Merge branch 'main' into api-dt-ints

Author: jbrockmendel

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

@@ -93,7 +93,7 @@ jobs:
       run: mv doc/build/html web/build/docs
 
     - name: Save website as an artifact
-      uses: actions/upload-artifact@v5
+      uses: actions/upload-artifact@v6
       with:
         name: website
         path: web/build

.github/workflows/unit-tests.yml

@@ -31,6 +31,7 @@ jobs:
         # Prevent the include jobs from overriding other jobs
         pattern: [""]
         pandas_future_infer_string: ["1"]
+        pandas_future_python_scalars: ["0"]
         include:
           - name: "Downstream Compat"
             env_file: actions-313-downstream_compat.yaml
@@ -75,6 +76,10 @@ jobs:
             env_file: actions-313.yaml
             pandas_future_infer_string: "0"
             platform: ubuntu-24.04
+          - name: "PANDAS_FUTURE_PYTHON_SCALARS=1"
+            env_file: actions-313.yaml
+            pandas_future_python_scalars: "1"
+            platform: ubuntu-24.04
           - name: "Numpy Dev"
             env_file: actions-313-numpydev.yaml
             pattern: "not slow and not network and not single_cpu"
@@ -92,6 +97,7 @@ jobs:
       LC_ALL: ${{ matrix.lc_all || '' }}
       PANDAS_CI: '1'
       PANDAS_FUTURE_INFER_STRING: ${{ matrix.pandas_future_infer_string || '1' }}
+      PANDAS_FUTURE_PYTHON_SCALARS: ${{ matrix.pandas_future_python_scalars || '0' }}
       TEST_ARGS: ${{ matrix.test_args || '' }}
       PYTEST_WORKERS: 'auto'
       PYTEST_TARGET: ${{ matrix.pytest_target || 'pandas' }}

.github/workflows/wheels.yml

@@ -64,7 +64,7 @@ jobs:
           python -m pip install build
           python -m build --sdist
 
-      - uses: actions/upload-artifact@v5
+      - uses: actions/upload-artifact@v6
         with:
           name: sdist
           path: ./dist/*
@@ -138,7 +138,7 @@ jobs:
       # removes unnecessary files from the release
       - name: Download sdist (not macOS)
         #if: ${{ matrix.buildplat[1] != 'macosx_*' }}
-        uses: actions/download-artifact@v6
+        uses: actions/download-artifact@v7
         with:
           name: sdist
           path: ./dist
@@ -197,7 +197,7 @@ jobs:
         shell: bash -el {0}
         run: for whl in $(ls ./dist/*.whl); do wheel unpack $whl -d /tmp; done
 
-      - uses: actions/upload-artifact@v5
+      - uses: actions/upload-artifact@v6
         with:
           name: ${{ matrix.python[0] }}-${{ matrix.buildplat[1] }}
           path: ./dist/*.whl
@@ -229,11 +229,11 @@ jobs:
 
     steps:
       - name: Download all artefacts
-        uses: actions/download-artifact@v6
+        uses: actions/download-artifact@v7
         with:
           path: dist          # everything lands in ./dist/**
 
-      # TODO: This step can be probably be achieved by actions/download-artifact@v6
+      # TODO: This step can be probably be achieved by actions/download-artifact@v7
       # by specifying merge-multiple: true, and a glob pattern
       - name: Collect files
         run: |

doc/_templates/docs-announcement-banner.html

@@ -0,0 +1 @@
+Announcement: pandas 3.0.0 release candidate ready for testing! Read more <a href="https://pandas.pydata.org/community/blog/pandas-3.0-release-candidate.html">in the blog post</a>

doc/source/_static/schemas/01_table_dataframe.svg

@@ -258,6 +258,7 @@
     # This shows a warning for patch releases since the
     # patch version doesn't compare as equal (e.g. 2.2.1 != 2.2.0 but it should be)
     "show_version_warning_banner": False,
+    "announcement": "https://raw.githubusercontent.com/pandas-dev/pandas/main/doc/_templates/docs-announcement-banner.html",
     "icon_links": [
         {
             "name": "X",

doc/source/conf.py

@@ -72,6 +72,8 @@ SQL table or the ``data.frame`` in `R <https://www.r-project.org/>`__.
 -  The column ``Name`` consists of textual data with each value a
    string, the column ``Age`` are numbers and the column ``Sex`` is
    textual data.
+-  The index labels each row. By default, this is a sequence of integers
+   starting at 0.
 
 In spreadsheet software, the table representation of our data would look
 very similar:

doc/source/getting_started/intro_tutorials/01_table_oriented.rst

@@ -80,8 +80,8 @@ and how to adapt your code to the new default.
 
 .. _whatsnew_300.enhancements.copy_on_write:
 
-Copy-on-Write
-^^^^^^^^^^^^^
+Consistent copy/view behaviour with Copy-on-Write
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
 The new "copy-on-write" behaviour in pandas 3.0 brings changes in behavior in
 how pandas operates with respect to copies and views. A summary of the changes:
@@ -101,9 +101,10 @@ copy or a view depended on the exact operation performed, which was often
 confusing).
 
