Skip to content

fix: Allow structured conversion to/from numpy with Array types, preserving shape #23438

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 1 commit into from
Jul 4, 2025
Merged

fix: Allow structured conversion to/from numpy with Array types, preserving shape #23438

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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: 0 additions & 3 deletions py-polars/polars/_utils/construction/dataframe.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1213,9 +1213,6 @@ def numpy_to_pydf(
n_columns = len(record_names)
for nm in record_names:
shape = data[nm].shape
if len(data[nm].shape) > 2:
msg = f"cannot create DataFrame from structured array with elements > 2D; shape[{nm!r}] = {shape}"
raise ValueError(msg)
if not schema:
schema = record_names
else:
Expand Down
2 changes: 1 addition & 1 deletion py-polars/polars/dataframe/frame.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2010,7 +2010,7 @@ def to_numpy(
if s.dtype == String and not s.has_nulls():
arr = arr.astype(str, copy=False)
arrays.append(arr)
struct_dtype.append((s.name, arr.dtype))
struct_dtype.append((s.name, arr.dtype, arr.shape[1:]))

out = np.empty(self.height, dtype=struct_dtype)
for idx, c in enumerate(self.columns):
Expand Down
17 changes: 17 additions & 0 deletions py-polars/tests/unit/interop/numpy/test_to_numpy_df.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -287,3 +287,20 @@ def test_to_numpy_c_order_1700() -> None:
df_chunked,
pl.from_numpy(df_chunked.to_numpy(order="c"), schema=df_chunked.schema),
)


def test_to_numpy_array_shape_23426() -> None:
df = pl.DataFrame(
{
"x": [1, 2],
"y": [[1.0, 2.0, 3.0], [4.0, 5.0, 6.0]],
"z": [[[-1, -1, -2], [4, 5, 6]], [[-3, -5, -8], [10, 20, 30]]],
},
schema={
"x": pl.UInt8,
"y": pl.Array(pl.Float32, 3),
"z": pl.Array(pl.Int16, (2, 3)),
},
)

assert_frame_equal(df, pl.from_numpy(df.to_numpy(structured=True)))
Loading