Skip to content

type datetimeindex constructor #1120

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 7 commits into from
Feb 18, 2025
Merged

type datetimeindex constructor #1120

Show file tree
Hide file tree
Changes from 6 commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
6dac3a1
type datetimeindex constructor
MarcoGorelli Feb 14, 2025
f7ae655
leave out index.to_frame name for now
MarcoGorelli Feb 14, 2025
4487a36
correct name annotation for MultiIndex
MarcoGorelli Feb 17, 2025
244d985
type names too
MarcoGorelli Feb 17, 2025
d9952ef
naming
MarcoGorelli Feb 17, 2025
fb87799
looks like we do need __new__
MarcoGorelli Feb 17, 2025
5f6a4f4
remove MultiIndex.__init__
MarcoGorelli Feb 18, 2025
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
40 changes: 20 additions & 20 deletions pandas-stubs/core/indexes/base.pyi
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -73,7 +73,7 @@ class Index(IndexOpsMixin[S1]):
*,
dtype: Literal["int"] | type_t[int | np.integer] = ...,
copy: bool = ...,
name=...,
name: Hashable = ...,
tupleize_cols: bool = ...,
**kwargs,
) -> Index[int]: ...
Expand All @@ -84,7 +84,7 @@ class Index(IndexOpsMixin[S1]):
*,
dtype: Literal["int"] | type_t[int | np.integer],
copy: bool = ...,
name=...,
name: Hashable = ...,
tupleize_cols: bool = ...,
**kwargs,
) -> Index[int]: ...
Expand All @@ -95,7 +95,7 @@ class Index(IndexOpsMixin[S1]):
*,
dtype: Literal["float"] | type_t[float | np.floating] = ...,
copy: bool = ...,
name=...,
name: Hashable = ...,
tupleize_cols: bool = ...,
**kwargs,
) -> Index[float]: ...
Expand All @@ -106,7 +106,7 @@ class Index(IndexOpsMixin[S1]):
*,
dtype: Literal["float"] | type_t[float | np.floating],
copy: bool = ...,
name=...,
name: Hashable = ...,
tupleize_cols: bool = ...,
**kwargs,
) -> Index[float]: ...
Expand All @@ -121,7 +121,7 @@ class Index(IndexOpsMixin[S1]):
*,
dtype: Literal["complex"] | type_t[complex | np.complexfloating] = ...,
copy: bool = ...,
name=...,
name: Hashable = ...,
tupleize_cols: bool = ...,
**kwargs,
) -> Index[complex]: ...
Expand All @@ -132,7 +132,7 @@ class Index(IndexOpsMixin[S1]):
*,
dtype: Literal["complex"] | type_t[complex | np.complexfloating],
copy: bool = ...,
name=...,
name: Hashable = ...,
tupleize_cols: bool = ...,
**kwargs,
) -> Index[complex]: ...
Expand All @@ -144,7 +144,7 @@ class Index(IndexOpsMixin[S1]):
*,
dtype: TimestampDtypeArg = ...,
copy: bool = ...,
name=...,
name: Hashable = ...,
tupleize_cols: bool = ...,
**kwargs,
) -> DatetimeIndex: ...
Expand All @@ -155,7 +155,7 @@ class Index(IndexOpsMixin[S1]):
*,
dtype: TimestampDtypeArg,
copy: bool = ...,
name=...,
name: Hashable = ...,
tupleize_cols: bool = ...,
**kwargs,
) -> DatetimeIndex: ...
Expand All @@ -166,7 +166,7 @@ class Index(IndexOpsMixin[S1]):
*,
dtype: PeriodDtype = ...,
copy: bool = ...,
name=...,
name: Hashable = ...,
tupleize_cols: bool = ...,
**kwargs,
) -> PeriodIndex: ...
Expand All @@ -177,7 +177,7 @@ class Index(IndexOpsMixin[S1]):
*,
