Skip to content

Fixes #453: _correl_pvalue does not divide by zero if r==1 #474

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
raphaelvallat merged 3 commits into from
Aug 30, 2025
Merged

Fixes #453: _correl_pvalue does not divide by zero if r==1 #474

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
f222fd7
Fixes #453
AlexanderJCS Jul 12, 2025
e66cd7c
Add test for perfect correlation using percbend method
AlexanderJCS Jul 25, 2025
c1070de
Reformat file
AlexanderJCS Jul 25, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions src/pingouin/correlation.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -54,6 +54,9 @@ def _correl_pvalue(r, n, k=0, alternative="two-sided"):
"less",
], "Alternative must be one of 'two-sided' (default), 'greater' or 'less'."

if np.isclose(r**2, 1): # Avoid divide by zero error
return 0.0 # Since p value approaches 0 as r approaches 1, just return 0

Copy link
Owner

@raphaelvallat raphaelvallat Jul 23, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can you please add a test in https://github.com/raphaelvallat/pingouin/blob/main/tests/test_correlation.py test_corr function:

stats = corr(x, x, method="percbend")  # calls _correl_pvalue
assert np.isclose(stats.at["percbend", "r"], 1)
assert np.isclose(stats.at["percbend", "p_val"], 0)

Copy link
Contributor Author

@AlexanderJCS AlexanderJCS Jul 25, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Hi Raphael, I added these lines in the test_corr(self) function under the perfect correlation test for the pearson method.

# Method 1: using a student T distribution
dof = n - k - 2
tval = r * np.sqrt(dof / (1 - r**2))
Expand Down
7 changes: 7 additions & 0 deletions tests/test_correlation.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -115,6 +115,13 @@ def test_corr(self):
stats = corr(x, x)
assert np.isclose(stats.at["pearson", "r"], 1)
assert np.isclose(stats.at["pearson", "power"], 1)

# Perfect correlation with percbend method
# https://github.com/raphaelvallat/pingouin/issues/453
stats = corr(x, x, method="percbend") # calls _correl_pvalue
assert np.isclose(stats.at["percbend", "r"], 1)
assert np.isclose(stats.at["percbend", "p_val"], 0)

# When one column is a constant, the correlation is not defined
# and Pingouin return a DataFrame full of NaN, except for ``n``
x, y = [1, 1, 1], [1, 2, 3]
Expand Down
Loading