4.1.3. doubleml.utils.DMLOptunaResult

class doubleml.utils.DMLOptunaResult(learner_name: str, params_name: str, best_estimator: object, best_params: dict, best_score: float, scoring_method: str | Callable, study: Study, tuned: bool)

Container for Optuna search results.

This dataclass holds the results of Optuna-based hyperparameter tuning, including the best estimator, parameters, score, and the complete study history.

Parameters:

• learner_name (str) – Name of the learner passed (e.g., ‘ml_g’).

• params_name (str) – Name of the nuisance parameter being tuned (e.g., ‘ml_g0’).

• best_estimator (object) – The estimator instance with the best found hyperparameters set and fitted on the full dataset used during tuning.

• best_params (dict) – The best hyperparameters found during tuning.

• best_score (float) – The best average cross-validation score achieved during tuning.

• scoring_method (str or callable) – The scoring method used during tuning.

• study (optuna.study.Study) – The Optuna study object containing the tuning history.

• tuned (bool) – Indicates whether tuning was performed (True) or skipped (False).

Methods

Attributes

learner_name
params_name
best_estimator
best_params
best_score
scoring_method
study
tuned