Merge branch 'pandas-dev:main' into 59078-nrow-doc

Author: mdavis-xyz

.github/actions/build_pandas/action.yml

@@ -4,12 +4,6 @@ inputs:
   editable:
     description: Whether to build pandas in editable mode (default true)
     default: true
-  meson_args:
-    description: Extra flags to pass to meson
-    required: false
-  cflags_adds:
-    description: Items to append to the CFLAGS variable
-    required: false
 runs:
   using: composite
   steps:
@@ -30,12 +24,11 @@ runs:
 
     - name: Build Pandas
       run: |
-        export CFLAGS="$CFLAGS ${{ inputs.cflags_adds }}"
         if [[ ${{ inputs.editable }} == "true" ]]; then
-          pip install -e . --no-build-isolation -v --no-deps ${{ inputs.meson_args }} \
+          pip install -e . --no-build-isolation -v --no-deps \
             --config-settings=setup-args="--werror"
         else
-          pip install . --no-build-isolation -v --no-deps ${{ inputs.meson_args }} \
+          pip install . --no-build-isolation -v --no-deps \
             --config-settings=setup-args="--werror"
         fi
       shell: bash -el {0}

.github/actions/run-tests/action.yml

@@ -7,14 +7,14 @@ runs:
       shell: bash -el {0}
 
     - name: Publish test results
-      uses: actions/upload-artifact@v3
+      uses: actions/upload-artifact@v4
       with:
         name: Test results
         path: test-data.xml
       if: failure()
 
     - name: Upload coverage to Codecov
-      uses: codecov/codecov-action@v3
+      uses: codecov/codecov-action@v4
       with:
         flags: unittests
         name: codecov-pandas

.github/workflows/unit-tests.yml

@@ -74,9 +74,9 @@ jobs:
       PATTERN: ${{ matrix.pattern }}
       LANG: ${{ matrix.lang || 'C.UTF-8' }}
       LC_ALL: ${{ matrix.lc_all || '' }}
-      PANDAS_CI: ${{ matrix.pandas_ci || '1' }}
+      PANDAS_CI: '1'
       TEST_ARGS: ${{ matrix.test_args || '' }}
-      PYTEST_WORKERS: ${{ matrix.pytest_workers || 'auto' }}
+      PYTEST_WORKERS: 'auto'
       PYTEST_TARGET: ${{ matrix.pytest_target || 'pandas' }}
       NPY_PROMOTION_STATE: ${{ matrix.env_file == 'actions-311-numpydev.yaml' && 'weak' || 'legacy' }}
       # Clipboard tests
@@ -88,7 +88,7 @@ jobs:
 
     services:
       mysql:
-        image: mysql:8.0.33
+        image: mysql:8
         env:
           MYSQL_ALLOW_EMPTY_PASSWORD: yes
           MYSQL_DATABASE: pandas
@@ -101,7 +101,7 @@ jobs:
           - 3306:3306
 
       postgres:
-        image: postgres:13
+        image: postgres:16
         env:
           PGUSER: postgres
           POSTGRES_USER: postgres
@@ -116,7 +116,7 @@ jobs:
           - 5432:5432
 
       moto:
-        image: motoserver/moto:4.1.13
+        image: motoserver/moto:5.0.0
         env:
           AWS_ACCESS_KEY_ID: foobar_key
           AWS_SECRET_ACCESS_KEY: foobar_secret
@@ -148,9 +148,6 @@ jobs:
       uses: ./.github/actions/build_pandas
       # TODO: Re-enable once Pypy has Pypy 3.10 on conda-forge
       if: ${{ matrix.name != 'Pypy' }}
-      with:
-        meson_args: ${{ matrix.meson_args }}
-        cflags_adds: ${{ matrix.cflags_adds }}
 