dtype: PeriodDtype,
copy: bool = ...,
name=...,
name: Hashable = ...,
tupleize_cols: bool = ...,
**kwargs,
) -> PeriodIndex: ...
Expand All @@ -188,7 +188,7 @@ class Index(IndexOpsMixin[S1]):
*,
dtype: TimedeltaDtypeArg = ...,
copy: bool = ...,
name=...,
name: Hashable = ...,
tupleize_cols: bool = ...,
**kwargs,
) -> TimedeltaIndex: ...
Expand All @@ -199,7 +199,7 @@ class Index(IndexOpsMixin[S1]):
*,
dtype: TimedeltaDtypeArg,
copy: bool = ...,
name=...,
name: Hashable = ...,
tupleize_cols: bool = ...,
**kwargs,
) -> TimedeltaIndex: ...
Expand All @@ -210,7 +210,7 @@ class Index(IndexOpsMixin[S1]):
*,
dtype: Literal["Interval"] = ...,
copy: bool = ...,
name=...,
name: Hashable = ...,
tupleize_cols: bool = ...,
**kwargs,
) -> IntervalIndex[Interval[_OrderableT]]: ...
Expand All @@ -221,7 +221,7 @@ class Index(IndexOpsMixin[S1]):
*,
dtype: Literal["Interval"],
copy: bool = ...,
name=...,
name: Hashable = ...,
tupleize_cols: bool = ...,
**kwargs,
) -> IntervalIndex[Interval[Any]]: ...
Expand All @@ -233,7 +233,7 @@ class Index(IndexOpsMixin[S1]):
*,
dtype: type[S1] = ...,
copy: bool = ...,
name=...,
name: Hashable = ...,
tupleize_cols: bool = ...,
**kwargs,
) -> Self: ...
Expand All @@ -244,7 +244,7 @@ class Index(IndexOpsMixin[S1]):
*,
dtype: type[S1],
copy: bool = ...,
name=...,
name: Hashable = ...,
tupleize_cols: bool = ...,
**kwargs,
) -> Self: ...
Expand All @@ -256,7 +256,7 @@ class Index(IndexOpsMixin[S1]):
*,
dtype=...,
copy: bool = ...,
name=...,
name: Hashable = ...,
tupleize_cols: bool = ...,
**kwargs,
) -> Self: ...
Expand All @@ -277,14 +277,14 @@ class Index(IndexOpsMixin[S1]):
self, indices, axis: int = ..., allow_fill: bool = ..., fill_value=..., **kwargs
): ...
def repeat(self, repeats, axis=...): ...
def copy(self, name=..., deep: bool = ...) -> Self: ...
def copy(self, name: Hashable = ..., deep: bool = ...) -> Self: ...
def __copy__(self, **kwargs): ...
def __deepcopy__(self, memo=...): ...
def format(
self, name: bool = ..., formatter: Callable | None = ..., na_rep: _str = ...
) -> list[_str]: ...
def to_flat_index(self): ...
def to_series(self, index=..., name=...) -> Series: ...
def to_series(self, index=..., name: Hashable = ...) -> Series: ...
def to_frame(self, index: bool = ..., name=...) -> DataFrame: ...
@property
def name(self): ...
Expand Down Expand Up @@ -341,7 +341,7 @@ class Index(IndexOpsMixin[S1]):
def intersection(self, other: list[S1] | Self, sort: bool = ...) -> Self: ...
def difference(self, other: list | Index, sort: bool | None = None) -> Self: ...
def symmetric_difference(
self, other: list[S1] | Self, result_name=..., sort=...
self, other: list[S1] | Self, result_name: Hashable = ..., sort=...
) -> Self: ...
def get_loc(
self,
Expand Down
7 changes: 5 additions & 2 deletions pandas-stubs/core/indexes/category.pyi
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,7 @@
from collections.abc import Iterable
from collections.abc import (
Hashable,
Iterable,
)
from typing import Literal

