Merge branch 'main' of https://github.com/pandas-dev/pandas

Author: xaris96

.github/workflows/wheels.yml

@@ -153,7 +153,7 @@ jobs:
         run: echo "sdist_name=$(cd ./dist && ls -d */)" >> "$GITHUB_ENV"
 
       - name: Build wheels
-        uses: pypa/cibuildwheel@v2.23.1
+        uses: pypa/cibuildwheel@v2.23.2
         with:
          package-dir: ./dist/${{ startsWith(matrix.buildplat[1], 'macosx') && env.sdist_name || needs.build_sdist.outputs.sdist_file }}
         env:

.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):

asv_bench/benchmarks/indexing_engines.py

@@ -67,6 +67,14 @@ class NumericEngineIndexing:
     def setup(self, engine_and_dtype, index_type, unique, N):
         engine, dtype = engine_and_dtype
 
+        if (
+            index_type == "non_monotonic"
+            and dtype in [np.int16, np.int8, np.uint8]
+            and unique
+        ):
+            # Values overflow
+            raise NotImplementedError
+
         if index_type == "monotonic_incr":
             if unique:
                 arr = np.arange(N * 3, dtype=dtype)
@@ -115,6 +123,14 @@ def setup(self, engine_and_dtype, index_type, unique, N):
         engine, dtype = engine_and_dtype
         dtype = dtype.lower()
 
+        if (
+            index_type == "non_monotonic"
+            and dtype in ["int16", "int8", "uint8"]
+            and unique
+        ):
+            # Values overflow
+            raise NotImplementedError
+
         if index_type == "monotonic_incr":
             if unique:
                 arr = np.arange(N * 3, dtype=dtype)

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/development/debugging_extensions.rst

@@ -23,7 +23,7 @@ By default building pandas from source will generate a release build. To generat
 
 .. note::
 
-   conda environments update CFLAGS/CPPFLAGS with flags that are geared towards generating releases. If using conda, you may need to set ``CFLAGS="$CFLAGS -O0"`` and ``CPPFLAGS="$CPPFLAGS -O0"`` to ensure optimizations are turned off for debugging
+   conda environments update CFLAGS/CPPFLAGS with flags that are geared towards generating releases, and may work counter towards usage in a development environment. If using conda, you should unset these environment variables via ``export CFLAGS=`` and ``export CPPFLAGS=``
 
 By specifying ``builddir="debug"`` all of the targets will be built and placed in the debug directory relative to the project root. This helps to keep your debug and release artifacts separate; you are of course able to choose a different directory name or omit altogether if you do not care to separate build types.
 

doc/source/getting_started/comparison/comparison_with_r.rst

@@ -383,7 +383,7 @@ In Python, since ``a`` is a list, you can simply use list comprehension.
 
 .. ipython:: python
 
-   a = np.array(list(range(1, 24)) + [np.NAN]).reshape(2, 3, 4)
+   a = np.array(list(range(1, 24)) + [np.nan]).reshape(2, 3, 4)
    pd.DataFrame([tuple(list(x) + [val]) for x, val in np.ndenumerate(a)])
 
 meltlist
@@ -402,7 +402,7 @@ In Python, this list would be a list of tuples, so
 
 .. ipython:: python
 
-   a = list(enumerate(list(range(1, 5)) + [np.NAN]))
+   a = list(enumerate(list(range(1, 5)) + [np.nan]))
    pd.DataFrame(a)
 
 For more details and examples see :ref:`the Intro to Data Structures

doc/source/user_guide/basics.rst

@@ -2064,12 +2064,12 @@ different numeric dtypes will **NOT** be combined. The following example will gi
 
 .. ipython:: python
 
-   df1 = pd.DataFrame(np.random.randn(8, 1), columns=["A"], dtype="float32")
+   df1 = pd.DataFrame(np.random.randn(8, 1), columns=["A"], dtype="float64")
    df1
    df1.dtypes
    df2 = pd.DataFrame(
        {
-           "A": pd.Series(np.random.randn(8), dtype="float16"),
+           "A": pd.Series(np.random.randn(8), dtype="float32"),
            "B": pd.Series(np.random.randn(8)),
            "C": pd.Series(np.random.randint(0, 255, size=8), dtype="uint8"),  # [0,255] (range of uint8)
        }

doc/source/user_guide/enhancingperf.rst

@@ -171,6 +171,7 @@ can be improved by passing an ``np.ndarray``.
    In [4]: %%cython
       ...: cimport numpy as np
       ...: import numpy as np
+      ...: np.import_array()
       ...: cdef double f_typed(double x) except? -2:
       ...:     return x * (x - 1)
       ...: cpdef double integrate_f_typed(double a, double b, int N):
@@ -225,6 +226,7 @@ and ``wraparound`` checks can yield more performance.
       ...: cimport cython
       ...: cimport numpy as np
       ...: import numpy as np
+      ...: np.import_array()
       ...: cdef np.float64_t f_typed(np.float64_t x) except? -2:
       ...:     return x * (x - 1)
       ...: cpdef np.float64_t integrate_f_typed(np.float64_t a, np.float64_t b, np.int64_t N):

doc/source/whatsnew/v0.11.0.rst

@@ -74,10 +74,10 @@ Numeric dtypes will propagate and can coexist in DataFrames. If a dtype is passe
 
