OptunaTuner
- class lightautoml.ml_algo.tuning.optuna.OptunaTuner(timeout=1000, n_trials=100, direction='maximize', fit_on_holdout=True, random_state=42)[source]
Bases:
lightautoml.ml_algo.tuning.base.ParamsTuner
Wrapper for optuna tuner.
- __init__(timeout=1000, n_trials=100, direction='maximize', fit_on_holdout=True, random_state=42)[source]
- fit(ml_algo, train_valid_iterator=None)[source]
Tune model.
- Parameters
ml_algo (~TunableAlgo) – Algo that is tuned.
train_valid_iterator (
Optional
[TrainValidIterator
]) – Classic cv-iterator.
- Return type
Tuple
[Optional
[~TunableAlgo],Optional
[LAMLDataset
]]- Returns
Tuple (None, None) if an optuna exception raised or
fit_on_holdout=True
andtrain_valid_iterator
is notHoldoutIterator
. Tuple (MlALgo, preds_ds) otherwise.