Fix: Correct comparison direction in EpsilonDiagnosis.find_root_causes#68
Open
yqZhang4480 wants to merge 1 commit intosalesforce:mainfrom
Open
Fix: Correct comparison direction in EpsilonDiagnosis.find_root_causes#68yqZhang4480 wants to merge 1 commit intosalesforce:mainfrom
yqZhang4480 wants to merge 1 commit intosalesforce:mainfrom
Conversation
|
Thanks for the contribution! Before we can merge this, we need @yqZhang4480 to sign the Salesforce Inc. Contributor License Agreement. |
The original implementation incorrectly identified metrics with HIGH correlation as root causes. According to epsilon-Diagnosis algorithm, metrics with LOW correlation between normal and abnormal data should be flagged as root causes (indicating behavior change). Changes: - Change comparison from `>` to `<` for threshold check - Change sort order from descending to ascending (lower correlation = more suspicious) - Add assertion to test to verify correctness This fix improves Recall@1 from 0.02 to 0.09 and Recall@3 from 0.02 to 0.19 on generated datasets, matching the performance reported in README.
yqZhang4480
force-pushed
the
fix/epsilon-diagnosis-comparison
branch
from
7670f9c to
8e177e8
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
The original implementation incorrectly identified metrics with HIGH correlation as root causes. According to epsilon-Diagnosis algorithm, metrics with LOW correlation between normal and abnormal data should be flagged as root causes (indicating behavior change).
Changes
>to<for threshold checkImpact
This fix improves Recall@1 from 0.02 to 0.09 and Recall@3 from 0.02 to 0.19 on generated datasets (according to my test). The latter are more matching the performance reported in README.