Fix compute_matthew_corr mutating its input confusion matrix#1672
Open
Kymi808 wants to merge 1 commit into
Open
Fix compute_matthew_corr mutating its input confusion matrix#1672Kymi808 wants to merge 1 commit into
Kymi808 wants to merge 1 commit into
Conversation
compute_matthew_corr folds the abstain column (index 2) into column 0 before computing the correlation. It did so via `r = confusion_matrix[:, :2]`, which is a NumPy view, so `r[:, 0] += confusion_matrix[:, 2]` modified the caller's confusion matrix in place. Any metric computed from the same matrix afterwards (e.g. compute_precision / compute_recall) then silently used corrupted counts. Operate on a copy so the input is left unchanged. The returned correlation is unaffected. Adds a regression test.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
compute_matthew_corrfolds the abstain column (index 2) into column 0 before computing the Matthews correlation:confusion_matrix[:, :2]is a NumPy view, sor[:, 0] += confusion_matrix[:, 2]modifies the caller's confusion matrix in place. Any metric computed from the same matrix afterwards silently uses corrupted counts:Fix
Operate on a copy (
confusion_matrix[:, :2].copy()) so the input is left intact. The returned correlation value is unchanged.Test plan
test_compute_matthew_corr_does_not_mutate_inputintests/unit/evals/test_metrics.py: asserts the returned MCC is correct and the input matrix is unchanged. It fails onmain(matrix mutated) and passes with this change.pytest tests/unit/evals/test_metrics.py→ 5 passed.ruff checkclean.