Merge branch 'main' into patch-4

Author: vkverma9534

.github/workflows/wheels.yml

@@ -45,6 +45,7 @@ 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 }}
@@ -117,6 +118,7 @@ jobs:
             python: ["cp313t", "3.13"]
 
     env:
+      IS_PUSH: ${{ github.event_name == 'push' && startsWith(github.ref, 'refs/tags/v') }}
       IS_SCHEDULE_DISPATCH: ${{ github.event_name == 'schedule' || github.event_name == 'workflow_dispatch' }}
     steps:
       - name: Checkout pandas
@@ -164,7 +166,6 @@ jobs:
         uses: pypa/cibuildwheel@v3.2.1
         with:
          package-dir: ./dist/${{ startsWith(matrix.buildplat[1], 'macosx') && env.sdist_name || needs.build_sdist.outputs.sdist_file }}
-         output-dir: ./dist
         env:
           CIBW_BUILD: ${{ matrix.python[0] }}-${{ matrix.buildplat[1] }}
           CIBW_BUILD_FRONTEND: ${{ matrix.cibw_build_frontend || 'pip' }}
@@ -195,19 +196,26 @@ jobs:
 
       - name: Validate wheel RECORD
         shell: bash -el {0}
-        run: for whl in $(ls ./dist/*.whl); do wheel unpack $whl -d /tmp; done
+        run: for whl in $(ls wheelhouse); do wheel unpack wheelhouse/$whl -d /tmp; done
 
       - uses: actions/upload-artifact@v6
         with:
           name: ${{ matrix.python[0] }}-${{ matrix.buildplat[1] }}
-          path: ./dist/*.whl
+          path: ./wheelhouse/*.whl
 
       - name: Upload wheels & sdist
-        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}}
+        if: ${{ success() && (env.IS_SCHEDULE_DISPATCH == 'true' || env.IS_PUSH == 'true') }}
+        shell: bash -el {0}
+        env:
+          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).
+        # The tokens were originally generated at anaconda.org
+        run: |
+          source ci/upload_wheels.sh
+          set_upload_vars
+          upload_wheels
 
   publish:
     if: >

.gitignore

@@ -67,6 +67,7 @@ pandas/py.typed
 .ropeproject
 # wheel files
 *.whl
+**/wheelhouse/*
 pip-wheel-metadata
 # coverage
 .coverage

README.md

@@ -115,7 +115,7 @@ details, see the commit logs at https://github.com/pandas-dev/pandas.
 ## Dependencies
 - [NumPy - Adds support for large, multi-dimensional arrays, matrices and high-level mathematical functions to operate on these arrays](https://www.numpy.org)
 - [python-dateutil - Provides powerful extensions to the standard datetime module](https://dateutil.readthedocs.io/en/stable/index.html)
-- [tzdata - Provides an IANA time zone database](https://tzdata.readthedocs.io/en/latest/)
+- [tzdata - Provides an IANA time zone database](https://tzdata.readthedocs.io/en/latest/) (Only required on Windows/Emscripten)
 
 See the [full installation instructions](https://pandas.pydata.org/pandas-docs/stable/install.html#dependencies) for minimum supported versions of required, recommended and optional dependencies.
 

ci/upload_wheels.sh

@@ -0,0 +1,36 @@
+#!/bin/bash
+# Modified from numpy's https://github.com/numpy/numpy/blob/main/tools/wheels/upload_wheels.sh
+
+set_upload_vars() {
+    echo "IS_SCHEDULE_DISPATCH is $IS_SCHEDULE_DISPATCH"
+    if [[ "$IS_SCHEDULE_DISPATCH" == "true" ]]; then
+        echo scheduled or dispatched event
+        export ANACONDA_ORG="scientific-python-nightly-wheels"
+        export TOKEN="$PANDAS_NIGHTLY_UPLOAD_TOKEN"
+        export ANACONDA_UPLOAD="true"
+    else
+        echo non-dispatch event
+        export ANACONDA_UPLOAD="false"
+    fi
+}
+upload_wheels() {
+    echo "${PWD}"
+    if [[ ${ANACONDA_UPLOAD} == true ]]; then
+        if [ -z "${TOKEN}" ]; then
+            echo no token set, not uploading
+        else
+            # sdists are located under dist folder when built through setup.py
+            if compgen -G "./dist/*.gz"; then
+                echo "Found sdist"
+                anaconda -q -t "${TOKEN}" upload --skip -u "${ANACONDA_ORG}" ./dist/*.gz
+                echo "Uploaded sdist"
+            fi
+            if compgen -G "./wheelhouse/*.whl"; then
+                echo "Found wheel"
+                anaconda -q -t "${TOKEN}" upload --skip -u "${ANACONDA_ORG}" ./wheelhouse/*.whl
+                echo "Uploaded wheel"
+            fi
+            echo "PyPI-style index: https://pypi.anaconda.org/$ANACONDA_ORG/simple"
+        fi
+    fi
+}

doc/source/getting_started/install.rst

@@ -150,9 +150,11 @@ Package                                                          Minimum support
 ================================================================ ==========================
 `NumPy <https://numpy.org>`__                                    1.26.0
 `python-dateutil <https://dateutil.readthedocs.io/en/stable/>`__ 2.8.2
-`tzdata <https://pypi.org/project/tzdata/>`__                    2023.3
+ `tzdata <https://pypi.org/project/tzdata/>`__ \*                /
 ================================================================ ==========================
 
+\* ``tzdata`` is only required on Windows and Pyodide (Emscripten).
+
 Generally, the minimum supported version is ~2 years old from the release date of a major or minor pandas version.
 
 .. _install.optional_dependencies:

doc/source/whatsnew/v3.0.0.rst

@@ -686,8 +686,6 @@ The following required dependencies were updated:
 +=================+======================+
 | numpy           | 1.26.0               |
 +-----------------+----------------------+
-| tzdata          | 2023.3               |
-+-----------------+----------------------+
 
 For `optional libraries <https://pandas.pydata.org/docs/getting_started/install.html>`_ the general recommendation is to use the latest version.
 The following table lists the lowest version per library that is currently being tested throughout the development of pandas.
@@ -820,6 +818,7 @@ Other API changes
   :meth:`~DataFrame.ffill`, :meth:`~DataFrame.bfill`, :meth:`~DataFrame.interpolate`,
   :meth:`~DataFrame.where`, :meth:`~DataFrame.mask`, :meth:`~DataFrame.clip`) now return
   the modified DataFrame or Series (``self``) instead of ``None`` when ``inplace=True`` (:issue:`63207`)
+- All Index constructors now copy ``numpy.ndarray`` and ``ExtensionArray`` inputs by default when ``copy=None``, consistent with :class:`Series` behavior (:issue:`63388`)
 
 .. ---------------------------------------------------------------------------
 .. _whatsnew_300.deprecations:
@@ -1160,6 +1159,7 @@ 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`)
 
@@ -1227,6 +1227,7 @@ Indexing
 - Bug in :meth:`DataFrame.loc.__getitem__` and :meth:`DataFrame.iloc.__getitem__` with a :class:`CategoricalDtype` column with integer categories raising when trying to index a row containing a ``NaN`` entry (:issue:`58954`)
 - Bug in :meth:`Index.__getitem__` incorrectly raising with a 0-dim ``np.ndarray`` key (:issue:`55601`)
 - Bug in :meth:`Index.get_indexer` not casting missing values correctly for new string datatype (:issue:`55833`)
+- Bug in :meth:`Index.intersection`, :meth:`Index.union`, :meth:`MultiIndex.intersection`, and :meth:`MultiIndex.union` returning a reference to the original Index instead of a new instance when operating on identical indexes, which could cause metadata corruption when modifying the result (:issue:`63169`)
 - Bug in adding new rows with :meth:`DataFrame.loc.__setitem__` or :class:`Series.loc.__setitem__` which failed to retain dtype on the object's index in some cases (:issue:`41626`)
 - Bug in indexing on a :class:`DatetimeIndex` with a ``timestamp[pyarrow]`` dtype or on a :class:`TimedeltaIndex` with a ``duration[pyarrow]`` dtype (:issue:`62277`)
 

pandas/_libs/meson.build

@@ -160,7 +160,7 @@ foreach ext_name, ext_dict : libs_sources
         ext_dict.get('sources'),
         cython_args: cython_args,
         include_directories: [inc_np, inc_pd],
-        dependencies: ext_dict.get('deps', ''),
+        dependencies: ext_dict.get('deps', []),
         subdir: 'pandas/_libs',
         install: true,
     )

pandas/_libs/tslibs/meson.build

@@ -40,7 +40,7 @@ foreach ext_name, ext_dict : tslibs_sources
         ext_dict.get('sources'),
         cython_args: cython_args,
         include_directories: [inc_np, inc_pd],
-        dependencies: ext_dict.get('deps', ''),
+        dependencies: ext_dict.get('deps', []),
         subdir: 'pandas/_libs/tslibs',
         install: true,
     )

pandas/_libs/tslibs/timedeltas.pyx

@@ -1022,9 +1022,23 @@ cdef _timedelta_from_value_and_reso(cls, int64_t value, NPY_DATETIMEUNIT reso):
     elif reso == NPY_DATETIMEUNIT.NPY_FR_us:
         td_base = _Timedelta.__new__(cls, microseconds=int(value))
     elif reso == NPY_DATETIMEUNIT.NPY_FR_ms:
-        td_base = _Timedelta.__new__(cls, milliseconds=0)
+        if -86_399_999_913_600_000 <= value < 86_400_000_000_000_000:
+            # i.e. we are in range for pytimedelta. By passing the
+            #  'correct' value here we can
+            #   make pydatetime + Timedelta operations work correctly,
+            #  xref GH#53643
+            td_base = _Timedelta.__new__(cls, milliseconds=value)
+        else:
+            td_base = _Timedelta.__new__(cls, milliseconds=0)
     elif reso == NPY_DATETIMEUNIT.NPY_FR_s:
-        td_base = _Timedelta.__new__(cls, seconds=0)
+        if -86_399_999_913_600 <= value < 86_400_000_000_000:
+            # i.e. we are in range for pytimedelta. By passing the
+            #  'correct' value here we can
+            #   make pydatetime + Timedelta operations work correctly,
+            #  xref GH#53643
+            td_base = _Timedelta.__new__(cls, seconds=value)
+        else:
+            td_base = _Timedelta.__new__(cls, seconds=0)
     # Other resolutions are disabled but could potentially be implemented here:
     # elif reso == NPY_DATETIMEUNIT.NPY_FR_m:
     #    td_base = _Timedelta.__new__(Timedelta, minutes=int(value))

pandas/_libs/tslibs/timezones.pyx

@@ -59,9 +59,6 @@ cdef bint is_utc_zoneinfo(tzinfo tz):
             utc_zoneinfo = zoneinfo.ZoneInfo("UTC")
         except zoneinfo.ZoneInfoNotFoundError:
             return False
-        # Warn if tzdata is too old, even if there is a system tzdata to alert
-        # users about the mismatch between local/system tzdata
-        import_optional_dependency("tzdata", errors="warn", min_version="2022.7")
 
     return tz is utc_zoneinfo