fix: add missing stacklevel=2 to warnings.warn() in losses/ (Fixes #8929)#8930
Open
rtmalikian wants to merge 2 commits into
Open
fix: add missing stacklevel=2 to warnings.warn() in losses/ (Fixes #8929)#8930rtmalikian wants to merge 2 commits into
rtmalikian wants to merge 2 commits into
Conversation
Add stacklevel=2 to 28 warnings.warn() calls across 9 loss modules so that warnings correctly point to the user's calling code instead of MONAI internal code. Affected files: - dice.py (7 instances) - tversky.py (3 instances) - mcc_loss.py (3 instances) - focal_loss.py (3 instances) - hausdorff_loss.py (3 instances) - unified_focal_loss.py (3 instances) - spatial_mask.py (3 instances) - perceptual.py (2 instances) - adversarial_loss.py (1 instance) Also fixes a typo in perceptual.py: 'supp, ort' -> 'support'. Fixes Project-MONAI#8929 Signed-off-by: Raphael Malikian <rtmalikian@gmail.com>
rtmalikian
requested review from
KumoLiu,
Nic-Ma,
ericspod and
virginiafdez
as code owners
Contributor
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (2)
✅ Files skipped from review due to trivial changes (2)
📝 WalkthroughWalkthroughAll Estimated code review effort🎯 1 (Trivial) | ⏱️ ~3 minutes 🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
🧹 Nitpick comments (2)
monai/losses/perceptual.py (1)
129-131: 💤 Low valueConsider moving
stacklevelparameter to previous line for consistency.The
stacklevel=2parameter is on a separate line with a leading comma, inconsistent with line 115 in this file and most other warnings in this PR.Suggested formatting
warnings.warn( - f"Setting cache_dir to {cache_dir}, this may change the default cache dir for all torch.hub calls." - , stacklevel=2) + f"Setting cache_dir to {cache_dir}, this may change the default cache dir for all torch.hub calls.", + stacklevel=2)🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@monai/losses/perceptual.py` around lines 129 - 131, The stacklevel=2 parameter in the warnings.warn() call is on a separate line with a leading comma, which is inconsistent with the formatting used at line 115 and elsewhere in the codebase. Move the stacklevel=2 parameter to the same line as the f-string message by placing the comma at the end of the f-string and positioning stacklevel=2 on the same line with proper indentation to match the consistent formatting style used throughout the file.monai/losses/adversarial_loss.py (1)
130-133: 💤 Low valueConsider moving
stacklevelparameter to previous line for consistency.The
stacklevel=2parameter is on a separate line with a leading comma. Other files in this PR keep the parameter on the same line as the closing quote. Consistent formatting improves readability.Suggested formatting
warnings.warn( "Variable target_is_real has been set to False, but for_discriminator is set" - "to False. To optimise a generator, target_is_real must be set to True." - , stacklevel=2) + "to False. To optimise a generator, target_is_real must be set to True.", + stacklevel=2)🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@monai/losses/adversarial_loss.py` around lines 130 - 133, In the warnings.warn call in the adversarial_loss.py file, the stacklevel parameter is currently on a separate line with a leading comma. Move the stacklevel=2 parameter to the same line as the closing quote of the warning message string and adjust the formatting so the comma follows the string closure rather than appearing on a separate line. This will align with the formatting convention used elsewhere in the PR.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Nitpick comments:
In `@monai/losses/adversarial_loss.py`:
- Around line 130-133: In the warnings.warn call in the adversarial_loss.py
file, the stacklevel parameter is currently on a separate line with a leading
comma. Move the stacklevel=2 parameter to the same line as the closing quote of
the warning message string and adjust the formatting so the comma follows the
string closure rather than appearing on a separate line. This will align with
the formatting convention used elsewhere in the PR.
In `@monai/losses/perceptual.py`:
- Around line 129-131: The stacklevel=2 parameter in the warnings.warn() call is
on a separate line with a leading comma, which is inconsistent with the
formatting used at line 115 and elsewhere in the codebase. Move the stacklevel=2
parameter to the same line as the f-string message by placing the comma at the
end of the f-string and positioning stacklevel=2 on the same line with proper
indentation to match the consistent formatting style used throughout the file.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
Run ID: 2d1171ec-b7a8-49b8-b1cf-d02878e99e70
📒 Files selected for processing (9)
monai/losses/adversarial_loss.pymonai/losses/dice.pymonai/losses/focal_loss.pymonai/losses/hausdorff_loss.pymonai/losses/mcc_loss.pymonai/losses/perceptual.pymonai/losses/spatial_mask.pymonai/losses/tversky.pymonai/losses/unified_focal_loss.py
…rsarial_loss.py Address CodeRabbit review: move stacklevel parameter to same line as closing quote for consistent formatting across the PR. Signed-off-by: Raphael Malikian <rtmalikian@gmail.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Fixes #8929
Problem
28 calls to
warnings.warn()inmonai/losses/are missing thestacklevelparameter. Withoutstacklevel=2, warnings point to the MONAI internal code instead of the user's calling code, making it difficult for users to identify which part of their script triggered the warning.Solution
Added
stacklevel=2to all 28warnings.warn()calls across 9 loss modules:dice.py(7 instances)tversky.py(3 instances)mcc_loss.py(3 instances)focal_loss.py(3 instances)hausdorff_loss.py(3 instances)unified_focal_loss.py(3 instances)spatial_mask.py(3 instances)perceptual.py(2 instances)adversarial_loss.py(1 instance)Also fixes a typo in
perceptual.py:"supp, ort"→"support"(carried from #8924).Verification
Changelog
Files Changed
monai/losses/dice.py— 7 warnings.warn() calls updatedmonai/losses/tversky.py— 3 calls updatedmonai/losses/mcc_loss.py— 3 calls updatedmonai/losses/focal_loss.py— 3 calls updatedmonai/losses/hausdorff_loss.py— 3 calls updatedmonai/losses/unified_focal_loss.py— 3 calls updatedmonai/losses/spatial_mask.py— 3 calls updatedmonai/losses/perceptual.py— 2 calls updated + typo fixmonai/losses/adversarial_loss.py— 1 call updatedVerification
About the Author: Raphael Malikian — Clinical AI Solutions Architect. I specialise in building and fixing AI/ML systems for healthcare, including vector databases, RAG pipelines, and clinical NLP. If you need help with your project or think I can add value to your organisation, feel free to reach out — I'd love to connect.
📧 rtmalikian@gmail.com
🔗 GitHub: https://github.com/rtmalikian
🔗 LinkedIn: http://www.linkedin.com/in/raphael-t-malikian-mbbs-bsc-hons-71075436a
Disclosure: This code was developed with assistance from MiMo-v2.5-Pro (Xiaomi) via Hermes Agent (Nous Research). All changes were reviewed, tested against the actual codebase, and verified for correctness.