Skip to content

BUG: IntervalIndex.unique() only contains the first interval if all interval borders are negative #61920

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.

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
wants to merge 9 commits into
base: main
Choose a base branch
from
19 changes: 15 additions & 4 deletions pandas/core/arrays/interval.py
Original file line number Diff line number Diff line change
Expand Up @@ -1971,10 +1971,10 @@ def _from_combined(self, combined: np.ndarray) -> IntervalArray:
"""
Create a new IntervalArray with our dtype from a 1D complex128 ndarray.
"""
nc = combined.view("i8").reshape(-1, 2)

dtype = self._left.dtype
if needs_i8_conversion(dtype):
nc = combined.view("i8").reshape(-1, 2)
assert isinstance(self._left, (DatetimeArray, TimedeltaArray))
new_left: DatetimeArray | TimedeltaArray | np.ndarray = type(
self._left
Expand All @@ -1985,16 +1985,27 @@ def _from_combined(self, combined: np.ndarray) -> IntervalArray:
)._from_sequence(nc[:, 1], dtype=dtype)
else:
assert isinstance(dtype, np.dtype)
nc = np.hstack(
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

is the hstack really necessary here since the next 2 lines is just splitting them back up?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

thanks @jbrockmendel , It's not required. I'll change this.

[np.real(combined).astype(dtype), np.imag(combined).astype(dtype)]
).reshape(-1, 2)
new_left = nc[:, 0].view(dtype)
new_right = nc[:, 1].view(dtype)
return self._shallow_copy(left=new_left, right=new_right)

def unique(self) -> IntervalArray:
# No overload variant of "__getitem__" of "ExtensionArray" matches argument
# type "Tuple[slice, int]"
nc = unique(
self._combined.view("complex128")[:, 0] # type: ignore[call-overload]
)
if needs_i8_conversion(self._left.dtype):
nc = unique(
self._combined.view("complex128")[:, 0] # type: ignore[call-overload]
)
else:
nc = unique(
# Using .view("complex128") with negatives causes issues.
# GH#61917
(np.array(self._combined[:, 0], dtype=complex))
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

if this is More Correct, should we just patch inside _combined directly? The only other place it is used is isin; will there be an analaguos but there?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

yes, agree we can add this logic directly in _combined.

+ (1j * np.array(self._combined[:, 1], dtype=complex))
)
nc = nc[:, None]
return self._from_combined(nc)

Expand Down
25 changes: 25 additions & 0 deletions pandas/tests/arrays/interval/test_interval.py
Original file line number Diff line number Diff line change
Expand Up @@ -111,6 +111,31 @@ def test_shift_datetime(self):
with pytest.raises(TypeError, match=msg):
a.shift(1, fill_value=np.timedelta64("NaT", "ns"))

def test_unique_with_negatives(self):
# GH#61917
idx_pos = IntervalIndex.from_tuples(
[(3, 4), (3, 4), (2, 3), (2, 3), (1, 2), (1, 2)]
)
result = idx_pos.unique()
expected = IntervalIndex.from_tuples([(3, 4), (2, 3), (1, 2)])
tm.assert_index_equal(result, expected)

idx_neg = IntervalIndex.from_tuples(
[(-4, -3), (-4, -3), (-3, -2), (-3, -2), (-2, -1), (-2, -1)]
)
result = idx_neg.unique()
expected = IntervalIndex.from_tuples([(-4, -3), (-3, -2), (-2, -1)])
tm.assert_index_equal(result, expected)

idx_mix = IntervalIndex.from_tuples(
[(1, 2), (0, 1), (-1, 0), (-2, -1), (-3, -2), (-3, -2)]
)
result = idx_mix.unique()
expected = IntervalIndex.from_tuples(
[(1, 2), (0, 1), (-1, 0), (-2, -1), (-3, -2)]
)
tm.assert_index_equal(result, expected)


class TestSetitem:
def test_set_na(self, left_right_dtypes):
Expand Down
Loading