Merge branch 'main' into read-csv-from-directory

Author: fangchenli

.github/workflows/wheels.yml

@@ -45,7 +45,6 @@ jobs:
       (github.event_name == 'push' && startsWith(github.ref, 'refs/tags/v') && ( ! endsWith(github.ref, 'dev0')))
     runs-on: ubuntu-24.04
     env:
-      IS_PUSH: ${{ github.event_name == 'push' && startsWith(github.ref, 'refs/tags/v') }}
       IS_SCHEDULE_DISPATCH: ${{ github.event_name == 'schedule' || github.event_name == 'workflow_dispatch' }}
     outputs:
       sdist_file: ${{ steps.save-path.outputs.sdist_name }}
@@ -118,7 +117,6 @@ jobs:
             python: ["cp313t", "3.13"]
 
     env:
-      IS_PUSH: ${{ github.event_name == 'push' && startsWith(github.ref, 'refs/tags/v') }}
       IS_SCHEDULE_DISPATCH: ${{ github.event_name == 'schedule' || github.event_name == 'workflow_dispatch' }}
     steps:
       - name: Checkout pandas
@@ -204,21 +202,11 @@ jobs:
           path: ./wheelhouse/*.whl
 
       - name: Upload wheels & sdist
-        if: ${{ success() && (env.IS_SCHEDULE_DISPATCH == 'true' || env.IS_PUSH == 'true') }}
-        shell: bash -el {0}
-        env:
-          PANDAS_STAGING_UPLOAD_TOKEN: ${{ secrets.PANDAS_STAGING_UPLOAD_TOKEN }}
-          PANDAS_NIGHTLY_UPLOAD_TOKEN: ${{ secrets.PANDAS_NIGHTLY_UPLOAD_TOKEN }}
-        # trigger an upload to
-        # https://anaconda.org/scientific-python-nightly-wheels/pandas
-        # for cron jobs or "Run workflow" (restricted to main branch).
-        # Tags will upload to
-        # https://anaconda.org/multibuild-wheels-staging/pandas
-        # The tokens were originally generated at anaconda.org
-        run: |
-          source ci/upload_wheels.sh
-          set_upload_vars
-          upload_wheels
+        if: ${{ success() && env.IS_SCHEDULE_DISPATCH == 'true' }}
+        uses: scientific-python/upload-nightly-action@0.6.2
+        with:
+          artifacts_path: dist
+          anaconda_nightly_upload_token: ${{secrets.PANDAS_NIGHTLY_UPLOAD_TOKEN}}
 
   publish:
     if: >

.pre-commit-config.yaml

@@ -19,7 +19,7 @@ ci:
     skip: [pyright, mypy]
 repos:
 -   repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.14.3
+    rev: v0.14.7
     hooks:
     -   id: ruff
         args: [--exit-non-zero-on-fix]
@@ -71,7 +71,7 @@ repos:
     hooks:
     -   id: isort
 -   repo: https://github.com/asottile/pyupgrade
-    rev: v3.21.0
+    rev: v3.21.2
     hooks:
     -   id: pyupgrade
         args: [--py311-plus]
@@ -87,12 +87,12 @@ repos:
         types: [text]  # overwrite types: [rst]
         types_or: [python, rst]
 -   repo: https://github.com/sphinx-contrib/sphinx-lint
-    rev: v1.0.1
+    rev: v1.0.2
     hooks:
     - id: sphinx-lint
       args: ["--enable", "all", "--disable", "line-too-long"]
 -   repo: https://github.com/pre-commit/mirrors-clang-format
-    rev: v21.1.2
+    rev: v21.1.6
     hooks:
     - id: clang-format
       files: ^pandas/_libs/src|^pandas/_libs/include

ci/code_checks.sh

@@ -69,9 +69,11 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
     "$BASE_DIR"/scripts/validate_docstrings.py \
         --format=actions \
         -i ES01 `# For now it is ok if docstrings are missing the extended summary` \
+        -i "pandas.DataFrame.from_arrow SA01,EX01" \
         -i "pandas.Series.dt PR01" `# Accessors are implemented as classes, but we do not document the Parameters section` \
         -i "pandas.Period.freq GL08" \
         -i "pandas.Period.ordinal GL08" \
+        -i "pandas.errors.ChainedAssignmentError SA01" \
         -i "pandas.errors.IncompatibleFrequency SA01,SS06,EX01" \
         -i "pandas.api.extensions.ExtensionArray.value_counts EX01,RT03,SA01" \
         -i "pandas.api.typing.DataFrameGroupBy.plot PR02" \
@@ -164,6 +166,8 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.tseries.offsets.DateOffset.is_on_offset GL08" \
         -i "pandas.tseries.offsets.DateOffset.n GL08" \
         -i "pandas.tseries.offsets.DateOffset.normalize GL08" \
+        -i "pandas.tseries.offsets.DateOffset.rollback SA01,EX01" \
+        -i "pandas.tseries.offsets.DateOffset.rollforward SA01,EX01" \
         -i "pandas.tseries.offsets.Day.freqstr SA01" \
         -i "pandas.tseries.offsets.Day.is_on_offset GL08" \
         -i "pandas.tseries.offsets.Day.n GL08" \

ci/upload_wheels.sh

@@ -433,14 +433,6 @@ which will be triggered when the tag is pushed.
 3. Download the source distribution and wheels from the `wheel staging area <https://anaconda.org/scientific-python-nightly-wheels/pandas>`_.
    Be careful to make sure that no wheels are missing (e.g. due to failed builds).
 
-   Running scripts/download_wheels.sh with the version that you want to download wheels/the sdist for should do the trick.
-   This script will make a ``dist`` folder inside your clone of pandas and put the downloaded wheels and sdist there::
-
-    scripts/download_wheels.sh <VERSION>
-
-   ATTENTION: this is currently not downloading *all* wheels, and you have to
-   manually download the remainings wheels and sdist!
-
 4. Create a `new GitHub release <https://github.com/pandas-dev/pandas/releases/new>`_:
 
    - Tag: ``<version>``

doc/source/development/maintaining.rst

@@ -360,6 +360,7 @@ Serialization / IO / conversion
 .. autosummary::
    :toctree: api/
 
+   DataFrame.from_arrow
    DataFrame.from_dict
    DataFrame.from_records
    DataFrame.to_orc

doc/source/reference/frame.rst

@@ -189,6 +189,7 @@ Categorical components
 .. autosummary::
    :toctree: api/
 
+   CategoricalIndex.append
    CategoricalIndex.codes
    CategoricalIndex.categories
    CategoricalIndex.ordered

doc/source/reference/indexing.rst

@@ -40,6 +40,8 @@ Methods
     DateOffset.is_quarter_end
     DateOffset.is_year_start
     DateOffset.is_year_end
+    DateOffset.rollback
+    DateOffset.rollforward
 
 BusinessDay
 -----------

doc/source/reference/offset_frequency.rst

@@ -424,6 +424,7 @@ strings and apply several methods to it. These can be accessed like
    Series.str.fullmatch
    Series.str.get
    Series.str.index
+   Series.str.isascii
    Series.str.join
    Series.str.len
    Series.str.ljust

doc/source/reference/series.rst

@@ -249,9 +249,9 @@ two subsequent indexing operations, e.g.
     In [3]: df
     Out[3]:
        foo  bar
-    0  100    4
+    0    1    4
     1    2    5
-    2    3    6
+    2  100    6
 
 The column ``foo`` was updated where the column ``bar`` is greater than 5.
 This violated the CoW principles though, because it would have to modify the