Merge branch 'main' into fix-issue-61221

Author: gsmll

.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/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/arrays/string_arrow.py

@@ -281,7 +281,7 @@ def isin(self, values: ArrayLike) -> npt.NDArray[np.bool_]:
         ]
 
         # short-circuit to return all False array.
-        if not len(value_set):
+        if not value_set:
             return np.zeros(len(self), dtype=bool)
 
         result = pc.is_in(

pandas/core/generic.py

@@ -9705,7 +9705,7 @@ def _where(
             # CoW: Make sure reference is not kept alive
             if cond.ndim == 1 and self.ndim == 2:
                 cond = cond._constructor_expanddim(
-                    {i: cond for i in range(len(self.columns))},
+                    dict.fromkeys(range(len(self.columns)), cond),
                     copy=False,
                 )
                 cond.columns = self.columns

pandas/core/groupby/generic.py

@@ -2505,7 +2505,7 @@ def _apply_to_column_groupbys(self, func) -> DataFrame:
         )
         results = [func(sgb) for sgb in sgbs]
 
-        if not len(results):
+        if not results:
             # concat would raise
             res_df = DataFrame([], columns=columns, index=self._grouper.result_index)
         else:

pandas/core/groupby/groupby.py

@@ -5175,8 +5175,8 @@ def diff(
                 shifted = shifted.astype("float32")
         else:
             to_coerce = [c for c, dtype in obj.dtypes.items() if dtype in dtypes_to_f32]
-            if len(to_coerce):
-                shifted = shifted.astype({c: "float32" for c in to_coerce})
+            if to_coerce:
+                shifted = shifted.astype(dict.fromkeys(to_coerce, "float32"))
 
         return obj - shifted
 

pandas/core/indexing.py

@@ -1582,11 +1582,7 @@ def _validate_key(self, key, axis: AxisInt) -> None:
         if com.is_bool_indexer(key):
             if hasattr(key, "index") and isinstance(key.index, Index):
                 if key.index.inferred_type == "integer":
-                    raise NotImplementedError(
-                        "iLocation based boolean "
-                        "indexing on an integer type "
-                        "is not available"
-                    )
+                    return
                 raise ValueError(
                     "iLocation based boolean indexing cannot use an indexable as a mask"
                 )

pandas/core/internals/blocks.py

@@ -805,7 +805,7 @@ def replace_list(
             for x, y in zip(src_list, dest_list)
             if (self._can_hold_element(x) or (self.dtype == "string" and is_re(x)))
         ]
-        if not len(pairs):
+        if not pairs:
             return [self.copy(deep=False)]
 
         src_len = len(pairs) - 1

pandas/core/internals/construction.py

@@ -864,7 +864,7 @@ def _finalize_columns_and_data(
         # GH#26429 do not raise user-facing AssertionError
         raise ValueError(err) from err
 
-    if len(contents) and contents[0].dtype == np.object_:
+    if contents and contents[0].dtype == np.object_:
         contents = convert_object_array(contents, dtype=dtype)
 
     return contents, columns

pandas/core/internals/managers.py

@@ -1298,7 +1298,7 @@ def value_getitem(placement):
                     # Defer setting the new values to enable consolidation
                     self._iset_split_block(blkno_l, blk_locs, refs=refs)
 
-        if len(removed_blknos):
+        if removed_blknos:
             # Remove blocks & update blknos accordingly
             is_deleted = np.zeros(self.nblocks, dtype=np.bool_)
             is_deleted[removed_blknos] = True

pandas/core/resample.py

@@ -518,6 +518,7 @@ def _wrap_result(self, result):
 
         if self._timegrouper._arrow_dtype is not None:
             result.index = result.index.astype(self._timegrouper._arrow_dtype)
+            result.index.name = self.obj.index.name
 
         return result
 

pandas/io/formats/format.py

@@ -566,7 +566,7 @@ def _initialize_colspace(self, col_space: ColspaceArgType | None) -> ColspaceTyp
             result = {}
         elif isinstance(col_space, (int, str)):
             result = {"": col_space}
-            result.update({column: col_space for column in self.frame.columns})
+            result.update(dict.fromkeys(self.frame.columns, col_space))
         elif isinstance(col_space, Mapping):
             for column in col_space.keys():
                 if column not in self.frame.columns and column != "":

pandas/io/formats/style_render.py

@@ -1225,7 +1225,7 @@ def format(
         data = self.data.loc[subset]
 
         if not isinstance(formatter, dict):
-            formatter = {col: formatter for col in data.columns}
+            formatter = dict.fromkeys(data.columns, formatter)
 
         cis = self.columns.get_indexer_for(data.columns)
         ris = self.index.get_indexer_for(data.index)
@@ -1411,7 +1411,7 @@ def format_index(
             return self  # clear the formatter / revert to default and avoid looping
 
         if not isinstance(formatter, dict):
-            formatter = {level: formatter for level in levels_}
+            formatter = dict.fromkeys(levels_, formatter)
         else:
             formatter = {
                 obj._get_level_number(level): formatter_
@@ -1708,7 +1708,7 @@ def format_index_names(
             return self  # clear the formatter / revert to default and avoid looping
 
         if not isinstance(formatter, dict):
-            formatter = {level: formatter for level in levels_}
+            formatter = dict.fromkeys(levels_, formatter)
         else:
             formatter = {
                 obj._get_level_number(level): formatter_

pandas/io/pytables.py

@@ -1760,7 +1760,7 @@ def info(self) -> str:
 
         if self.is_open:
             lkeys = sorted(self.keys())
-            if len(lkeys):
+            if lkeys:
                 keys = []
                 values = []
 
@@ -4540,7 +4540,7 @@ def write_data(self, chunksize: int | None, dropna: bool = False) -> None:
                     masks.append(mask.astype("u1", copy=False))
 
         # consolidate masks
-        if len(masks):
+        if masks:
             mask = masks[0]
             for m in masks[1:]:
                 mask = mask & m
@@ -4660,7 +4660,7 @@ def delete(
             groups = list(diff[diff > 1].index)
 
             # 1 group
-            if not len(groups):
+            if not groups:
                 groups = [0]
 
             # final element