You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I'm working on a Multigression problem. Indeed, I have 13 response variables to predict. The problem statement tells us the weight of each response variable. When I train my Catboost model without considering the weights, I get a bad score. So, I would like to train my CatBoostRegressor() with the weights of the response variables: I would like its equivalent to CatBoostClassifier(auto_class_weights=).
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
I'm working on a Multigression problem. Indeed, I have 13 response variables to predict. The problem statement tells us the weight of each response variable. When I train my Catboost model without considering the weights, I get a bad score. So, I would like to train my CatBoostRegressor() with the weights of the response variables: I would like its equivalent to CatBoostClassifier(auto_class_weights=).
I leaned towards a custom objective function because my model will have to seek the best parameters while taking into account the weights of the response variables.
This link was a bit helpful for me (Section 5. Multiregression): https://github.com/catboost/catboost/blob/master/catboost/tutorials/custom_loss/custom_loss_and_metric_tutorial.ipynb
Unfortunately, I cannot assign my weights to the "weights" parameter.
Please, can someone have a solution to my problem? How to assign weights to response variables at CatBoostRegressor?
Thank you!
Beta Was this translation helpful? Give feedback.
All reactions