Merge branch 'main' into improve_error_message_for_missing_dependencies

Author: chilin0525

.pre-commit-config.yaml

@@ -1,4 +1,4 @@
-minimum_pre_commit_version: 2.15.0
+minimum_pre_commit_version: 4.0.0
 exclude: ^LICENSES/|\.(html|csv|svg)$
 # reserve "manual" for relatively slow hooks which we still want to run in CI
 default_stages: [
@@ -19,13 +19,13 @@ ci:
     skip: [pyright, mypy]
 repos:
 -   repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.9.9
+    rev: v0.11.4
     hooks:
     -   id: ruff
         args: [--exit-non-zero-on-fix]
         exclude: ^pandas/tests/frame/test_query_eval.py
     -   id: ruff
-        # TODO: remove autofixe-only rules when they are checked by ruff
+        # TODO: remove autofix only rules when they are checked by ruff
         name: ruff-selected-autofixes
         alias: ruff-selected-autofixes
         files: ^pandas
@@ -34,7 +34,7 @@ repos:
     -   id: ruff-format
         exclude: ^scripts|^pandas/tests/frame/test_query_eval.py
 -   repo: https://github.com/jendrikseipp/vulture
-    rev: 'v2.14'
+    rev: v2.14
     hooks:
       - id: vulture
         entry: python scripts/run_vulture.py
@@ -95,14 +95,14 @@ repos:
     - id: sphinx-lint
       args: ["--enable", "all", "--disable", "line-too-long"]
 -   repo: https://github.com/pre-commit/mirrors-clang-format
-    rev: v19.1.7
+    rev: v20.1.0
     hooks:
     - id: clang-format
       files: ^pandas/_libs/src|^pandas/_libs/include
       args: [-i]
       types_or: [c, c++]
 -   repo: https://github.com/trim21/pre-commit-mirror-meson
-    rev: v1.7.0
+    rev: v1.7.2
     hooks:
     - id: meson-fmt
       args: ['--inplace']

asv_bench/benchmarks/frame_methods.py

@@ -517,7 +517,7 @@ def setup(self):
         self.df = DataFrame(np.random.randn(1000, 100))
 
         self.s = Series(np.arange(1028.0))
-        self.df2 = DataFrame({i: self.s for i in range(1028)})
+        self.df2 = DataFrame(dict.fromkeys(range(1028), self.s))
         self.df3 = DataFrame(np.random.randn(1000, 3), columns=list("ABC"))
 
     def time_apply_user_func(self):

ci/code_checks.sh

@@ -72,9 +72,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Series.dt PR01" `# Accessors are implemented as classes, but we do not document the Parameters section` \
         -i "pandas.Period.freq GL08" \
         -i "pandas.Period.ordinal GL08" \
-        -i "pandas.Timestamp.max PR02" \
-        -i "pandas.Timestamp.min PR02" \
-        -i "pandas.Timestamp.resolution PR02" \
         -i "pandas.core.groupby.DataFrameGroupBy.plot PR02" \
         -i "pandas.core.groupby.SeriesGroupBy.plot PR02" \
         -i "pandas.core.resample.Resampler.quantile PR01,PR07" \

