Skip to content

fix(skore): Convert DataFrame column names to strings #2034

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
merged 3 commits into from
Oct 7, 2025
Merged

fix(skore): Convert DataFrame column names to strings #2034

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
eca2659
fix: convert DataFrame column names to string type
waridrox Sep 15, 2025
c2c8de7
test: Added tests to assert different column types in DataFrame
waridrox Sep 16, 2025
b33ad33
test: Simplify tests
auguste-probabl Sep 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
11 changes: 11 additions & 0 deletions skore/src/skore/_sklearn/_estimator/data_accessor.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -50,6 +50,10 @@ def _retrieve_data_as_frame(
raise ValueError(err_msg.format(f"X_{dataset}", data_source))
elif not sbd.is_dataframe(X):
X = pd.DataFrame(X, columns=[f"Feature {i}" for i in range(X.shape[1])])
else:
if not all(isinstance(col, str) for col in X.columns):
X = X.copy()
X.columns = [str(col) for col in X.columns]

if with_y:
if y is None:
Expand All @@ -63,6 +67,13 @@ def _retrieve_data_as_frame(
else:
columns = [f"Target {i}" for i in range(y.shape[1])]
y = pd.DataFrame(y, columns=columns)
else:
if not all(isinstance(col, str) for col in y.columns):
y = y.copy()
if y.shape[1] == 1 and list(y.columns) == [0]:
y.columns = ["Target"]
else:
y.columns = [str(col) for col in y.columns]

return X, y

Expand Down
3 changes: 3 additions & 0 deletions skore/tests/unit/displays/table_report/test_estimator.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -69,6 +69,8 @@ def test_constructor(display):
pd.DataFrame(
np.ones((100, 5)), columns=[f"Feature number {i}" for i in range(5)]
),
pd.DataFrame(np.ones((100, 5))),
pd.DataFrame(np.ones((100, 5)), columns=["a", 1, "c", 3, "e"]),
],
)
@pytest.mark.parametrize(
Expand All @@ -78,6 +80,7 @@ def test_constructor(display):
np.ones(100),
pd.Series(np.ones(100)),
pd.DataFrame(np.ones((100, 1)), columns=["Target"]),
pd.DataFrame(np.ones((100, 1))),
],
)
def test_X_y(X, y):
Expand Down
Loading