src.evaluation

Module Contents

Classes

DatasetMetadata	_summary_
Evaluation	_summary_

Attributes

EvaluationTask
K
V

src.evaluation.EvaluationTask: TypeAlias

src.evaluation.K

src.evaluation.V

class src.evaluation.DatasetMetadata

Bases: TypedDict

_summary_

Parameters:

TypedDict (_type_) – _description_

name: str

version: str

class src.evaluation.Evaluation

Bases: pydantic.BaseModel, abc.ABC

_summary_

Parameters:

• BaseModel (_type_) – _description_

• ABC (_type_) – _description_

Returns:

_description_

Return type:

_type_

task: EvaluationTask

metric: Callable[[list[float | int], list[float | int]], Any]

plotter: src.plots.Plotter | None

__call__(predictions: dict[K, V], labels: dict[K, V]) → int | float

static combine_inputs(labels: dict[K, V], predictions: dict[K, V]) → pandas.DataFrame

Take results as input, combine the instance column and merge all other data.

Parameters:

• labels (dict[K, V]) – the true value

• predictions (dict[K, V]) – the value predicted by model

Returns:

a dataframe with three columns: instances, predictions, labels

Return type:

DataFrame