doc/source/whatsnew/v3.0.0.rst

@@ -68,6 +68,7 @@ Other enhancements
 - :func:`read_parquet` accepts ``to_pandas_kwargs`` which are forwarded to :meth:`pyarrow.Table.to_pandas` which enables passing additional keywords to customize the conversion to pandas, such as ``maps_as_pydicts`` to read the Parquet map data type as python dictionaries (:issue:`56842`)
 - :meth:`.DataFrameGroupBy.transform`, :meth:`.SeriesGroupBy.transform`, :meth:`.DataFrameGroupBy.agg`, :meth:`.SeriesGroupBy.agg`, :meth:`.SeriesGroupBy.apply`, :meth:`.DataFrameGroupBy.apply` now support ``kurt`` (:issue:`40139`)
 - :meth:`DataFrame.apply` supports using third-party execution engines like the Bodo.ai JIT compiler (:issue:`60668`)
+- :meth:`DataFrame.iloc` and :meth:`Series.iloc` now support boolean masks in ``__getitem__`` for more consistent indexing behavior (:issue:`60994`)
 - :meth:`DataFrameGroupBy.transform`, :meth:`SeriesGroupBy.transform`, :meth:`DataFrameGroupBy.agg`, :meth:`SeriesGroupBy.agg`, :meth:`RollingGroupby.apply`, :meth:`ExpandingGroupby.apply`, :meth:`Rolling.apply`, :meth:`Expanding.apply`, :meth:`DataFrame.apply` with ``engine="numba"`` now supports positional arguments passed as kwargs (:issue:`58995`)
 - :meth:`Rolling.agg`, :meth:`Expanding.agg` and :meth:`ExponentialMovingWindow.agg` now accept :class:`NamedAgg` aggregations through ``**kwargs`` (:issue:`28333`)
 - :meth:`Series.map` can now accept kwargs to pass on to func (:issue:`59814`)
@@ -762,6 +763,7 @@ Plotting
 - Bug in :meth:`DataFrame.plot.bar` with ``stacked=True`` where labels on stacked bars with zero-height segments were incorrectly positioned at the base instead of the label position of the previous segment (:issue:`59429`)
 - Bug in :meth:`DataFrame.plot.line` raising ``ValueError`` when set both color and a ``dict`` style (:issue:`59461`)
 - Bug in :meth:`DataFrame.plot` that causes a shift to the right when the frequency multiplier is greater than one. (:issue:`57587`)
+- Bug in :meth:`Series.plot` preventing a line and scatter plot from being aligned (:issue:`61005`)
 - Bug in :meth:`Series.plot` with ``kind="pie"`` with :class:`ArrowDtype` (:issue:`59192`)
 
 Groupby/resample/rolling
@@ -773,6 +775,7 @@ Groupby/resample/rolling
 - Bug in :meth:`.DataFrameGroupBy.quantile` when ``interpolation="nearest"`` is inconsistent with :meth:`DataFrame.quantile` (:issue:`47942`)
 - Bug in :meth:`.Resampler.interpolate` on a :class:`DataFrame` with non-uniform sampling and/or indices not aligning with the resulting resampled index would result in wrong interpolation (:issue:`21351`)
 - Bug in :meth:`DataFrame.ewm` and :meth:`Series.ewm` when passed ``times`` and aggregation functions other than mean (:issue:`51695`)
+- Bug in :meth:`DataFrame.resample` and :meth:`Series.resample` were not keeping the index name when the index had :class:`ArrowDtype` timestamp dtype (:issue:`61222`)
 - Bug in :meth:`DataFrame.resample` changing index type to :class:`MultiIndex` when the dataframe is empty and using an upsample method (:issue:`55572`)
 - Bug in :meth:`DataFrameGroupBy.agg` that raises ``AttributeError`` when there is dictionary input and duplicated columns, instead of returning a DataFrame with the aggregation of all duplicate columns. (:issue:`55041`)
 - Bug in :meth:`DataFrameGroupBy.apply` and :meth:`SeriesGroupBy.apply` for empty data frame with ``group_keys=False`` still creating output index using group keys. (:issue:`60471`)

environment.yml

@@ -80,7 +80,7 @@ dependencies:
   - flake8=7.1.0  # run in subprocess over docstring examples
   - mypy=1.13.0  # pre-commit uses locally installed mypy
   - tokenize-rt  # scripts/check_for_inconsistent_pandas_namespace.py
-  - pre-commit>=4.0.1
+  - pre-commit>=4.2.0
 
   # documentation
   - gitpython  # obtain contributors from git for whatsnew

pandas/_libs/tslibs/timedeltas.pyi

@@ -3,7 +3,6 @@ from typing import (
     ClassVar,
     Literal,
     TypeAlias,
-    TypeVar,
     overload,
 )
 
