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
21 changes: 11 additions & 10 deletions pandas/core/arrays/interval.py
Original file line number Diff line number Diff line change
Expand Up @@ -1932,16 +1932,16 @@ def isin(self, values: ArrayLike) -> npt.NDArray[np.bool_]:
if self.dtype == values.dtype:
# GH#38353 instead of casting to object, operating on a
# complex128 ndarray is much more performant.
left = self._combined.view("complex128")
right = values._combined.view("complex128")
left = self._combined
right = values._combined
# error: Argument 1 to "isin" has incompatible type
# "Union[ExtensionArray, ndarray[Any, Any],
# ndarray[Any, dtype[Any]]]"; expected
# "Union[_SupportsArray[dtype[Any]],
# _NestedSequence[_SupportsArray[dtype[Any]]], bool,
# int, float, complex, str, bytes, _NestedSequence[
# Union[bool, int, float, complex, str, bytes]]]"
return np.isin(left, right).ravel() # type: ignore[arg-type]
return np.isin(left, right).ravel()

elif needs_i8_conversion(self.left.dtype) ^ needs_i8_conversion(
values.left.dtype
Expand All @@ -1963,18 +1963,21 @@ def _combined(self) -> IntervalSide:
comb = left._concat_same_type( # type: ignore[union-attr]
[left, right], axis=1
)
comb = comb.view("complex128")[:, 0]
else:
comb = np.concatenate([left, right], axis=1)
comb = (np.array(left.ravel(), dtype=complex)) + (
1j * np.array(right.ravel(), dtype=complex)
)
return comb

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 +1988,14 @@ def _from_combined(self, combined: np.ndarray) -> IntervalArray:
)._from_sequence(nc[:, 1], dtype=dtype)
else:
assert isinstance(dtype, np.dtype)
new_left = nc[:, 0].view(dtype)
new_right = nc[:, 1].view(dtype)
new_left = np.real(combined).astype(dtype).ravel()
new_right = np.imag(combined).astype(dtype).ravel()
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]
)
nc = unique(self._combined)
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