Hi, I'm working with AutoMLForecast and trying to modify the best trial configuration after optimization. Specifically, I'm doing:

config_lgb = auto_mlf.results_['my_lgb'].best_trial.user_attrs['config']
config_lgb['mlf_init_params']['date_features'] = ['month']

What is the recommended way to update the best trial configuration to make some minor modifications?

I'd just hardcopy the best config into a dict (ray) or trial function (optuna) and make the adjustment you need.

Thanks. Also, how can I inspect what specific target transformations were applied in the autoML configuration? When I retrieve the best trial I get this:

'target_transforms': [<mlforecast.target_transforms.GlobalSklearnTransformer at 0x7fe669c55e10>,
   <mlforecast.target_transforms.Differences at 0x7fe669c38450>,
   <mlforecast.target_transforms.LocalStandardScaler at 0x7fe513c8b650>]

I'd like to know what sklearn transformer was used in GlobalSklearnTransformer and what parameters were used for Differences.