import numpy as np
Expand All @@ -22,7 +25,7 @@ class CategoricalIndex(ExtensionIndex[S1], accessor.PandasDelegate):
ordered=...,
dtype=...,
copy: bool = ...,
name=...,
name: Hashable = ...,
) -> Self: ...
def equals(self, other): ...
@property
Expand Down
16 changes: 10 additions & 6 deletions pandas-stubs/core/indexes/datetimes.pyi
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,10 @@ from datetime import (
)
from typing import overload

from _typing import TimeZones
from _typing import (
Frequency,
TimeZones,
)
import numpy as np
from pandas import (
DataFrame,
Expand All @@ -29,6 +32,7 @@ from pandas._typing import (
AnyArrayLike,
ArrayLike,
DateAndDatetimeLike,
Dtype,
IntervalClosedType,
TimeUnit,
)
Expand All @@ -41,14 +45,14 @@ class DatetimeIndex(DatetimeTimedeltaMixin[Timestamp], DatetimeIndexProperties):
def __init__(
self,
data: ArrayLike | AnyArrayLike | list | tuple,
freq=...,
tz=...,
freq: Frequency = ...,
tz: TimeZones = ...,
ambiguous: str = ...,
dayfirst: bool = ...,
yearfirst: bool = ...,
dtype=...,
dtype: Dtype = ...,
copy: bool = ...,
name=...,
name: Hashable = ...,
) -> None: ...
def __array__(self, dtype=...) -> np.ndarray: ...
def __reduce__(self): ...
Expand All @@ -70,7 +74,7 @@ class DatetimeIndex(DatetimeTimedeltaMixin[Timestamp], DatetimeIndexProperties):
def __sub__(
self, other: datetime | Timestamp | DatetimeIndex
) -> TimedeltaIndex: ...
def to_series(self, index=..., name=...) -> TimestampSeries: ...
def to_series(self, index=..., name: Hashable = ...) -> TimestampSeries: ...
def snap(self, freq: str = ...): ...
def slice_indexer(self, start=..., end=..., step=...): ...
def searchsorted(self, value, side: str = ..., sorter=...): ...
Expand Down
25 changes: 17 additions & 8 deletions pandas-stubs/core/indexes/multi.pyi
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,7 @@ from typing import (
overload,
)

from _typing import SequenceNotStr
import numpy as np
import pandas as pd
from pandas.core.indexes.base import Index
Expand All @@ -29,10 +30,10 @@ class MultiIndex(Index[Any]):
levels=...,
codes=...,
sortorder=...,
names=...,
names: SequenceNotStr[Hashable] = ...,
dtype=...,
copy=...,
name=...,
name: SequenceNotStr[Hashable] = ...,
verify_integrity: bool = ...,
_set_identity: bool = ...,
) -> Self: ...
Expand All @@ -41,21 +42,29 @@ class MultiIndex(Index[Any]):
levels=...,
codes=...,
sortorder=...,
names=...,
names: SequenceNotStr[Hashable] = ...,
dtype=...,
copy=...,
name=...,
name: SequenceNotStr[Hashable] = ...,
verify_integrity: bool = ...,
_set_identity: bool = ...,
) -> None: ...
Copy link
Collaborator

Choose a reason for hiding this comment

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

We have an opportunity for cleanup here. No need to have both __new__() and __init__(). We should just have __init__(). We use __new__() instead of __init__() in the stubs when we want to return different subclasses based on the arguments. But for MultiIndex, that isn't the case. So we can delete __new__().

Ideally, we'd have types for all of the arguments, which will have to be based on the 3.0 docs, because the docs did get updated to correspond to what is in the code (which doesn't have _set_identity.

For this PR, I'm OK if you don't do them all, BUT names and name need to be SequenceNotStr[Hashable]

Copy link
Member Author

Choose a reason for hiding this comment

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

thanks Irv! sure, I corrected name for multiindex, sorry for not having spotted that

Copy link
Member Author

Choose a reason for hiding this comment

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

Looks like we might need MultiIndex.__new__ too, else the test I added fails pyright with

  /home/marcogorelli/pandas-stubs-dev/tests/test_indexes.py:70:62 - error: Argument of type "list[str]" cannot be assigned to parameter "name" of type "Hashable" in function "__new__"
    "list[str]" is incompatible with protocol "Hashable"

Copy link
Collaborator

Choose a reason for hiding this comment

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

Interesting. I guess because the parent class uses __new__(), then the subclass has to do it as well. So for MultiIndex, we should provide __new__() and not provide __init__()

