Merge branch 'main' into issue57049

Author: simonjayhawkins

.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/actions/run-tests/action.yml

@@ -14,7 +14,7 @@ runs:
       if: failure()
 
     - name: Upload coverage to Codecov
-      uses: codecov/codecov-action@v4
+      uses: codecov/codecov-action@v5
       with:
         flags: unittests
         name: codecov-pandas

.github/actions/setup-conda/action.yml

@@ -7,7 +7,7 @@ runs:
   using: composite
   steps:
     - name: Install ${{ inputs.environment-file }}
-      uses: mamba-org/setup-micromamba@v1
+      uses: mamba-org/setup-micromamba@v2
       with:
         environment-file: ${{ inputs.environment-file }}
         environment-name: test

.github/workflows/docbuild-and-upload.yml

@@ -59,6 +59,10 @@ jobs:
     - name: Build documentation
       run: doc/make.py --warnings-are-errors
 
+    - name: Build the interactive terminal
+      working-directory: web/interactive_terminal
+      run: jupyter lite build
+
     - name: Build documentation zip
       run: doc/make.py zip_html
 

.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@v2.22.0
+        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: v0.9.4
+    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
@@ -70,7 +70,7 @@ repos:
     -   id: trailing-whitespace
         args: [--markdown-linebreak-ext=md]
 -   repo: https://github.com/PyCQA/isort
-    rev: 6.0.0
+    rev: 6.0.1
     hooks:
     -   id: isort
 -   repo: https://github.com/asottile/pyupgrade
@@ -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']

Dockerfile

@@ -13,5 +13,5 @@ COPY requirements-dev.txt /tmp
 RUN python -m pip install -r /tmp/requirements-dev.txt
 RUN git config --global --add safe.directory /home/pandas
 
-ENV SHELL "/bin/bash"
+ENV SHELL="/bin/bash"
 CMD ["/bin/bash"]

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)

asv_bench/benchmarks/rolling.py

@@ -10,7 +10,19 @@ class Methods:
         ["DataFrame", "Series"],
         [("rolling", {"window": 10}), ("rolling", {"window": 1000}), ("expanding", {})],
         ["int", "float"],
-        ["median", "mean", "max", "min", "std", "count", "skew", "kurt", "sum", "sem"],
+        [
+            "median",
+            "mean",
+            "max",
+            "min",
+            "std",
+            "count",
+            "skew",
+            "kurt",
+            "sum",
+            "sem",
+            "nunique",
+        ],
     )
     param_names = ["constructor", "window_kwargs", "dtype", "method"]
 

ci/code_checks.sh

@@ -72,17 +72,20 @@ 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" \
         -i "pandas.tseries.offsets.BDay PR02,SA01" \
+        -i "pandas.tseries.offsets.BHalfYearBegin.is_on_offset GL08" \
+        -i "pandas.tseries.offsets.BHalfYearBegin.n GL08" \
+        -i "pandas.tseries.offsets.BHalfYearBegin.normalize GL08" \
+        -i "pandas.tseries.offsets.BHalfYearBegin.rule_code GL08" \
+        -i "pandas.tseries.offsets.BHalfYearBegin.startingMonth GL08" \
+        -i "pandas.tseries.offsets.BHalfYearEnd.is_on_offset GL08" \
+        -i "pandas.tseries.offsets.BHalfYearEnd.n GL08" \
+        -i "pandas.tseries.offsets.BHalfYearEnd.normalize GL08" \
+        -i "pandas.tseries.offsets.BHalfYearEnd.rule_code GL08" \
+        -i "pandas.tseries.offsets.BHalfYearEnd.startingMonth GL08" \
         -i "pandas.tseries.offsets.BQuarterBegin.is_on_offset GL08" \
         -i "pandas.tseries.offsets.BQuarterBegin.n GL08" \
         -i "pandas.tseries.offsets.BQuarterBegin.normalize GL08" \
@@ -185,6 +188,16 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.tseries.offsets.FY5253Quarter.variation GL08" \
         -i "pandas.tseries.offsets.FY5253Quarter.weekday GL08" \
         -i "pandas.tseries.offsets.FY5253Quarter.year_has_extra_week GL08" \
+        -i "pandas.tseries.offsets.HalfYearBegin.is_on_offset GL08" \
+        -i "pandas.tseries.offsets.HalfYearBegin.n GL08" \
+        -i "pandas.tseries.offsets.HalfYearBegin.normalize GL08" \
+        -i "pandas.tseries.offsets.HalfYearBegin.rule_code GL08" \
+        -i "pandas.tseries.offsets.HalfYearBegin.startingMonth GL08" \
+        -i "pandas.tseries.offsets.HalfYearEnd.is_on_offset GL08" \
+        -i "pandas.tseries.offsets.HalfYearEnd.n GL08" \
+        -i "pandas.tseries.offsets.HalfYearEnd.normalize GL08" \
+        -i "pandas.tseries.offsets.HalfYearEnd.rule_code GL08" \
+        -i "pandas.tseries.offsets.HalfYearEnd.startingMonth GL08" \
         -i "pandas.tseries.offsets.Hour.is_on_offset GL08" \
         -i "pandas.tseries.offsets.Hour.n GL08" \
         -i "pandas.tseries.offsets.Hour.normalize GL08" \

ci/meta.yaml

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

doc/source/development/contributing_codebase.rst

@@ -198,7 +198,7 @@ In some cases you may be tempted to use ``cast`` from the typing module when you
            obj = cast(str, obj)  # Mypy complains without this!
            return obj.upper()
 
-The limitation here is that while a human can reasonably understand that ``is_number`` would catch the ``int`` and ``float`` types mypy cannot make that same inference just yet (see `mypy #5206 <https://github.com/python/mypy/issues/5206>`_. While the above works, the use of ``cast`` is **strongly discouraged**. Where applicable a refactor of the code to appease static analysis is preferable
+The limitation here is that while a human can reasonably understand that ``is_number`` would catch the ``int`` and ``float`` types mypy cannot make that same inference just yet (see `mypy #5206 <https://github.com/python/mypy/issues/5206>`_). While the above works, the use of ``cast`` is **strongly discouraged**. Where applicable a refactor of the code to appease static analysis is preferable
 
 .. code-block:: python
 
@@ -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/getting_started/intro_tutorials/03_subset_data.rst

@@ -335,7 +335,7 @@ the name ``anonymous`` to the first 3 elements of the fourth column:
 .. ipython:: python
 
     titanic.iloc[0:3, 3] = "anonymous"
-    titanic.head()
+    titanic.iloc[:5, 3]
 
 .. raw:: html
 

doc/source/getting_started/overview.rst

@@ -174,3 +174,4 @@ License
 -------
 
 .. literalinclude:: ../../../LICENSE
+   :language: none

doc/source/reference/groupby.rst

@@ -79,6 +79,8 @@ Function application
    DataFrameGroupBy.cumsum
    DataFrameGroupBy.describe
    DataFrameGroupBy.diff
+   DataFrameGroupBy.ewm
+   DataFrameGroupBy.expanding
    DataFrameGroupBy.ffill
    DataFrameGroupBy.first
    DataFrameGroupBy.head
@@ -130,6 +132,8 @@ Function application
    SeriesGroupBy.cumsum
    SeriesGroupBy.describe
    SeriesGroupBy.diff
+   SeriesGroupBy.ewm
+   SeriesGroupBy.expanding
    SeriesGroupBy.ffill
    SeriesGroupBy.first
    SeriesGroupBy.head