merlin.datasets.metadata module

class merlin.datasets.metadata.DatasetMetadata(name, description, features, num_instances, subset=None, num_features=None, normalization=None, task_type=<factory>, num_classes=None, characteristics=<factory>, homepage=None, license=None, citation=None, creators=<factory>, year=None, feature_relationships=None)

Bases: object

characteristics: list[str]

citation: Optional[str] = None

creators: list[str]

description: str

feature_relationships: Optional[str] = None

features: list[Feature]

classmethod from_dict(data)

Return type:: DatasetMetadata

homepage: Optional[str] = None

license: Optional[str] = None

name: str

normalization: Optional[Normalization] = None

num_classes: Optional[int] = None

num_features: int = None

num_instances: int

subset: str = None

task_type: Optional[list[str]]

to_dict()

Convert the metadata to a dictionary format

Return type:: dict[str, Any]

year: Optional[int] = None

class merlin.datasets.metadata.Feature(name, description, type, value_range=None, unit=None, stats=None, normalization=None)

Bases: object

description: str

name: str

normalization: Optional[FeatureNormalization] = None

stats: Optional[dict[str, float]] = None

to_text()

Return type:: str

type: str

unit: Optional[str] = None

value_range: Optional[tuple] = None

class merlin.datasets.metadata.FeatureNormalization(original_unit=None, scale_factor=None, offset=None)

Bases: object

offset: Optional[float] = None

original_unit: Optional[str] = None

scale_factor: Optional[float] = None

to_text()

Return type:: str

class merlin.datasets.metadata.Normalization(method, range, per_feature=True)

Bases: object

method: str

per_feature: bool = True

range: tuple

to_text()

Return type:: str