search

IIIS-Li-Group / OpenFE

OpenFE: automated feature generation with expert-level performance
MIT License
781 stars 99 forks source link

How to close Lightgbm's messages ? #41

Open Ach-1914 opened 9 months ago

Ach-1914 commented 9 months ago

When I use the fit() function, it always prints too many messages from LightGBM, and it seems I can't turn them off by setting parameters. Is there any solution? Please help!

image
ZhangTP1996 commented 9 months ago

As far as I could remember, the warnings can be suppressed by warnings.filterwarnings.

Tonghui Zou @.***> 于2024年1月23日周二 15:19写道：

When use ofe.fit(), it always print too much messages from lightgbm, and it seems can't close by setting params. Any solution ?please !!! image.png (view on web) https://github.com/IIIS-Li-Group/OpenFE/assets/77445456/24c5beb3-4308-49cd-9732-e8412ed46b6f WechatIMG281.jpg (view on web) https://github.com/IIIS-Li-Group/OpenFE/assets/77445456/aca2babd-aad4-40fd-b24f-ff4e2e387140

— Reply to this email directly, view it on GitHub https://github.com/IIIS-Li-Group/OpenFE/issues/41, or unsubscribe https://github.com/notifications/unsubscribe-auth/AG2DAPRYUETPZJCCAG3YHPDYP5QAHAVCNFSM6AAAAABCGPLOOSVHI2DSMVQWIX3LMV43ASLTON2WKOZSGA4TKNBRGI4DAMA . You are receiving this because you are subscribed to this thread.Message ID: @.***>

PeMikj commented 7 months ago

warnings.filterwarnings doesn't help. as far as i understood, we need to remove verbosity, when we create lgb instance. and in fit method.

CherpanovNazim commented 5 months ago

If you are using a Jupyter Notebook or Kaggle Notebook, you can simply write %%capture before your code. This will block any outputs.

samvelkoch commented 5 months ago

features = ofe.fit(data=train_x, label=train_y, **verbose=0**) solves an issue