autointent.modules.base.BaseDecision#

class autointent.modules.base.BaseDecision#

Bases: autointent.modules.base.BaseModule, abc.ABC

Base class for decision modules.

abstract fit(scores, labels, tags=None)#

Fit the model.

Parameters:
  • scores (numpy.typing.NDArray[Any]) – Scores to fit

  • labels (autointent.custom_types.ListOfGenericLabels) – Labels to fit

  • tags (list[autointent.schemas.Tag] | None) – Tags to fit

Return type:

None

abstract predict(scores)#

Predict the best score.

Parameters:

scores (numpy.typing.NDArray[Any]) – Scores to predict

Returns:

Predicted labels

Return type:

autointent.custom_types.ListOfGenericLabels

score_ho(context, metrics)#

Calculate metric on test set and return metric value.

Parameters:
Returns:

Dictionary of computed metrics values for the test set

Raises:

RuntimeError – If no folded scores are found

Return type:

dict[str, float]

score_cv(context, metrics)#

Calculate metric on test set and return metric value.

Parameters:
Returns:

Dictionary of computed metrics values for the test set

Raises:

RuntimeError – If no folded scores are found

Return type:

dict[str, float]

get_assets()#

Return useful assets that represent intermediate data into context.

Returns:

Decision artifact containing intermediate data

Return type:

autointent.context.optimization_info.DecisionArtifact

clear_cache()#

Clear cache.

Return type:

None

get_train_data(context)#

Get training data from context.

Parameters:

context (autointent.Context) – Context containing the data

Returns:

Tuple containing scores, labels, and tags

Return type:

tuple[numpy.typing.NDArray[Any], autointent.custom_types.ListOfGenericLabels, list[autointent.schemas.Tag]]