search

crflynn / skranger

scikit-learn compatible Python bindings for ranger C++ random forest library
https://skranger.readthedocs.io/en/stable/
GNU General Public License v3.0
51 stars 7 forks source link

OOB Error #115

Closed Nbruneau9 closed 2 years ago

Nbruneau9 commented 2 years ago

Hello,

Stupid question, but when I activate the OOB_error keyword, it doesn't change the outcomes of predict ? Is there something else I need to set-up.

I also realised that in near line 385 "return np.array(result["predictions"]) ", the result dictionnary only contains 3 keys: predictions, num_trees and num_independent_variables but no other keys like prediction.error for example.

I just would like to access the OOB error after training the model.

Many thanks for your help. Cheers, Nicolas

import skranger skranger.version '0.6.1'

Nbruneau9 commented 2 years ago

Sorry I have found my issue and all the OOB properties are stored under rangerforest['predictions'] and rangerforest['prediction_error']

Sorry raising this issue Thanks Nicolas