Skip to content

Support for array-like and pandas-like data #470

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

Open
smathot wants to merge 3 commits into
base: main
Choose a base branch
from
Open

Support for array-like and pandas-like data #470

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
6029679
Be more flexible in accepting dataframe-like and array-like data
smathot Jun 19, 2025
dca6e63
Additional more flexible check in rm_corr()
smathot Jun 19, 2025
41df958
Reformat with ruff
smathot Jun 19, 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
4 changes: 2 additions & 2 deletions src/pingouin/correlation.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -830,7 +830,7 @@ def partial_corr(
"pearson",
"spearman",
], 'only "pearson" and "spearman" are supported for partial correlation.'
assert isinstance(data, pd.DataFrame), "data must be a pandas DataFrame."
assert hasattr(data, "__dataframe__"), "Data must be compatible with DataFrame"
assert data.shape[0] > 2, "Data must have at least 3 samples."
if covar is not None and (x_covar is not None or y_covar is not None):
raise ValueError("Cannot specify both covar and {x,y}_covar.")
Expand Down Expand Up @@ -1189,7 +1189,7 @@ def rm_corr(data=None, x=None, y=None, subject=None):
from pingouin import ancova, power_corr

# Safety checks
assert isinstance(data, pd.DataFrame), "Data must be a DataFrame"
assert hasattr(data, "__dataframe__"), "Data must be compatible with DataFrame"
assert x in data.columns, "The %s column is not in data." % x
assert y in data.columns, "The %s column is not in data." % y
assert data[x].dtype.kind in "bfiu", "%s must be numeric." % x
Expand Down
9 changes: 6 additions & 3 deletions src/pingouin/distribution.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -207,13 +207,16 @@ def normality(data, dv=None, group=None, method="shapiro", alpha=0.05):
Pre 0.304021 0.858979 True
Post 1.265656 0.531088 True
"""
assert isinstance(data, (pd.DataFrame, pd.Series, list, np.ndarray))
assert isinstance(data, (pd.DataFrame, pd.Series, list, np.ndarray)) or hasattr(
data, "__dataframe__"
)
assert method in ["shapiro", "normaltest", "jarque_bera"]
if isinstance(data, pd.Series):
data = data.to_frame()
col_names = ["W", "pval"]
func = getattr(scipy.stats, method)
if isinstance(data, (list, np.ndarray)):
# Check if the data is 1D array-like
if isinstance(data, (list, np.ndarray)) or (hasattr(data, "__array__") and data.ndim == 1):
data = np.asarray(data)
assert data.ndim == 1, "Data must be 1D."
assert data.size > 3, "Data must have more than 3 samples."
Expand All @@ -222,7 +225,7 @@ def normality(data, dv=None, group=None, method="shapiro", alpha=0.05):
stats.columns = col_names
stats["normal"] = np.where(stats["pval"] > alpha, True, False)
else:
# Data is a Pandas DataFrame
# Any other kind of data is assumed to be DataFrame-like
if dv is None and group is None:
# Wide-format
# Get numeric data only
Expand Down
Loading