@@ -60,7 +59,6 @@ UnitChoices: TypeAlias = Literal[
     "nanos",
     "nanosecond",
 ]
-_S = TypeVar("_S", bound=timedelta)
 
 def get_unit_for_round(freq, creso: int) -> int: ...
 def disallow_ambiguous_unit(unit: str | None) -> None: ...
@@ -95,11 +93,11 @@ class Timedelta(timedelta):
     _value: int  # np.int64
     # error: "__new__" must return a class instance (got "Union[Timestamp, NaTType]")
     def __new__(  # type: ignore[misc]
-        cls: type[_S],
+        cls: type[Self],
         value=...,
         unit: str | None = ...,
         **kwargs: float | np.integer | np.floating,
-    ) -> _S | NaTType: ...
+    ) -> Self | NaTType: ...
     @classmethod
     def _from_value_and_reso(cls, value: np.int64, reso: int) -> Timedelta: ...
     @property

pandas/_libs/tslibs/timestamps.pyx

@@ -200,8 +200,9 @@ class MinMaxReso:
 
     See also: timedeltas.MinMaxReso
     """
-    def __init__(self, name):
+    def __init__(self, name, docstring):
         self._name = name
+        self.__doc__ = docstring
 
     def __get__(self, obj, type=None):
         cls = Timestamp
@@ -216,11 +217,15 @@ class MinMaxReso:
 
         if obj is None:
             # i.e. this is on the class, default to nanos
-            return cls(val)
+            result = cls(val)
         elif self._name == "resolution":
-            return Timedelta._from_value_and_reso(val, obj._creso)
+            result = Timedelta._from_value_and_reso(val, obj._creso)
         else:
-            return Timestamp._from_value_and_reso(val, obj._creso, tz=None)
+            result = Timestamp._from_value_and_reso(val, obj._creso, tz=None)
+
+        result.__doc__ = self.__doc__
+
+        return result
 
     def __set__(self, obj, value):
         raise AttributeError(f"{self._name} is not settable.")
@@ -235,9 +240,74 @@ cdef class _Timestamp(ABCTimestamp):
     dayofweek = _Timestamp.day_of_week
     dayofyear = _Timestamp.day_of_year
 
-    min = MinMaxReso("min")
-    max = MinMaxReso("max")
-    resolution = MinMaxReso("resolution")  # GH#21336, GH#21365
+    _docstring_min = """
+    Returns the minimum bound possible for Timestamp.
+
+    This property provides access to the smallest possible value that
+    can be represented by a Timestamp object.
+
+    Returns
+    -------
+    Timestamp
+
+    See Also
+    --------
+    Timestamp.max: Returns the maximum bound possible for Timestamp.
+    Timestamp.resolution: Returns the smallest possible difference between
+        non-equal Timestamp objects.
+
+    Examples
+    --------
+    >>> pd.Timestamp.min
+    Timestamp('1677-09-21 00:12:43.145224193')
+    """
+
+    _docstring_max = """
+    Returns the maximum bound possible for Timestamp.
+
+    This property provides access to the largest possible value that
+    can be represented by a Timestamp object.
+
+    Returns
+    -------
+    Timestamp
+
+    See Also
+    --------
+    Timestamp.min: Returns the minimum bound possible for Timestamp.
+    Timestamp.resolution: Returns the smallest possible difference between
+        non-equal Timestamp objects.
+
+    Examples
+    --------
+    >>> pd.Timestamp.max
+    Timestamp('2262-04-11 23:47:16.854775807')
+    """
+
+    _docstring_reso = """
+    Returns the smallest possible difference between non-equal Timestamp objects.
+
+    The resolution value is determined by the underlying representation of time
+    units and is equivalent to Timedelta(nanoseconds=1).
+
+    Returns
+    -------
+    Timedelta
+
+    See Also
+    --------
+    Timestamp.max: Returns the maximum bound possible for Timestamp.
+    Timestamp.min: Returns the minimum bound possible for Timestamp.
+
+    Examples
+    --------
+    >>> pd.Timestamp.resolution
+    Timedelta('0 days 00:00:00.000000001')
+    """
+
+    min = MinMaxReso("min", _docstring_min)
+    max = MinMaxReso("max", _docstring_max)
+    resolution = MinMaxReso("resolution", _docstring_reso)  # GH#21336, GH#21365
 