 Because every single indexing step now behaves as a copy, this also means that
-"chained assignment" (updating a DataFrame with multiple setitem steps) will
-stop working. Because this now consistently never works, the
-``SettingWithCopyWarning`` is removed.
+**"chained assignment"** (updating a DataFrame with multiple setitem steps)
+**will stop working**. Because this now consistently never works, the
+``SettingWithCopyWarning`` is removed,  and defensive ``.copy()`` calls to
+silence the warning are no longer needed.
 
 The new behavioral semantics are explained in more detail in the
 :ref:`user guide about Copy-on-Write <copy_on_write>`.
@@ -130,10 +131,18 @@ and will be removed in pandas 4.0.
 
 .. _whatsnew_300.enhancements.col:
 
-``pd.col`` syntax can now be used in :meth:`DataFrame.assign` and :meth:`DataFrame.loc`
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+Initial support for ``pd.col()`` syntax to create expressions
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
-You can now use ``pd.col`` to create callables for use in dataframe methods which accept them. For example, if you have a dataframe
+This release introduces :func:`col` to refer to a DataFrame column by name
+and build up expressions.
+
+This can be used as a simplified syntax to create callables for use in
+methods such as :meth:`DataFrame.assign`. In practice, where you would
+have to use a ``lambda`` function before, you can now use ``pd.col()``
+instead.
+
+For example, if you have a dataframe
 
 .. ipython:: python
 
@@ -151,6 +160,18 @@ you can now write:
 
     df.assign(c = pd.col('a') + pd.col('b'))
 
+The expression object returned by :func:`col` supports all standard operators
+(like ``+``, ``-``, ``*``, ``/``, etc.) and all Series methods and namespaces
+(like ``pd.col("name").sum()``, ``pd.col("name").str.upper()``, etc.).
+
+Currently, the ``pd.col()`` syntax can be used in any place which accepts a
+callable that takes the calling DataFrame as first argument and returns a
+Series, like ``lambda df: df[col_name]``.
+This includes :meth:`DataFrame.assign`, :meth:`DataFrame.loc`, and getitem/setitem.
+
+It is expected that the support for ``pd.col()`` will be expanded to more methods
+in future releases.
+
 New Deprecation Policy
 ^^^^^^^^^^^^^^^^^^^^^^
 pandas 3.0.0 introduces a new 3-stage deprecation policy: using ``DeprecationWarning`` initially, then switching to ``FutureWarning`` for broader visibility in the last minor version before the next major release, and then removal of the deprecated functionality in the major release. This was done to give downstream packages more time to adjust to pandas deprecations, which should reduce the amount of warnings that a user gets from code that isn't theirs. See `PDEP 17 <https://pandas.pydata.org/pdeps/0017-backwards-compatibility-and-deprecation-policy.html>`_ for more details.
@@ -1139,6 +1160,7 @@ Timedelta
 - Accuracy improvement in :meth:`Timedelta.to_pytimedelta` to round microseconds consistently for large nanosecond based Timedelta (:issue:`57841`)
 - Bug in :class:`Timedelta` constructor failing to raise when passed an invalid keyword (:issue:`53801`)
 - Bug in :meth:`DataFrame.cumsum` which was raising ``IndexError`` if dtype is ``timedelta64[ns]`` (:issue:`57956`)
+- Bug in adding or subtracting a :class:`Timedelta` object with non-nanosecond unit to a python ``datetime.datetime`` object giving incorrect results; this now works correctly for Timedeltas inside the ``datetime.timedelta`` implementation bounds (:issue:`53643`)
 - Bug in multiplication operations with ``timedelta64`` dtype failing to raise ``TypeError`` when multiplying by ``bool`` objects or dtypes (:issue:`58054`)
 - Bug in multiplication operations with ``timedelta64`` dtype incorrectly raising when multiplying by numpy-nullable dtypes or pyarrow integer dtypes (:issue:`58054`)
 

doc/source/whatsnew/v3.0.0.rst

@@ -86,7 +86,8 @@ dependencies:
   - natsort  # DataFrame.sort_values doctest
   - pickleshare  # Needed for IPython Sphinx directive in the docs GH#60429
   - numpydoc
-  - pydata-sphinx-theme=0.16
+  # temporary installed with pip with custom patch until released
+  # - pydata-sphinx-theme=0.16
   - pytest-cython  # doctest
   - sphinx
   - sphinx-design
@@ -126,3 +127,4 @@ dependencies:
 
   - pip:
       - tzdata>=2023.3
+      - https://github.com/jorisvandenbossche/pydata-sphinx-theme/archive/refs/heads/v0.16.1+dismissable-announcement-banner.zip

environment.yml

@@ -35,6 +35,11 @@ def using_string_dtype() -> bool:
     return _mode_options["infer_string"]
 
 
+def using_python_scalars() -> bool:
+    _mode_options = _global_config["future"]
+    return _mode_options["python_scalars"]
+
+
 def is_nan_na() -> bool:
     _mode_options = _global_config["future"]
     return not _mode_options["distinguish_nan_and_na"]