     - name: Test (not single_cpu)
       uses: ./.github/actions/run-tests
@@ -302,7 +299,7 @@ jobs:
     #    To freeze this file, uncomment out the ``if: false`` condition, and migrate the jobs
     #    to the corresponding posix/windows-macos/sdist etc. workflows.
     # Feel free to modify this comment as necessary.
-    if: false # Uncomment this to freeze the workflow, comment it to unfreeze
+    # if: false # Uncomment this to freeze the workflow, comment it to unfreeze
     defaults:
       run:
         shell: bash -eou pipefail {0}
@@ -317,7 +314,7 @@ 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 }}-${{ matrix.pytest_target }}-dev
+      group: ${{ github.event_name == 'push' && github.run_number || github.ref }}-${{ matrix.os }}-python-dev
       cancel-in-progress: true
 
     env:
@@ -334,7 +331,7 @@ jobs:
       - name: Set up Python Dev Version
         uses: actions/setup-python@v5
         with:
-          python-version: '3.12-dev'
+          python-version: '3.13-dev'
 
       - name: Build Environment
         run: |
@@ -349,6 +346,51 @@ jobs:
       - name: Run Tests
         uses: ./.github/actions/run-tests
 
+  python-freethreading:
+    defaults:
+      run:
+        shell: bash -eou pipefail {0}
+    runs-on: ubuntu-22.04
+
+    timeout-minutes: 90
+
+    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
+      cancel-in-progress: true
+
+    env:
+      PYTEST_WORKERS: "auto"
+      PANDAS_CI: 1
+      PATTERN: "not slow and not network and not clipboard and not single_cpu"
+      PYTEST_TARGET: pandas
+
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Set up Python Free-threading Version
+        uses: deadsnakes/[email protected]
+        with:
+          python-version: 3.13-dev
+          nogil: true
+
+      - name: Build Environment
+        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 numpy cython
+          python -m pip install versioneer[toml]
+          python -m pip install python-dateutil pytz tzdata hypothesis>=6.46.1 pytest>=7.3.2 pytest-xdist>=2.2.0 pytest-cov
+          python -m pip install -ve . --no-build-isolation --no-index --no-deps --config-settings=setup-args="--werror"
+          python -m pip list
+
+      - name: Run Tests
+        uses: ./.github/actions/run-tests
+        env:
+          PYTHON_GIL: 0
+
   emscripten:
     # Note: the Python version, Emscripten toolchain version are determined
     # by the Pyodide version. The appropriate versions can be found in the

asv_bench/benchmarks/tslibs/timedelta.py

@@ -20,7 +20,7 @@ def time_from_int(self):
         Timedelta(123456789)
 
     def time_from_unit(self):
-        Timedelta(1, unit="d")
+        Timedelta(1, unit="D")
 
     def time_from_components(self):
         Timedelta(

ci/code_checks.sh

@@ -162,7 +162,7 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Series.ne SA01" \
         -i "pandas.Series.pad PR01,SA01" \
         -i "pandas.Series.plot PR02" \
-        -i "pandas.Series.pop RT03,SA01" \
+        -i "pandas.Series.pop SA01" \
         -i "pandas.Series.prod RT03" \
         -i "pandas.Series.product RT03" \
         -i "pandas.Series.reorder_levels RT03,SA01" \
@@ -260,7 +260,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Timestamp.to_period PR01,SA01" \
         -i "pandas.Timestamp.today SA01" \
         -i "pandas.Timestamp.toordinal SA01" \
-        -i "pandas.Timestamp.tz SA01" \
         -i "pandas.Timestamp.tz_localize SA01" \
         -i "pandas.Timestamp.tzinfo GL08" \
         -i "pandas.Timestamp.tzname SA01" \

ci/deps/actions-311-pyarrownightly.yaml

@@ -18,7 +18,7 @@ dependencies:
 