 .. ipython:: python
 
-   df1 = pd.DataFrame(np.random.randn(8, 1), columns=['A'], dtype='float32')
+   df1 = pd.DataFrame(np.random.randn(8, 1), columns=['A'], dtype='float64')
    df1
    df1.dtypes
-   df2 = pd.DataFrame({'A': pd.Series(np.random.randn(8), dtype='float16'),
+   df2 = pd.DataFrame({'A': pd.Series(np.random.randn(8), dtype='float32'),
                        'B': pd.Series(np.random.randn(8)),
                        'C': pd.Series(range(8), dtype='uint8')})
    df2

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`)
@@ -825,6 +828,7 @@ Other
 - Bug in :class:`DataFrame` when passing a ``dict`` with a NA scalar and ``columns`` that would always return ``np.nan`` (:issue:`57205`)
 - Bug in :class:`Series` ignoring errors when trying to convert :class:`Series` input data to the given ``dtype`` (:issue:`60728`)
 - Bug in :func:`eval` on :class:`ExtensionArray` on including division ``/`` failed with a ``TypeError``. (:issue:`58748`)
+- Bug in :func:`eval` where method calls on binary operations like ``(x + y).dropna()`` would raise ``AttributeError: 'BinOp' object has no attribute 'value'`` (:issue:`61175`)
 - Bug in :func:`eval` where the names of the :class:`Series` were not preserved when using ``engine="numexpr"``. (:issue:`10239`)
 - Bug in :func:`eval` with ``engine="numexpr"`` returning unexpected result for float division. (:issue:`59736`)
 - Bug in :func:`to_numeric` raising ``TypeError`` when ``arg`` is a :class:`Timedelta` or :class:`Timestamp` scalar. (:issue:`59944`)
@@ -834,6 +838,7 @@ Other
 - Bug in :meth:`DataFrame.eval` and :meth:`DataFrame.query` which did not allow to use ``tan`` function. (:issue:`55091`)
 - Bug in :meth:`DataFrame.query` where using duplicate column names led to a ``TypeError``. (:issue:`59950`)
 - Bug in :meth:`DataFrame.query` which raised an exception or produced incorrect results when expressions contained backtick-quoted column names containing the hash character ``#``, backticks, or characters that fall outside the ASCII range (U+0001..U+007F). (:issue:`59285`) (:issue:`49633`)
+- Bug in :meth:`DataFrame.query` which raised an exception when querying integer column names using backticks. (:issue:`60494`)
 - Bug in :meth:`DataFrame.shift` where passing a ``freq`` on a DataFrame with no columns did not shift the index correctly. (:issue:`60102`)
 - Bug in :meth:`DataFrame.sort_index` when passing ``axis="columns"`` and ``ignore_index=True`` and ``ascending=False`` not returning a :class:`RangeIndex` columns (:issue:`57293`)
 - Bug in :meth:`DataFrame.transform` that was returning the wrong order unless the index was monotonically increasing. (:issue:`57069`)

environment.yml

@@ -23,7 +23,7 @@ dependencies:
 
   # required dependencies
   - python-dateutil
-  - numpy<2
+  - numpy<3
 
   # optional dependencies
   - beautifulsoup4>=4.11.2
@@ -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/algos.pyx

@@ -391,10 +391,11 @@ def nancorr(const float64_t[:, :] mat, bint cov=False, minp=None):
                     # clip `covxy / divisor` to ensure coeff is within bounds
                     if divisor != 0:
                         val = covxy / divisor
-                        if val > 1.0:
-                            val = 1.0
-                        elif val < -1.0:
-                            val = -1.0
+                        if not cov:
+                            if val > 1.0:
+                                val = 1.0
+                            elif val < -1.0:
+                                val = -1.0
                         result[xi, yi] = result[yi, xi] = val
                     else:
                         result[xi, yi] = result[yi, xi] = NaN

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/compat/numpy/__init__.py

@@ -36,8 +36,8 @@
                 r".*In the future `np\.long` will be defined as.*",
                 FutureWarning,
             )
-            np_long = np.long  # type: ignore[attr-defined]
-            np_ulong = np.ulong  # type: ignore[attr-defined]
+            np_long = np.long
+            np_ulong = np.ulong
     except AttributeError:
         np_long = np.int_
         np_ulong = np.uint