Python generalized ndcg #1812
Merged
Python generalized ndcg #1812
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
ChuyangKe
requested review from
miguelgfierro,
gramhagen,
anargyri,
loomlike and
wutaomsft
as code owners
ChuyangKe
commented
Aug 18, 2022
| @@ -185,7 +185,7 @@ def test_python_ndcg_at_k(rating_true, rating_pred): | |||
| col_prediction=DEFAULT_PREDICTION_COL, | |||
| k=10, | |||
| ) | |||
| assert t.interval < 21.55627936 * (1 + TOL) | |||
There was a problem hiding this comment.
The new version takes more time, because for raw and exp scores, we need to sort the dataframe based on the true ratings. We can probably use the old version for binary, and new version for raw and exp.
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Outdated suggestions cannot be applied.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.
Description
Implemented a generalized version of NDCG. The function now supports three types of relevance scores: binary, raw, and exponential. It also supports two types of discount functions: natural log, and log2.
Related Issues
Related to issue: #1749. The example is added as a new test case for raw relevance scores.
Checklist:
staging branchand not tomain branch.