Set non iid num issues with an extra rule #707
Merged
Conversation
This file contains 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
A new heuristic is used, where a low p_value indicates that at least one datapoint in the dataset should have an issue. Otherwise, we disregard the number of issues overall.
…dataset Previously, no example was flagged. With the new heuristic, the "worst" scoring example is flagged.
jwmueller
reviewed
May 9, 2023
| @@ -89,7 +89,7 @@ def test_find_issues(self, issue_manager, embeddings): | |||
| issue_manager.summary, | |||
There was a problem hiding this comment.
can we add more end-to-end tests of the noniid check at the datalab level?
jwmueller
reviewed
May 9, 2023
jwmueller
reviewed
May 9, 2023
Codecov Report
@@ Coverage Diff @@
## master #707 +/- ##
==========================================
- Coverage 95.74% 95.46% -0.28%
==========================================
Files 46 46
Lines 3642 3639 -3
Branches 650 645 -5
==========================================
- Hits 3487 3474 -13
- Misses 80 85 +5
- Partials 75 80 +5
|
…iid issue manager
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
With this PR, we perform an additional check for the number of issues when we have a low p-value (under 0.05), vs a high p-value.
We have to change the number of issues in the
is_non_iid_issuecolumn for this to take effect in the issue summary.