Merge branch 'main' into series_map_func_param

Author: datapythonista

.github/CODEOWNERS

@@ -10,10 +10,8 @@ doc/source/development            @noatamir
 
 # pandas
 pandas/_libs/                     @WillAyd
-pandas/_libs/tslibs/*             @MarcoGorelli
 pandas/_typing.py                 @Dr-Irv
 pandas/core/groupby/*             @rhshadrach
-pandas/core/tools/datetimes.py    @MarcoGorelli
 pandas/io/excel/*                 @rhshadrach
 pandas/io/formats/style.py        @attack68
 pandas/io/formats/style_render.py @attack68

.github/workflows/wheels.yml

@@ -153,7 +153,7 @@ jobs:
         run: echo "sdist_name=$(cd ./dist && ls -d */)" >> "$GITHUB_ENV"
 
       - name: Build wheels
-        uses: pypa/[email protected].0
+        uses: pypa/[email protected].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

@@ -72,13 +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.Timedelta.max PR02" \
-        -i "pandas.Timedelta.min PR02" \
-        -i "pandas.Timedelta.resolution PR02" \
-        -i "pandas.Timestamp.max PR02" \
-        -i "pandas.Timestamp.min PR02" \
-        -i "pandas.Timestamp.resolution PR02" \
-        -i "pandas.Timestamp.tzinfo GL08" \
         -i "pandas.core.groupby.DataFrameGroupBy.plot PR02" \
         -i "pandas.core.groupby.SeriesGroupBy.plot PR02" \
         -i "pandas.core.resample.Resampler.quantile PR01,PR07" \

ci/meta.yaml

@@ -89,4 +89,3 @@ extra:
     - datapythonista
     - phofl
     - lithomas1
-    - marcogorelli

doc/source/development/contributing_codebase.rst

@@ -537,7 +537,7 @@ Preferred ``pytest`` idioms
     test and does not check if the test will fail. If this is the behavior you desire, use ``pytest.skip`` instead.
 
 If a test is known to fail but the manner in which it fails
-is not meant to be captured, use ``pytest.mark.xfail`` It is common to use this method for a test that
+is not meant to be captured, use ``pytest.mark.xfail``. It is common to use this method for a test that
 exhibits buggy behavior or a non-implemented feature. If
 the failing test has flaky behavior, use the argument ``strict=False``. This
 will make it so pytest does not fail if the test happens to pass. Using ``strict=False`` is highly undesirable, please use it only as a last resort.

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

@@ -36,7 +36,7 @@ of elements to display is five, but you may pass a custom number.
 Attributes and underlying data
 ------------------------------
 
-pandas objects have a number of attributes enabling you to access the metadata
+pandas objects have a number of attributes enabling you to access the metadata.
 
 * **shape**: gives the axis dimensions of the object, consistent with ndarray
 * Axis labels
@@ -59,7 +59,7 @@ NumPy's type system to add support for custom arrays
 (see :ref:`basics.dtypes`).
 
 To get the actual data inside a :class:`Index` or :class:`Series`, use
-the ``.array`` property
+the ``.array`` property.
 
 .. ipython:: python
 
@@ -88,18 +88,18 @@ NumPy doesn't have a dtype to represent timezone-aware datetimes, so there
 are two possibly useful representations:
 
 1. An object-dtype :class:`numpy.ndarray` with :class:`Timestamp` objects, each
-   with the correct ``tz``
+   with the correct ``tz``.
 2. A ``datetime64[ns]`` -dtype :class:`numpy.ndarray`, where the values have
-   been converted to UTC and the timezone discarded
+   been converted to UTC and the timezone discarded.
 
-Timezones may be preserved with ``dtype=object``
+Timezones may be preserved with ``dtype=object``:
 
 .. ipython:: python
 
    ser = pd.Series(pd.date_range("2000", periods=2, tz="CET"))
    ser.to_numpy(dtype=object)
 
-Or thrown away with ``dtype='datetime64[ns]'``
+Or thrown away with ``dtype='datetime64[ns]'``:
 
 .. ipython:: python
 
@@ -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`)
@@ -637,6 +638,7 @@ Bug fixes
 Categorical
 ^^^^^^^^^^^
 - Bug in :func:`Series.apply` where ``nan`` was ignored for :class:`CategoricalDtype` (:issue:`59938`)
+- Bug in :meth:`Series.convert_dtypes` with ``dtype_backend="pyarrow"`` where empty :class:`CategoricalDtype` :class:`Series` raised an error or got converted to ``null[pyarrow]`` (:issue:`59934`)
 -
 