     @property
     def value(self) -> int:

pandas/core/algorithms.py

@@ -215,7 +215,7 @@ def _reconstruct_data(
         values = cls._from_sequence(values, dtype=dtype)  # type: ignore[assignment]
 
     else:
-        values = values.astype(dtype, copy=False)
+        values = values.astype(dtype, copy=False)  # type: ignore[assignment]
 
     return values
 

pandas/core/apply.py

@@ -327,7 +327,7 @@ def transform(self) -> DataFrame | Series:
             if is_series:
                 func = {com.get_callable_name(v) or v: v for v in func}
             else:
-                func = {col: func for col in obj}
+                func = dict.fromkeys(obj, func)
 
         if is_dict_like(func):
             func = cast(AggFuncTypeDict, func)

pandas/core/array_algos/quantile.py

@@ -102,7 +102,7 @@ def quantile_with_mask(
             interpolation=interpolation,
         )
 
-        result = np.asarray(result)
+        result = np.asarray(result)  # type: ignore[assignment]
         result = result.T
 
     return result
@@ -196,7 +196,7 @@ def _nanquantile(
         # Caller is responsible for ensuring mask shape match
         assert mask.shape == values.shape
         result = [
-            _nanquantile_1d(val, m, qs, na_value, interpolation=interpolation)
+            _nanquantile_1d(val, m, qs, na_value, interpolation=interpolation)  # type: ignore[arg-type]
             for (val, m) in zip(list(values), list(mask))
         ]
         if values.dtype.kind == "f":

pandas/core/arrays/_mixins.py

@@ -142,18 +142,12 @@ def view(self, dtype: Dtype | None = None) -> ArrayLike:
 
             dt64_values = arr.view(dtype)
             return DatetimeArray._simple_new(dt64_values, dtype=dtype)
-
         elif lib.is_np_dtype(dtype, "m") and is_supported_dtype(dtype):
             from pandas.core.arrays import TimedeltaArray
 
             td64_values = arr.view(dtype)
             return TimedeltaArray._simple_new(td64_values, dtype=dtype)
-
-        # error: Argument "dtype" to "view" of "_ArrayOrScalarCommon" has incompatible
-        # type "Union[ExtensionDtype, dtype[Any]]"; expected "Union[dtype[Any], None,
-        # type, _SupportsDType, str, Union[Tuple[Any, int], Tuple[Any, Union[int,
-        # Sequence[int]]], List[Any], _DTypeDict, Tuple[Any, Any]]]"
-        return arr.view(dtype=dtype)  # type: ignore[arg-type]
+        return arr.view(dtype=dtype)
 
     def take(
         self,

pandas/core/arrays/arrow/_arrow_utils.py

@@ -44,7 +44,7 @@ def pyarrow_array_to_numpy_and_mask(
         mask = pyarrow.BooleanArray.from_buffers(
             pyarrow.bool_(), len(arr), [None, bitmask], offset=arr.offset
         )
-        mask = np.asarray(mask)
+        mask = np.asarray(mask)  # type: ignore[assignment]
     else:
         mask = np.ones(len(arr), dtype=bool)
     return data, mask

pandas/core/arrays/arrow/array.py

@@ -2540,7 +2540,7 @@ def _str_get_dummies(self, sep: str = "|", dtype: NpDtype | None = None):
             dummies_dtype = np.bool_
         dummies = np.zeros(n_rows * n_cols, dtype=dummies_dtype)
         dummies[indices] = True
-        dummies = dummies.reshape((n_rows, n_cols))
+        dummies = dummies.reshape((n_rows, n_cols))  # type: ignore[assignment]
         result = type(self)(pa.array(list(dummies)))
         return result, uniques_sorted.to_pylist()
 

pandas/core/arrays/base.py

@@ -596,7 +596,7 @@ def to_numpy(
         if copy or na_value is not lib.no_default:
             result = result.copy()
         if na_value is not lib.no_default:
-            result[self.isna()] = na_value
+            result[self.isna()] = na_value  # type: ignore[index]
         return result
 
