explanation for this reasoned evidence.
- Returns:
Assuming this reasoned evidence represents a pathway where each mapping in the chain’s subject shares the object from the previous mapping, returns a space-delmited list of the CURIEs for these entities.
- mapping_set
Return an empty mapping set, since this is a reasoned evidence.
- mapping_set_names
Get a set containing the union of all the mappings’ evidences’ mapping set names.
- model_config: ClassVar[ConfigDict] = {'frozen': True}
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
Methods Documentation
- get_confidence() float[source]
Calculate confidence for the reasoned evidence.
- Returns:
The joint binomial probability that all reasoned evidences are correct. This is calculated with the following:
$alpha times (1 - sum_{e in E} 1 - text{confidence}_e)$
where $E$ is the set of all evidences in this object and $alpha$ is the confidence factor for the reasoning approach.