Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

monotonic constraints not working in xgboost_ray #273

Open
heyitsmui opened this issue Mar 2, 2023 · 2 comments
Open

monotonic constraints not working in xgboost_ray #273

heyitsmui opened this issue Mar 2, 2023 · 2 comments
Assignees

Comments

@heyitsmui
Copy link

heyitsmui commented Mar 2, 2023

Was chatting with @krfricke about this in recent weeks, the monotonic constraints parameter doesn't seem to be working on xgboost_ray.

Steps to reproduce: Provided a notebook here which compares an open source xgboost model vs. open source xgboost_ray trained model, with monotonicity enabled for certain features.
debug_xgboost_ray_monotonic_constraints (1).pdf

What do we expect: Monotonicity should be enforced. EG in the notebook above,
image

In this plot, the first subplot should be strictly monotonically increasing as the x-axis increases but we see a dip at the beginning when x ~= 0.5ish

@Yard1 Yard1 self-assigned this Mar 3, 2023
@heyitsmui
Copy link
Author

XGBoost Ray Monotonic Constraints.ipynb.zip

attached the notebook in .ipynb format for convenience

@Yard1
Copy link
Member

Yard1 commented Mar 15, 2023

Hey @heyitsmui, I cannot reproduce this. I get the exact same plot from both xgboost and xgboost-ray (with 1 or 2 workers). I used your notebook and edited the saving of the second plot so it doesn't override the previous plot.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants