Merge remote-tracking branch 'upstream/main' into string-dtype-index-union-with-empty-object

Author: jorisvandenbossche

.github/workflows/unit-tests.yml

@@ -107,7 +107,7 @@ jobs:
 
     services:
       mysql:
-        image: mysql:8
+        image: mysql:9
         env:
           MYSQL_ALLOW_EMPTY_PASSWORD: yes
           MYSQL_DATABASE: pandas
@@ -120,7 +120,7 @@ jobs:
           - 3306:3306
 
       postgres:
-        image: postgres:16
+        image: postgres:17
         env:
           PGUSER: postgres
           POSTGRES_USER: postgres
@@ -135,7 +135,7 @@ jobs:
           - 5432:5432
 
       moto:
-        image: motoserver/moto:5.0.0
+        image: motoserver/moto:5.0.27
         env:
           AWS_ACCESS_KEY_ID: foobar_key
           AWS_SECRET_ACCESS_KEY: foobar_secret
@@ -242,15 +242,14 @@ jobs:
       - name: Build environment and Run Tests
         # https://github.com/numpy/numpy/issues/24703#issuecomment-1722379388
         run: |
-          /opt/python/cp311-cp311/bin/python -m venv ~/virtualenvs/pandas-dev
+          /opt/python/cp313-cp313/bin/python -m venv ~/virtualenvs/pandas-dev
           . ~/virtualenvs/pandas-dev/bin/activate
           python -m pip install --no-cache-dir -U pip wheel setuptools meson[ninja]==1.2.1 meson-python==0.13.1
           python -m pip install numpy -Csetup-args="-Dallow-noblas=true"
           python -m pip install --no-cache-dir versioneer[toml] cython python-dateutil pytest>=7.3.2 pytest-xdist>=3.4.0 hypothesis>=6.84.0
           python -m pip install --no-cache-dir --no-build-isolation -e . -Csetup-args="--werror"
           python -m pip list --no-cache-dir
-          export PANDAS_CI=1
-          python -m pytest -m 'not slow and not network and not clipboard and not single_cpu' pandas --junitxml=test-data.xml
+          PANDAS_CI=1 python -m pytest -m 'not slow and not network and not clipboard and not single_cpu' pandas --junitxml=test-data.xml
     concurrency:
       # https://github.community/t/concurrecy-not-work-for-push/183068/7
       group: ${{ github.event_name == 'push' && github.run_number || github.ref }}-32bit
@@ -259,7 +258,7 @@ jobs:
   Linux-Musl:
     runs-on: ubuntu-22.04
     container:
-      image: quay.io/pypa/musllinux_1_1_x86_64
+      image: quay.io/pypa/musllinux_1_2_x86_64
     steps:
       - name: Checkout pandas Repo
         # actions/checkout does not work since it requires node
@@ -281,7 +280,7 @@ jobs:
           apk add musl-locales
       - name: Build environment
         run: |
-          /opt/python/cp311-cp311/bin/python -m venv ~/virtualenvs/pandas-dev
+          /opt/python/cp313-cp313/bin/python -m venv ~/virtualenvs/pandas-dev
           . ~/virtualenvs/pandas-dev/bin/activate
           python -m pip install --no-cache-dir -U pip wheel setuptools meson-python==0.13.1 meson[ninja]==1.2.1
           python -m pip install --no-cache-dir versioneer[toml] cython numpy python-dateutil pytest>=7.3.2 pytest-xdist>=3.4.0 hypothesis>=6.84.0
@@ -291,8 +290,7 @@ jobs:
       - name: Run Tests
         run: |
           . ~/virtualenvs/pandas-dev/bin/activate
-          export PANDAS_CI=1
-          python -m pytest -m 'not slow and not network and not clipboard and not single_cpu' pandas --junitxml=test-data.xml
+          PANDAS_CI=1 python -m pytest -m 'not slow and not network and not clipboard and not single_cpu' pandas --junitxml=test-data.xml
     concurrency:
       # https://github.community/t/concurrecy-not-work-for-push/183068/7
       group: ${{ github.event_name == 'push' && github.run_number || github.ref }}-musl
@@ -357,8 +355,7 @@ jobs:
           python --version
           python -m pip install --upgrade pip setuptools wheel meson[ninja]==1.2.1 meson-python==0.13.1
           python -m pip install --pre --extra-index-url https://pypi.anaconda.org/scientific-python-nightly-wheels/simple numpy
-          python -m pip install versioneer[toml]
-          python -m pip install python-dateutil tzdata cython hypothesis>=6.84.0 pytest>=7.3.2 pytest-xdist>=3.4.0 pytest-cov
+          python -m pip install versioneer[toml] python-dateutil tzdata cython hypothesis>=6.84.0 pytest>=7.3.2 pytest-xdist>=3.4.0 pytest-cov
           python -m pip install -ve . --no-build-isolation --no-index --no-deps -Csetup-args="--werror"
           python -m pip list
 
@@ -375,7 +372,7 @@ jobs:
 
     concurrency:
       # https://github.community/t/concurrecy-not-work-for-push/183068/7
-      group: ${{ github.event_name == 'push' && github.run_number || github.ref }}-${{ matrix.os }}-python-freethreading-dev
+      group: ${{ github.event_name == 'push' && github.run_number || github.ref }}-python-freethreading-dev
       cancel-in-progress: true
 
     env:
@@ -396,14 +393,11 @@ jobs:
           nogil: true
 
       - name: Build Environment
-        # TODO: Once numpy 2.2.1 is out, don't install nightly version
-        # Tests segfault with numpy 2.2.0: https://github.com/numpy/numpy/pull/27955
         run: |
           python --version
-          python -m pip install --upgrade pip setuptools wheel meson[ninja]==1.2.1 meson-python==0.13.1
-          python -m pip install --pre --extra-index-url https://pypi.anaconda.org/scientific-python-nightly-wheels/simple cython numpy
-          python -m pip install versioneer[toml]
-          python -m pip install python-dateutil pytz tzdata hypothesis>=6.84.0 pytest>=7.3.2 pytest-xdist>=3.4.0 pytest-cov
+          python -m pip install --upgrade pip setuptools wheel numpy meson[ninja]==1.2.1 meson-python==0.13.1
+          python -m pip install --pre --extra-index-url https://pypi.anaconda.org/scientific-python-nightly-wheels/simple cython
+          python -m pip install versioneer[toml] python-dateutil pytz tzdata hypothesis>=6.84.0 pytest>=7.3.2 pytest-xdist>=3.4.0 pytest-cov
           python -m pip install -ve . --no-build-isolation --no-index --no-deps -Csetup-args="--werror"
           python -m pip list
 

.pre-commit-config.yaml

@@ -19,7 +19,7 @@ ci:
     skip: [pyright, mypy]
 repos:
 -   repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.8.6
+    rev: v0.9.4
     hooks:
     -   id: ruff
         args: [--exit-non-zero-on-fix]
@@ -41,7 +41,7 @@ repos:
         pass_filenames: true
         require_serial: false
 -   repo: https://github.com/codespell-project/codespell
-    rev: v2.3.0
+    rev: v2.4.1
     hooks:
     -   id: codespell
         types_or: [python, rst, markdown, cython, c]
@@ -70,7 +70,7 @@ repos:
     -   id: trailing-whitespace
         args: [--markdown-linebreak-ext=md]
 -   repo: https://github.com/PyCQA/isort
-    rev: 5.13.2
+    rev: 6.0.0
     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: v19.1.6
+    rev: v19.1.7
     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: v1.6.1
+    rev: v1.7.0
     hooks:
     - id: meson-fmt
       args: ['--inplace']

asv_bench/benchmarks/io/style.py

@@ -13,8 +13,8 @@ class Render:
     def setup(self, cols, rows):
         self.df = DataFrame(
             np.random.randn(rows, cols),
-            columns=[f"float_{i+1}" for i in range(cols)],
-            index=[f"row_{i+1}" for i in range(rows)],
+            columns=[f"float_{i + 1}" for i in range(cols)],
+            index=[f"row_{i + 1}" for i in range(rows)],
         )
 
     def time_apply_render(self, cols, rows):

doc/make.py

@@ -260,8 +260,7 @@ def latex(self, force=False):
                 for i in range(3):
                     self._run_os("pdflatex", "-interaction=nonstopmode", "pandas.tex")
                 raise SystemExit(
-                    "You should check the file "
-                    '"build/latex/pandas.pdf" for problems.'
+                    'You should check the file "build/latex/pandas.pdf" for problems.'
                 )
             self._run_os("make")
             return ret_code
@@ -343,8 +342,7 @@ def main():
         dest="verbosity",
         default=0,
         help=(
-            "increase verbosity (can be repeated), "
-            "passed to the sphinx build command"
+            "increase verbosity (can be repeated), passed to the sphinx build command"
         ),
     )
     argparser.add_argument(

doc/source/reference/style.rst

@@ -27,6 +27,7 @@ Styler properties
    Styler.template_html_style
    Styler.template_html_table
    Styler.template_latex
+   Styler.template_typst
    Styler.template_string
    Styler.loader
 
@@ -77,6 +78,7 @@ Style export and import
 
    Styler.to_html
    Styler.to_latex
+   Styler.to_typst
    Styler.to_excel
    Styler.to_string
    Styler.export

doc/source/user_guide/cookbook.rst

@@ -874,7 +874,7 @@ Timeseries
 <https://stackoverflow.com/questions/13893227/vectorized-look-up-of-values-in-pandas-dataframe>`__
 
 `Aggregation and plotting time series
-<https://nipunbatra.github.io/blog/visualisation/2013/05/01/aggregation-timeseries.html>`__
+<https://nipunbatra.github.io/blog/posts/2013-05-01-aggregation-timeseries.html>`__
 
 Turn a matrix with hours in columns and days in rows into a continuous row sequence in the form of a time series.
 `How to rearrange a Python pandas DataFrame?

doc/source/user_guide/gotchas.rst

@@ -372,5 +372,5 @@ constructors using something similar to the following:
    s = pd.Series(newx)
 
 See `the NumPy documentation on byte order
-<https://numpy.org/doc/stable/user/basics.byteswapping.html>`__ for more
+<https://numpy.org/doc/stable/user/byteswapping.html>`__ for more
 details.

doc/source/user_guide/style.ipynb

@@ -1288,7 +1288,7 @@
    "outputs": [],
    "source": [
     "df2.loc[:4].style.highlight_max(\n",
-    "    axis=1, props=(\"color:white; \" \"font-weight:bold; \" \"background-color:darkblue;\")\n",
+    "    axis=1, props=(\"color:white; font-weight:bold; background-color:darkblue;\")\n",
     ")"
    ]
   },

doc/source/whatsnew/v2.3.0.rst

@@ -35,6 +35,7 @@ Other enhancements
 - The semantics for the ``copy`` keyword in ``__array__`` methods (i.e. called
   when using ``np.array()`` or ``np.asarray()`` on pandas objects) has been
   updated to work correctly with NumPy >= 2 (:issue:`57739`)
+- :meth:`Series.str.decode` result now has ``StringDtype`` when ``future.infer_string`` is True (:issue:`60709`)
 - :meth:`~Series.to_hdf` and :meth:`~DataFrame.to_hdf` now round-trip with ``StringDtype``  (:issue:`60663`)
 - The :meth:`~Series.cumsum`, :meth:`~Series.cummin`, and :meth:`~Series.cummax` reductions are now implemented for ``StringDtype`` columns when backed by PyArrow (:issue:`60633`)
 - The :meth:`~Series.sum` reduction is now implemented for ``StringDtype`` columns (:issue:`59853`)

doc/source/whatsnew/v3.0.0.rst

@@ -31,6 +31,7 @@ Other enhancements
 - :class:`pandas.api.typing.FrozenList` is available for typing the outputs of :attr:`MultiIndex.names`, :attr:`MultiIndex.codes` and :attr:`MultiIndex.levels` (:issue:`58237`)
 - :class:`pandas.api.typing.SASReader` is available for typing the output of :func:`read_sas` (:issue:`55689`)
 - :meth:`pandas.api.interchange.from_dataframe` now uses the `PyCapsule Interface <https://arrow.apache.org/docs/format/CDataInterface/PyCapsuleInterface.html>`_ if available, only falling back to the Dataframe Interchange Protocol if that fails (:issue:`60739`)
+- Added :meth:`.Styler.to_typst` to write Styler objects to file, buffer or string in Typst format (:issue:`57617`)
 - :class:`pandas.api.typing.NoDefault` is available for typing ``no_default``
 - :func:`DataFrame.to_excel` now raises an ``UserWarning`` when the character count in a cell exceeds Excel's limitation of 32767 characters (:issue:`56954`)
 - :func:`pandas.merge` now validates the ``how`` parameter input (merge type) (:issue:`59435`)
@@ -58,9 +59,9 @@ Other enhancements
 - :meth:`Series.cummin` and :meth:`Series.cummax` now supports :class:`CategoricalDtype` (:issue:`52335`)
 - :meth:`Series.plot` now correctly handle the ``ylabel`` parameter for pie charts, allowing for explicit control over the y-axis label (:issue:`58239`)
 - :meth:`DataFrame.plot.scatter` argument ``c`` now accepts a column of strings, where rows with the same string are colored identically (:issue:`16827` and :issue:`16485`)
+- :class:`DataFrameGroupBy` and :class:`SeriesGroupBy` methods ``sum``, ``mean``, ``median``, ``prod``, ``min``, ``max``, ``std``, ``var`` and ``sem`` now accept ``skipna`` parameter (:issue:`15675`)
 - :class:`Rolling` and :class:`Expanding` now support aggregations ``first`` and ``last`` (:issue:`33155`)
 - :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.mean`, :meth:`.DataFrameGroupBy.sum`, :meth:`.SeriesGroupBy.mean` and :meth:`.SeriesGroupBy.sum` now accept ``skipna`` parameter (:issue:`15675`)
 - :meth:`.DataFrameGroupBy.transform`, :meth:`.SeriesGroupBy.transform`, :meth:`.DataFrameGroupBy.agg`, :meth:`.SeriesGroupBy.agg`, :meth:`.SeriesGroupBy.apply`, :meth:`.DataFrameGroupBy.apply` now support ``kurt`` (:issue:`40139`)
 - :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`)
@@ -765,6 +766,7 @@ Reshaping
 - Bug in :meth:`DataFrame.unstack` producing incorrect results when ``sort=False`` (:issue:`54987`, :issue:`55516`)
 - Bug in :meth:`DataFrame.merge` when merging two :class:`DataFrame` on ``intc`` or ``uintc`` types on Windows (:issue:`60091`, :issue:`58713`)
 - Bug in :meth:`DataFrame.pivot_table` incorrectly subaggregating results when called without an ``index`` argument (:issue:`58722`)
+- Bug in :meth:`DataFrame.stack` with the new implementation where ``ValueError`` is raised when ``level=[]`` (:issue:`60740`)
 - Bug in :meth:`DataFrame.unstack` producing incorrect results when manipulating empty :class:`DataFrame` with an :class:`ExtentionDtype` (:issue:`59123`)
 
 Sparse