Allow fit params for LightGBM

[ValeriaGomes]

Describe the feature and the current state.

• LightGBM has several parameters inside the fit method. One possible solution is to add a fit_params into the LightGBM function in FkLearn for increased flexibility.
• This improvement would have to be done for both classification and regression.

Will this change a current behavior? How?

We would be able to configure the fit function using FkLearn.

Additional Information

https://lightgbm.readthedocs.io/en/latest/pythonapi/lightgbm.LGBMClassifier.html#lightgbm.LGBMClassifier.fit

[sadikneipp]

@ValeriaGomes I think the extra_params argument covers that, right?
https://github.com/nubank/fklearn/blob/aa55552ad796cfadcde63b073a7070e0398f21d7/src/fklearn/training/classification.py#L507:L511

[sadikneipp]

Hmm I'm wrong, this argument only covers the hyperparameter section here https://lightgbm.readthedocs.io/en/latest/Parameters.html

[sadikneipp]

Any specific behaviour you feel we are missing @ValeriaGomes? I see there's some overlap between what extra_params cover and the params in the link you sent

[ValeriaGomes]

@sadikneipp : Good point! I hadn't seen the extra_params. I'll check if there're parameters missing and if it's not the case, I'll close the issue.

[robotenique]

🆙 on this, I think with the current learners we cannot pass a validation set to work with early stopping in LightGBM.