@classmethod
def from_arrays(cls, arrays, sortorder=..., names=...) -> Self: ...
def from_arrays(
cls, arrays, sortorder=..., names: SequenceNotStr[Hashable] = ...
) -> Self: ...
@classmethod
def from_tuples(cls, tuples, sortorder=..., names=...) -> Self: ...
def from_tuples(
cls, tuples, sortorder=..., names: SequenceNotStr[Hashable] = ...
) -> Self: ...
@classmethod
def from_product(cls, iterables, sortorder=..., names=...) -> Self: ...
def from_product(
cls, iterables, sortorder=..., names: SequenceNotStr[Hashable] = ...
) -> Self: ...
@classmethod
def from_frame(cls, df, sortorder=..., names=...) -> Self: ...
def from_frame(
cls, df, sortorder=..., names: SequenceNotStr[Hashable] = ...
) -> Self: ...
@property
def shape(self): ...
@property # Should be read-only
Expand Down
2 changes: 1 addition & 1 deletion pandas-stubs/core/indexes/period.pyi
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,7 +26,7 @@ class PeriodIndex(DatetimeIndexOpsMixin[pd.Period], PeriodIndexFieldOps):
tz=...,
dtype=...,
copy: bool = ...,
name=...,
name: Hashable = ...,
**fields,
): ...
@property
Expand Down
11 changes: 7 additions & 4 deletions pandas-stubs/core/indexes/range.pyi
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,7 @@
from collections.abc import Sequence
from collections.abc import (
Hashable,
Sequence,
)
from typing import overload

import numpy as np
Expand All @@ -19,10 +22,10 @@ class RangeIndex(Index[int]):
step: int = ...,
dtype=...,
copy: bool = ...,
name=...,
name: Hashable = ...,
): ...
@classmethod
def from_range(cls, data, name=..., dtype=...): ...
def from_range(cls, data, name: Hashable = ..., dtype=...): ...
def __reduce__(self): ...
@property
def start(self) -> int: ...
Expand All @@ -46,7 +49,7 @@ class RangeIndex(Index[int]):
def __contains__(self, key: int | np.integer) -> bool: ...
def get_indexer(self, target, method=..., limit=..., tolerance=...): ...
def tolist(self): ...
def copy(self, name=..., deep: bool = ..., dtype=..., **kwargs): ...
def copy(self, name: Hashable = ..., deep: bool = ..., dtype=..., **kwargs): ...
def min(self, axis=..., skipna: bool = ..., *args, **kwargs): ...
def max(self, axis=..., skipna: bool = ..., *args, **kwargs): ...
def argsort(self, *args, **kwargs): ...
Expand Down
2 changes: 1 addition & 1 deletion pandas-stubs/core/indexes/timedeltas.pyi
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -76,7 +76,7 @@ class TimedeltaIndex(DatetimeTimedeltaMixin[Timedelta], TimedeltaIndexProperties
@property
def inferred_type(self) -> str: ...
def insert(self, loc, item): ...
def to_series(self, index=..., name=...) -> TimedeltaSeries: ...
def to_series(self, index=..., name: Hashable = ...) -> TimedeltaSeries: ...

def timedelta_range(
start: TimedeltaConvertibleTypes = ...,
Expand Down
31 changes: 31 additions & 0 deletions tests/test_indexes.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -64,6 +64,21 @@ def test_multiindex_get_level_values() -> None:
check(assert_type(i1, pd.Index), pd.Index)


def test_multiindex_constructor() -> None:
check(
assert_type(
pd.MultiIndex([[1], [4]], codes=[[0], [0]], name=["a", "b"]), pd.MultiIndex
),
pd.MultiIndex,
)
check(
assert_type(
pd.MultiIndex([[1], [4]], codes=[[0], [0]], names=["a", "b"]), pd.MultiIndex
),
pd.MultiIndex,
)


def test_index_tolist() -> None:
i1 = pd.Index([1, 2, 3])
check(assert_type(i1.tolist(), list[int]), list, int)
Expand Down Expand Up @@ -1053,6 +1068,22 @@ def test_index_constructors():
pd.Index(flist, dtype=np.float16)


def test_datetime_index_constructor() -> None:
check(assert_type(pd.DatetimeIndex(["2020"]), pd.DatetimeIndex), pd.DatetimeIndex)
check(
assert_type(pd.DatetimeIndex(["2020"], name="ts"), pd.DatetimeIndex),
pd.DatetimeIndex,
)
check(
assert_type(pd.DatetimeIndex(["2020"], freq="D"), pd.DatetimeIndex),
pd.DatetimeIndex,
)
check(
assert_type(pd.DatetimeIndex(["2020"], tz="Asia/Kathmandu"), pd.DatetimeIndex),
pd.DatetimeIndex,
)


def test_iter() -> None:
# GH 723
with pytest_warns_bounded(
Expand Down