-
Notifications
You must be signed in to change notification settings - Fork 112
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
249 clarification of the symmetry argument in cqr and more general documentation about cqr #443
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Super PR that clarifies the theoretical aspects of CQR. Bravo! I have made suggestions to add clarification.
Maybe rework to the notebook to improve it (add a legend, use a more meaningful example, show visually where quantile models and quantile corrections come into play in interval estimation).
Co-authored-by: Thibault Cordier <[email protected]>
Co-authored-by: Thibault Cordier <[email protected]>
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks for adding your comments to the notebooks.
To make sure we're talking about the same thing, I've made some suggestions to highlight the difference between quantile regressors with the symmetric/asymmetric option.
The code could not be put into words because CQRs are not random_state
parameters. To check and see how we can have the same regressor for both.
Another possibility is to have a single MapieQuantileRegressor and change the attribute by hand during prediction (without re-fit the model). I think this is a preferable solution.
examples/regression/1-quickstart/plot_cqr_symmetry_difference.py
Outdated
Show resolved
Hide resolved
examples/regression/1-quickstart/plot_cqr_symmetry_difference.py
Outdated
Show resolved
Hide resolved
examples/regression/1-quickstart/plot_cqr_symmetry_difference.py
Outdated
Show resolved
Hide resolved
examples/regression/1-quickstart/plot_cqr_symmetry_difference.py
Outdated
Show resolved
Hide resolved
examples/regression/1-quickstart/plot_cqr_symmetry_difference.py
Outdated
Show resolved
Hide resolved
examples/regression/1-quickstart/plot_cqr_symmetry_difference.py
Outdated
Show resolved
Hide resolved
examples/regression/1-quickstart/plot_cqr_symmetry_difference.py
Outdated
Show resolved
Hide resolved
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Here's my second proposal that I presented earlier to compare the symmetrical and asymmetrical options.
examples/regression/1-quickstart/plot_cqr_symmetry_difference.py
Outdated
Show resolved
Hide resolved
examples/regression/1-quickstart/plot_cqr_symmetry_difference.py
Outdated
Show resolved
Hide resolved
examples/regression/1-quickstart/plot_cqr_symmetry_difference.py
Outdated
Show resolved
Hide resolved
Co-authored-by: Thibault Cordier <[email protected]>
…-in-cqr-and-more-general-documentation-about-cqr
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Ready to merge. Thank you for your final modifications.
Description
This change adds an example to the documentation that demonstrates the impact of the symmetry parameter in the
MapieQuantileRegressor
class. The example generates plots for prediction intervals with both symmetry=True and symmetry=False, allowing users to visualize and understand the differences.Fixes #249.
Type of change
How Has This Been Tested?
Checklist
make lint
make type-check
make tests
make coverage
make doc