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.

Sign up for GitHub

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

Jump to bottom

🐛 Thin FQCurveDisplay when scores are almost constant #27

Open
sanjaradylov opened this issue Sep 21, 2024 · 0 comments
Open

🐛 Thin FQCurveDisplay when scores are almost constant #27

sanjaradylov opened this issue Sep 21, 2024 · 0 comments
Assignees
@sanjaradylov
Labels
invalid This doesn't seem right package:metrics Adding new or improving existing fallback metrics

Comments

@sanjaradylov
Copy link
Owner

Describe the bug
If a prediction quality doesn't change over fallback rate, a fallback-quality plot becomes unrecognizable.

To Reproduce
Try ThresholdFallbackClassifier(fallback_mode="store") if it's not the best choice, and then FQCurveDisplay.

Expected behavior
See Screenshots.

Screenshots
Screenshot 2024-09-21 at 4 49 34 PM

Please complete the following information:

  • OS: NA
  • Python version: NA
  • scikit-fallback version: <=0.1

Additional context
NA
@sanjaradylov sanjaradylov added invalid This doesn't seem right package:metrics Adding new or improving existing fallback metrics labels Sep 21, 2024
@sanjaradylov sanjaradylov self-assigned this Sep 21, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@sanjaradylov sanjaradylov

Labels
invalid This doesn't seem right package:metrics Adding new or improving existing fallback metrics
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@sanjaradylov