 Datetimelike
@@ -673,6 +675,7 @@ Timezones
 
 Numeric
 ^^^^^^^
+- Bug in :meth:`DataFrame.corr` where numerical precision errors resulted in correlations above ``1.0`` (:issue:`61120`)
 - Bug in :meth:`DataFrame.quantile` where the column type was not preserved when ``numeric_only=True`` with a list-like ``q`` produced an empty result (:issue:`59035`)
 - Bug in ``np.matmul`` with :class:`Index` inputs raising a ``TypeError`` (:issue:`57079`)
 
@@ -704,6 +707,7 @@ Indexing
 - Bug in :meth:`Index.get_indexer` and similar methods when ``NaN`` is located at or after position 128 (:issue:`58924`)
 - Bug in :meth:`MultiIndex.insert` when a new value inserted to a datetime-like level gets cast to ``NaT`` and fails indexing (:issue:`60388`)
 - Bug in printing :attr:`Index.names` and :attr:`MultiIndex.levels` would not escape single quotes (:issue:`60190`)
+- Bug in reindexing of :class:`DataFrame` with :class:`PeriodDtype` columns in case of consolidated block (:issue:`60980`, :issue:`60273`)
 
 Missing
 ^^^^^^^
@@ -740,6 +744,7 @@ I/O
 - Bug in :meth:`read_csv` where the order of the ``na_values`` makes an inconsistency when ``na_values`` is a list non-string values. (:issue:`59303`)
 - Bug in :meth:`read_excel` raising ``ValueError`` when passing array of boolean values when ``dtype="boolean"``. (:issue:`58159`)
 - Bug in :meth:`read_html` where ``rowspan`` in header row causes incorrect conversion to ``DataFrame``. (:issue:`60210`)
+- Bug in :meth:`read_json` ignoring the given ``dtype`` when ``engine="pyarrow"`` (:issue:`59516`)
 - Bug in :meth:`read_json` not validating the ``typ`` argument to not be exactly ``"frame"`` or ``"series"`` (:issue:`59124`)
 - Bug in :meth:`read_json` where extreme value integers in string format were incorrectly parsed as a different integer number (:issue:`20608`)
 - Bug in :meth:`read_stata` raising ``KeyError`` when input file is stored in big-endian format and contains strL data. (:issue:`58638`)
@@ -759,6 +764,7 @@ 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
@@ -770,6 +776,8 @@ 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`)
 - Bug in :meth:`DataFrameGroupBy.apply` that was returning a completely empty DataFrame when all return values of ``func`` were ``None`` instead of returning an empty DataFrame with the original columns and dtypes. (:issue:`57775`)
@@ -821,6 +829,7 @@ 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`)
@@ -830,15 +839,18 @@ 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`)
 - Bug in :meth:`DataFrame.where` where using a non-bool type array in the function would return a ``ValueError`` instead of a ``TypeError`` (:issue:`56330`)
 - Bug in :meth:`Index.sort_values` when passing a key function that turns values into tuples, e.g. ``key=natsort.natsort_key``, would raise ``TypeError`` (:issue:`56081`)
 - Bug in :meth:`MultiIndex.fillna` error message was referring to ``isna`` instead of ``fillna`` (:issue:`60974`)
+- Bug in :meth:`Series.describe` where median percentile was always included when the ``percentiles`` argument was passed (:issue:`60550`).
 - Bug in :meth:`Series.diff` allowing non-integer values for the ``periods`` argument. (:issue:`56607`)
 - Bug in :meth:`Series.dt` methods in :class:`ArrowDtype` that were returning incorrect values. (:issue:`57355`)
 - Bug in :meth:`Series.isin` raising ``TypeError`` when series is large (>10**6) and ``values`` contains NA (:issue:`60678`)
+- Bug in :meth:`Series.mode` where an exception was raised when taking the mode with nullable types with no null values in the series. (:issue:`58926`)
 - Bug in :meth:`Series.rank` that doesn't preserve missing values for nullable integers when ``na_option='keep'``. (:issue:`56976`)
 - Bug in :meth:`Series.replace` and :meth:`DataFrame.replace` inconsistently replacing matching instances when ``regex=True`` and missing values are present. (:issue:`56599`)
 - Bug in :meth:`Series.replace` and :meth:`DataFrame.replace` throwing ``ValueError`` when ``regex=True`` and all NA values. (:issue:`60688`)