   # required dependencies
   - python-dateutil
-  - numpy
+  - numpy<2
   - pytz
   - pip
 

doc/source/whatsnew/v3.0.0.rst

@@ -39,6 +39,7 @@ Other enhancements
 - Users can globally disable any ``PerformanceWarning`` by setting the option ``mode.performance_warnings`` to ``False`` (:issue:`56920`)
 - :meth:`Styler.format_index_names` can now be used to format the index and column names (:issue:`48936` and :issue:`47489`)
 - :class:`.errors.DtypeWarning` improved to include column names when mixed data types are detected (:issue:`58174`)
+- :func:`DataFrame.to_excel` argument ``merge_cells`` now accepts a value of ``"columns"`` to only merge :class:`MultiIndex` column header header cells (:issue:`35384`)
 - :meth:`DataFrame.corrwith` now accepts ``min_periods`` as optional arguments, as in :meth:`DataFrame.corr` and :meth:`Series.corr` (:issue:`9490`)
 - :meth:`DataFrame.cummin`, :meth:`DataFrame.cummax`, :meth:`DataFrame.cumprod` and :meth:`DataFrame.cumsum` methods now have a ``numeric_only`` parameter (:issue:`53072`)
 - :meth:`DataFrame.fillna` and :meth:`Series.fillna` can now accept ``value=None``; for non-object dtype the corresponding NA value will be used (:issue:`57723`)
@@ -380,6 +381,8 @@ Other Removals
 - Enforced deprecation of strings ``T``, ``L``, ``U``, and ``N`` denoting frequencies in :class:`Minute`, :class:`Milli`, :class:`Micro`, :class:`Nano` (:issue:`57627`)
 - Enforced deprecation of strings ``T``, ``L``, ``U``, and ``N`` denoting units in :class:`Timedelta` (:issue:`57627`)
 - Enforced deprecation of the behavior of :func:`concat` when ``len(keys) != len(objs)`` would truncate to the shorter of the two. Now this raises a ``ValueError`` (:issue:`43485`)
+- Enforced deprecation of the behavior of :meth:`DataFrame.replace` and :meth:`Series.replace` with :class:`CategoricalDtype` that would introduce new categories. (:issue:`58270`)
+- Enforced deprecation of the behavior of :meth:`Series.argsort` in the presence of NA values (:issue:`58232`)
 - Enforced deprecation of values "pad", "ffill", "bfill", and "backfill" for :meth:`Series.interpolate` and :meth:`DataFrame.interpolate` (:issue:`57869`)
 - Enforced deprecation removing :meth:`Categorical.to_list`, use ``obj.tolist()`` instead (:issue:`51254`)
 - Enforced silent-downcasting deprecation for :ref:`all relevant methods <whatsnew_220.silent_downcasting>` (:issue:`54710`)
@@ -544,6 +547,7 @@ MultiIndex
 ^^^^^^^^^^
 - :func:`DataFrame.loc` with ``axis=0``  and :class:`MultiIndex` when setting a value adds extra columns (:issue:`58116`)
 - :meth:`DataFrame.melt` would not accept multiple names in ``var_name`` when the columns were a :class:`MultiIndex` (:issue:`58033`)
+- :meth:`MultiIndex.insert` would not insert NA value correctly at unified location of index -1 (:issue:`59003`)
 -
 
 I/O
@@ -556,7 +560,9 @@ I/O
 - Bug in :meth:`HDFStore.get` was failing to save data of dtype datetime64[s] correctly (:issue:`59004`)
 - Bug in :meth:`read_csv` raising ``TypeError`` when ``index_col`` is specified and ``na_values`` is a dict containing the key ``None``. (:issue:`57547`)
 - Bug in :meth:`read_csv` raising ``TypeError`` when ``nrows`` and ``iterator`` are specified without specifying a ``chunksize``. (:issue:`59079`)
+- Bug in :meth:`read_excel` raising ``ValueError`` when passing array of boolean values when ``dtype="boolean"``. (:issue:`58159`)
 - Bug in :meth:`read_stata` raising ``KeyError`` when input file is stored in big-endian format and contains strL data. (:issue:`58638`)
+-
 
