autointent.context.optimization_info.ScorerArtifact

class autointent.context.optimization_info.ScorerArtifact(/, **data)

Bases: Artifact

Artifact containing outputs from the scoring node.

Outputs from the best scorer, numpy arrays of shape (n_samples, n_classes).

Parameters:

data (Any)

train_scores

Scorer outputs for train utterances.

validation_scores

Scorer outputs for validation utterances.

test_scores

Scorer outputs for test utterances.

folded_scores

Scores for each fold from cross-validation.

model_config

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

train_scores: numpy.typing.NDArray[numpy.float64] | None = None

validation_scores: numpy.typing.NDArray[numpy.float64] | None = None

test_scores: numpy.typing.NDArray[numpy.float64] | None = None

folded_scores: list[numpy.typing.NDArray[numpy.float64]] | None = None

model_dump(**kwargs)

Convert the model to a dictionary, converting numpy arrays to lists.

Parameters:

kwargs (Any)

Return type:

dict[str, Any]

classmethod model_validate(obj)

Convert lists back to numpy arrays during validation.

Parameters:

obj (dict[str, Any])

Return type:

ScorerArtifact