SklearnModelConfig¶

SklearnModelConfig ¶

Configuration container for scikit-learn models in the factrainer framework.

This class encapsulates all necessary components for training and prediction with scikit-learn models.

Warnings

Do not instantiate this class directly by calling SklearnModelConfig(...). Use the factory method SklearnModelConfig.create instead.

Attributes:

Name	Type	Description
`learner`	`SklearnLearner`	Component responsible for training scikit-learn models.
`predictor`	`SklearnPredictor`	Component responsible for making predictions with trained models.
`train_config`	`SklearnTrainConfig`	Configuration for training parameters (estimator and fit kwargs).
`pred_config`	`SklearnPredictConfig`	Configuration for prediction parameters (prediction method and kwargs).

See Also

SklearnModelConfig.create : Factory method for creating configurations. SklearnTrainConfig : Configuration for training parameters. SklearnPredictConfig : Configuration for prediction parameters. SingleModelContainer : For training a single model. CvModelContainer : For cross-validation workflows.

Examples:

>>> from sklearn.ensemble import RandomForestClassifier
>>> from factrainer.sklearn import SklearnModelConfig, SklearnTrainConfig
>>> # Create configuration with default prediction settings
>>> estimator = RandomForestClassifier(n_estimators=10)
>>> train_config = SklearnTrainConfig(estimator=estimator)
>>> model_config = SklearnModelConfig.create(train_config)
>>> # Create configuration with custom prediction settings
>>> from factrainer.sklearn import SklearnPredictConfig, SklearnPredictMethod
>>> pred_config = SklearnPredictConfig(
...     predict_method=SklearnPredictMethod.PREDICT_PROBA
... )
>>> model_config = SklearnModelConfig.create(train_config, pred_config)

Attributes¶

learner `instance-attribute` ¶

learner: SklearnLearner

predictor `instance-attribute` ¶

predictor: SklearnPredictor

train_config `instance-attribute` ¶

train_config: SklearnTrainConfig

pred_config `instance-attribute` ¶

pred_config: SklearnPredictConfig

Functions¶

create `classmethod` ¶

create(
    train_config: SklearnTrainConfig,
    pred_config: SklearnPredictConfig | None = None,
) -> Self

Create a new SklearnModelConfig instance.

Parameters:

Name	Type	Description	Default
`train_config`	`SklearnTrainConfig`	Configuration for training parameters including the estimator and any additional fit keyword arguments.	required
`pred_config`	`SklearnPredictConfig \| None`	Configuration for prediction parameters. If None, uses default SklearnPredictConfig() which automatically selects the prediction method.	`None`

Returns:

Type	Description
`SklearnModelConfig`	A configuration instance ready for use with SingleModelContainer or CvModelContainer.

SklearnModelConfig¶