     # ------------------------------------------------------------------------

pandas/core/arrays/categorical.py

@@ -1853,7 +1853,7 @@ def value_counts(self, dropna: bool = True) -> Series:
             count = np.bincount(obs, minlength=ncat or 0)
         else:
             count = np.bincount(np.where(mask, code, ncat))
-            ix = np.append(ix, -1)
+            ix = np.append(ix, -1)  # type: ignore[assignment]
 
         ix = coerce_indexer_dtype(ix, self.dtype.categories)
         ix_categorical = self._from_backing_data(ix)

pandas/core/arrays/datetimelike.py

@@ -2394,7 +2394,7 @@ def take(
         )
 
         indices = np.asarray(indices, dtype=np.intp)
-        maybe_slice = lib.maybe_indices_to_slice(indices, len(self))
+        maybe_slice = lib.maybe_indices_to_slice(indices, len(self))  # type: ignore[arg-type]
 
         if isinstance(maybe_slice, slice):
             freq = self._get_getitem_freq(maybe_slice)

pandas/core/arrays/datetimes.py

@@ -331,7 +331,7 @@ def _simple_new(  # type: ignore[override]
         else:
             # DatetimeTZDtype. If we have e.g. DatetimeTZDtype[us, UTC],
             #  then values.dtype should be M8[us].
-            assert dtype._creso == get_unit_from_dtype(values.dtype)
+            assert dtype._creso == get_unit_from_dtype(values.dtype)  # type: ignore[union-attr]
 
         result = super()._simple_new(values, dtype)
         result._freq = freq
@@ -542,7 +542,7 @@ def _unbox_scalar(self, value) -> np.datetime64:
             raise ValueError("'value' should be a Timestamp.")
         self._check_compatible_with(value)
         if value is NaT:
-            return np.datetime64(value._value, self.unit)
+            return np.datetime64(value._value, self.unit)  # type: ignore[call-overload]
         else:
             return value.as_unit(self.unit, round_ok=False).asm8
 
@@ -813,10 +813,7 @@ def _add_offset(self, offset: BaseOffset) -> Self:
         try:
             res_values = offset._apply_array(values._ndarray)
             if res_values.dtype.kind == "i":
-                # error: Argument 1 to "view" of "ndarray" has incompatible type
-                # "dtype[datetime64] | DatetimeTZDtype"; expected
-                # "dtype[Any] | type[Any] | _SupportsDType[dtype[Any]]"
-                res_values = res_values.view(values.dtype)  # type: ignore[arg-type]
+                res_values = res_values.view(values.dtype)
         except NotImplementedError:
             if get_option("performance_warnings"):
                 warnings.warn(

pandas/core/arrays/masked.py

@@ -515,7 +515,7 @@ def tolist(self) -> list:
         if self.ndim > 1:
             return [x.tolist() for x in self]
         dtype = None if self._hasna else self._data.dtype
-        return self.to_numpy(dtype=dtype, na_value=libmissing.NA).tolist()
+        return self.to_numpy(dtype=dtype, na_value=libmissing.NA).tolist()  # type: ignore[return-value]
 
     @overload
     def astype(self, dtype: npt.DTypeLike, copy: bool = ...) -> np.ndarray: ...
@@ -1497,10 +1497,10 @@ def all(
         result = values.all(axis=axis)
 
         if skipna:
-            return result
+            return result  # type: ignore[return-value]
         else:
             if not result or len(self) == 0 or not self._mask.any():
-                return result
+                return result  # type: ignore[return-value]
             else:
                 return self.dtype.na_value
 

pandas/core/arrays/sparse/scipy_sparse.py

@@ -79,7 +79,7 @@ def _levels_to_axis(
         ax_coords = codes[valid_ilocs]
 
     ax_labels = ax_labels.tolist()
-    return ax_coords, ax_labels
+    return ax_coords, ax_labels  # pyright: ignore[reportReturnType]
 
 
 def _to_ijv(