 Period
 ^^^^^^

pandas/_libs/src/vendored/ujson/python/objToJSON.c

@@ -410,8 +410,8 @@ static void NpyArr_iterBegin(JSOBJ _obj, JSONTypeContext *tc) {
   npyarr->type_num = PyArray_DESCR(obj)->type_num;
 
   if (GET_TC(tc)->transpose) {
-    npyarr->dim = PyArray_DIM(obj, npyarr->ndim);
-    npyarr->stride = PyArray_STRIDE(obj, npyarr->ndim);
+    npyarr->dim = PyArray_DIM(obj, (int)npyarr->ndim);
+    npyarr->stride = PyArray_STRIDE(obj, (int)npyarr->ndim);
     npyarr->stridedim = npyarr->ndim;
     npyarr->index[npyarr->ndim] = 0;
     npyarr->inc = -1;
@@ -452,8 +452,8 @@ static void NpyArrPassThru_iterEnd(JSOBJ obj, JSONTypeContext *tc) {
     return;
   }
   const PyArrayObject *arrayobj = (const PyArrayObject *)npyarr->array;
-  npyarr->dim = PyArray_DIM(arrayobj, npyarr->stridedim);
-  npyarr->stride = PyArray_STRIDE(arrayobj, npyarr->stridedim);
+  npyarr->dim = PyArray_DIM(arrayobj, (int)npyarr->stridedim);
+  npyarr->stride = PyArray_STRIDE(arrayobj, (int)npyarr->stridedim);
   npyarr->dataptr += npyarr->stride;
 
   NpyArr_freeItemValue(obj, tc);
@@ -524,8 +524,8 @@ static int NpyArr_iterNext(JSOBJ _obj, JSONTypeContext *tc) {
   }
   const PyArrayObject *arrayobj = (const PyArrayObject *)npyarr->array;
 
-  npyarr->dim = PyArray_DIM(arrayobj, npyarr->stridedim);
-  npyarr->stride = PyArray_STRIDE(arrayobj, npyarr->stridedim);
+  npyarr->dim = PyArray_DIM(arrayobj, (int)npyarr->stridedim);
+  npyarr->stride = PyArray_STRIDE(arrayobj, (int)npyarr->stridedim);
   npyarr->index[npyarr->stridedim] = 0;
 
   ((PyObjectEncoder *)tc->encoder)->npyCtxtPassthru = npyarr;

pandas/_libs/tslibs/offsets.pyx

@@ -4948,7 +4948,12 @@ cpdef to_offset(freq, bint is_period=False):
     if result is None:
         raise ValueError(INVALID_FREQ_ERR_MSG.format(freq))
 
-    if is_period and not hasattr(result, "_period_dtype_code"):
+    try:
+        has_period_dtype_code = hasattr(result, "_period_dtype_code")
+    except ValueError:
+        has_period_dtype_code = False
+
+    if is_period and not has_period_dtype_code:
         if isinstance(freq, str):
             raise ValueError(f"{result.name} is not supported as period frequency")
         else:

pandas/_libs/tslibs/timestamps.pyx

@@ -2368,6 +2368,17 @@ timedelta}, default 'raise'
         """
         Alias for tzinfo.
 
+        The `tz` property provides a simple and direct way to retrieve the timezone
+        information of a `Timestamp` object. It is particularly useful when working
+        with time series data that includes timezone information, allowing for easy
+        access and manipulation of the timezone context.
+
+        See Also
+        --------
+        Timestamp.tzinfo : Returns the timezone information of the Timestamp.
+        Timestamp.tz_convert : Convert timezone-aware Timestamp to another time zone.
+        Timestamp.tz_localize : Localize the Timestamp to a timezone.
+
         Examples
         --------
         >>> ts = pd.Timestamp(1584226800, unit='s', tz='Europe/Stockholm')