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

Handle Interval scalars when passed in list-like inputs to cudf.Index #13956

Merged
merged 4 commits into from
Aug 25, 2023
Merged

Handle Interval scalars when passed in list-like inputs to cudf.Index #13956

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
f5e8039
Handle interval scalars in the form of a list
galipremsagar Aug 25, 2023
564b848
isort
galipremsagar Aug 25, 2023
5c610b1
Merge branch 'branch-23.10' into 13952
galipremsagar Aug 25, 2023
e4c4fff
black
galipremsagar Aug 25, 2023
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
10 changes: 7 additions & 3 deletions python/cudf/cudf/core/column/column.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2454,25 +2454,29 @@ def as_column(

def _construct_array(
arbitrary: Any, dtype: Optional[Dtype]
) -> Union[np.ndarray, cupy.ndarray]:
) -> Union[np.ndarray, cupy.ndarray, pd.api.extensions.ExtensionArray]:
"""
Construct a CuPy or NumPy array from `arbitrary`
Construct a CuPy/NumPy/Pandas array from `arbitrary`
"""
try:
dtype = dtype if dtype is None else cudf.dtype(dtype)
arbitrary = cupy.asarray(arbitrary, dtype=dtype)
except (TypeError, ValueError):
native_dtype = dtype
inferred_dtype = None
if (
dtype is None
and not cudf._lib.scalar._is_null_host_scalar(arbitrary)
and infer_dtype(arbitrary, skipna=False)
and (inferred_dtype := infer_dtype(arbitrary, skipna=False))
in (
"mixed",
"mixed-integer",
)
):
native_dtype = "object"
if inferred_dtype == "interval":
# Only way to construct an Interval column.
return pd.array(arbitrary)
arbitrary = np.asarray(
arbitrary,
dtype=native_dtype
Expand Down
13 changes: 13 additions & 0 deletions python/cudf/cudf/tests/test_interval.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -136,6 +136,19 @@ def test_create_interval_df(data1, data2, data3, data4, closed):
assert_eq(expect_three, got_three)


def test_create_interval_index_from_list():
interval_list = [
np.nan,
pd.Interval(2.0, 3.0, closed="right"),
pd.Interval(3.0, 4.0, closed="right"),
]

expected = pd.Index(interval_list)
actual = cudf.Index(interval_list)

assert_eq(expected, actual)


def test_interval_index_unique():
interval_list = [
np.nan,
Expand Down