Skip to content
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

Jump to bottom

fix: Properly choose inner physical type for Array #18942

Merged
merged 2 commits into from
Sep 26, 2024
Merged

fix: Properly choose inner physical type for Array #18942

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
9b32492
fix: Properly choose inner physical type for Array
coastalwhite Sep 26, 2024
2de8220
fix mypy
coastalwhite Sep 26, 2024
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
23 changes: 19 additions & 4 deletions crates/polars-core/src/chunked_array/ops/full.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -128,14 +128,21 @@ impl ArrayChunked {
ArrowDataType::FixedSizeList(
Box::new(ArrowField::new(
PlSmallStr::from_static("item"),
inner_dtype.to_arrow(CompatLevel::newest()),
inner_dtype.to_physical().to_arrow(CompatLevel::newest()),
true,
)),
width,
),
length,
);
ChunkedArray::with_chunk(name, arr)
// SAFETY: physical type matches the logical.
unsafe {
ChunkedArray::from_chunks_and_dtype(
name,
vec![Box::new(arr)],
DataType::Array(Box::new(inner_dtype.clone()), width),
)
}
}
}

Expand All @@ -147,14 +154,22 @@ impl ChunkFull<&Series> for ArrayChunked {
let arrow_dtype = ArrowDataType::FixedSizeList(
Box::new(ArrowField::new(
PlSmallStr::from_static("item"),
dtype.to_arrow(CompatLevel::newest()),
dtype.to_physical().to_arrow(CompatLevel::newest()),
true,
)),
width,
);
let value = value.rechunk().chunks()[0].clone();
let arr = FixedSizeListArray::full(length, value, arrow_dtype);
ChunkedArray::with_chunk(name, arr)

// SAFETY: physical type matches the logical.
unsafe {
ChunkedArray::from_chunks_and_dtype(
name,
vec![Box::new(arr)],
DataType::Array(Box::new(dtype.clone()), width),
)
}
}
}

Expand Down
15 changes: 15 additions & 0 deletions py-polars/tests/unit/datatypes/test_array.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -327,3 +327,18 @@ def test_array_inner_recursive_python_dtype() -> None:
def test_array_missing_shape() -> None:
with pytest.raises(TypeError):
pl.Array(pl.Int8)


def test_array_invalid_physical_type_18920() -> None:
s1 = pl.Series("x", [[1000, 2000]], pl.List(pl.Datetime))
s2 = pl.Series("x", [None], pl.List(pl.Datetime))

df1 = s1.to_frame().with_columns(pl.col.x.list.to_array(2))
df2 = s2.to_frame().with_columns(pl.col.x.list.to_array(2))

df = pl.concat([df1, df2])

expected_s = pl.Series("x", [[1000, 2000], None], pl.List(pl.Datetime))

expected = expected_s.to_frame().with_columns(pl.col.x.list.to_array(2))
assert_frame_equal(df, expected)
Loading