BUG: zero result in Series.kurt for low variance arrays
#62405
Merged
Conversation
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
Alvaro-Kothe
changed the title
Series.kurt for low variance arraysSeries.kurt for low variance arrays
mroeschke
reviewed
Sep 22, 2025
| m4 = adjusted4.sum(axis, dtype=np.float64) | ||
|
|
||
| # Several floating point errors may occur during the summation due to rounding. | ||
| # We need to estimate an upper bound to the error to consider the data constant. |
There was a problem hiding this comment.
Could you also mention and maybe link to where Scipy does a similar calculation?
There was a problem hiding this comment.
I added the permalink. It's also important to point out that I adapted their code to use the maximum instead of the mean for scaling. I was worried about zero mean, resulting in tolerance=0. Let me know if it needs any further modifications.
mroeschke
approved these changes
Sep 22, 2025
|
Thanks @Alvaro-Kothe |
jzwick
pushed a commit
to jzwick/pandas
that referenced
this pull request
Oct 1, 2025
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Outdated suggestions cannot be applied.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.
doc/source/whatsnew/vX.X.X.rstfile if fixing a bug or adding a new feature.This PR fixes a bug in
Series.kurtwhere a fixed tolerance of1e-14caused incorrect results for low-variance arrays.The tolerance is now computed based on the data magnitude, using an approach based on SciPy's implementation.
Additional notes:
test_constant_seriesbecause it was only showingAssertionErrorwhen I broke this test.st.kurtosis(data, bias=False): 18.087646853025614st.kurtosis(data, bias=True): 14.916104870028551