Merge remote-tracking branch 'upstream' into feat/pep770-sbom

Author: fangchenli

.clang-format

@@ -0,0 +1 @@
+IndentPPDirectives: AfterHash

.github/CODEOWNERS

@@ -7,6 +7,8 @@ ci/                               @mroeschke
 # docs
 doc/cheatsheet                    @Dr-Irv
 doc/source/development            @noatamir
+doc/source/getting_started        @afeld
+doc/source/user_guide             @afeld
 
 # pandas
 pandas/_typing.py                 @Dr-Irv

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

@@ -11,11 +11,19 @@ on:
     branches:
       - main
       - 2.3.x
+  workflow_dispatch:
+    inputs:
+      version:
+        description: 'The pandas version to override'
+        required: false
+        type: string
 
 env:
   ENV_FILE: environment.yml
   PANDAS_CI: 1
   GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+  PANDAS_VERSION: "${{ github.event_name == 'workflow_dispatch' && github.event.inputs.version || '' }}"
+  PANDAS_VERSION_OVERRIDE: "${{ github.event_name == 'workflow_dispatch' && github.event.inputs.version || '' }}"
 
 permissions:
   contents: read
@@ -35,6 +43,16 @@ jobs:
         shell: bash -el {0}
 
     steps:
+    - name: Set pandas version
+      run: |
+        echo "PANDAS_VERSION=${GITHUB_REF_NAME:1}" >> "$GITHUB_ENV"
+      if: github.event_name != 'workflow_dispatch'
+
+    - name: Show environment variables
+      run: |
+        echo "PANDAS_VERSION=${{ env.PANDAS_VERSION }}"
+        echo "PANDAS_VERSION_OVERRIDE=${{ env.PANDAS_VERSION_OVERRIDE }}"
+
     - name: Checkout
       uses: actions/checkout@v6
       with:
@@ -72,7 +90,7 @@ jobs:
         echo "${{ secrets.server_ssh_key }}" > ~/.ssh/id_rsa
         chmod 600 ~/.ssh/id_rsa
         echo "${{ secrets.server_ip }} ecdsa-sha2-nistp256 AAAAE2VjZHNhLXNoYTItbmlzdHAyNTYAAAAIbmlzdHAyNTYAAABBBFjYkJBk7sos+r7yATODogQc3jUdW1aascGpyOD4bohj8dWjzwLJv/OJ/fyOQ5lmj81WKDk67tGtqNJYGL9acII=" > ~/.ssh/known_hosts
-      if: github.event_name == 'push' && (github.ref == 'refs/heads/main' || startsWith(github.ref, 'refs/tags/'))
+      if: (github.event_name == 'push' && (github.ref == 'refs/heads/main' || startsWith(github.ref, 'refs/tags/'))) || github.event_name == 'workflow_dispatch'
 
     - name: Copy cheatsheets into site directory
       run: cp doc/cheatsheet/Pandas_Cheat_Sheet* web/build/
@@ -86,8 +104,8 @@ jobs:
       if: github.event_name == 'push' && github.ref == 'refs/heads/main'
 
     - name: Upload prod docs
-      run: rsync -az --delete doc/build/html/ web@${{ secrets.server_ip }}:/var/www/html/pandas-docs/version/${GITHUB_REF_NAME:1}
-      if: github.event_name == 'push' && startsWith(github.ref, 'refs/tags/')
+      run: rsync -az --delete doc/build/html/ web@${{ secrets.server_ip }}:/var/www/html/pandas-docs/version/${{ env.PANDAS_VERSION }}
+      if: (github.event_name == 'push' && startsWith(github.ref, 'refs/tags/')) || (github.event_name == 'workflow_dispatch' && env.PANDAS_VERSION_OVERRIDE != '')
 
     - name: Move docs into site directory
       run: mv doc/build/html web/build/docs

.github/workflows/unit-tests.yml

@@ -124,7 +124,7 @@ jobs:
           - 3306:3306
 
       postgres:
-        image: postgres:17
+        image: postgres:18
         env:
           PGUSER: postgres
           POSTGRES_USER: postgres
@@ -139,7 +139,7 @@ jobs:
           - 5432:5432
 
       moto:
-        image: motoserver/moto:5.0.27
+        image: motoserver/moto:5.1.18
         ports:
           - 5000:5000
 

ci/code_checks.sh

@@ -57,7 +57,8 @@ fi
 if [[ -z "$CHECK" || "$CHECK" == "doctests" ]]; then
 
     MSG='Python and Cython Doctests' ; echo "$MSG"
-    python -c 'import pandas as pd; pd.test(run_doctests=True)'
+    # Using future.python_scalars=True avoids NumPy scalar reprs in docstrings.
+    PANDAS_FUTURE_PYTHON_SCALARS="1" python -c 'import pandas as pd; pd.test(run_doctests=True)'
     RET=$(($RET + $?)) ; echo "$MSG" "DONE"
 
 fi
@@ -70,14 +71,13 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         --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.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" \
-        -i "pandas.api.typing.SeriesGroupBy.plot PR02" \
         -i "pandas.api.typing.Resampler.quantile PR01,PR07" \
         -i "pandas.StringDtype.storage SA01" \
         -i "pandas.StringDtype.na_value SA01" \

doc/source/conf.py

@@ -175,6 +175,8 @@
 
 # version = '%s r%s' % (pandas.__version__, svn_version())
 version = str(pandas.__version__)
+if version_override := os.environ.get("PANDAS_VERSION_OVERRIDE"):
+    version = version_override
 
 # The full version, including alpha/beta/rc tags.
 release = version
@@ -232,7 +234,7 @@
 # further.  For a list of options available for each theme, see the
 # documentation.
 
-if ".dev" in version:
+if ".dev" in version or ("rc" in version and "+" in version):
     switcher_version = "dev"
 elif "rc" in version:
     switcher_version = version.split("rc", maxsplit=1)[0] + " (rc)"
@@ -406,7 +408,7 @@
 # html_split_index = False
 
 # If true, links to the reST sources are added to the pages.
-# html_show_sourcelink = True
+html_show_sourcelink = False
 
 # If true, an OpenSearch description file will be output, and all pages will
 # contain a <link> tag referring to it.  The value of this option must be the

doc/source/reference/series.rst

@@ -624,6 +624,7 @@ Serialization / IO / conversion
 .. autosummary::
    :toctree: api/
 
+   Series.from_arrow
    Series.to_pickle
    Series.to_csv
    Series.to_dict

doc/source/user_guide/cookbook.rst

@@ -1245,16 +1245,16 @@ csv file and creating a store by chunks, with date parsing as well.
 `Reading in a sequence of files, then providing a global unique index to a store while appending
 <https://stackoverflow.com/questions/16997048/how-does-one-append-large-amounts-of-data-to-a-pandas-hdfstore-and-get-a-natural>`__
 
-`Groupby on a HDFStore with low group density
+`Groupby on an HDFStore with low group density
 <https://stackoverflow.com/questions/15798209/pandas-group-by-query-on-large-data-in-hdfstore>`__
 
-`Groupby on a HDFStore with high group density
+`Groupby on an HDFStore with high group density
 <https://stackoverflow.com/questions/25459982/trouble-with-grouby-on-millions-of-keys-on-a-chunked-file-in-python-pandas/25471765#25471765>`__
 
-`Hierarchical queries on a HDFStore
+`Hierarchical queries on an HDFStore
 <https://stackoverflow.com/questions/22777284/improve-query-performance-from-a-large-hdfstore-table-with-pandas/22820780#22820780>`__
 
-`Counting with a HDFStore
+`Counting with an HDFStore
 <https://stackoverflow.com/questions/20497897/converting-dict-of-dicts-into-pandas-dataframe-memory-issues>`__
 
 `Troubleshoot HDFStore exceptions
@@ -1284,7 +1284,7 @@ Storing Attributes to a group node
    store.close()
    os.remove("test.h5")
 
-You can create or load a HDFStore in-memory  by passing the ``driver``
+You can create or load an HDFStore in-memory by passing the ``driver``
 parameter to PyTables. Changes are only written to disk when the HDFStore
 is closed.
 

doc/source/user_guide/groupby.rst

@@ -237,9 +237,9 @@ The default setting of ``dropna`` argument is ``True`` which means ``NA`` are no
 GroupBy object attributes
 ~~~~~~~~~~~~~~~~~~~~~~~~~
 
-The ``groups`` attribute is a dictionary whose keys are the computed unique groups
-and corresponding values are the index labels belonging to each group. In the
-above example we have:
+The ``groups`` attribute of a GroupBy object is a dictionary that maps each
+unique group key to the index labels belonging to that group. In the above
+example:
 
 .. ipython:: python
 

doc/source/user_guide/text.rst

@@ -776,7 +776,7 @@ NA values in this array are represented and behave as ``np.nan``.
    )
 
 Notice that the last three values are all inferred by pandas as being
-an NA values, and hence stored as ``np.nan``.
+NA values, and hence stored as ``np.nan``.
 
 PyArrow storage with ``np.nan`` values
 --------------------------------------
@@ -795,7 +795,7 @@ are represented and behave as ``np.nan``.
    )
 
 Notice that the last three values are all inferred by pandas as being
-an NA values, and hence stored as ``np.nan``.
+NA values, and hence stored as ``np.nan``.
 
 Python storage with ``pd.NA`` values
 ------------------------------------