Merge branch 'main' into fix/type_coercion_for_unobserved_categories

.circleci/config.yml

@@ -72,10 +72,6 @@ jobs:
           no_output_timeout: 30m # Sometimes the tests won't generate any output, make sure the job doesn't get killed by that
           command: |
             pip3 install cibuildwheel==2.15.0
-            # When this is a nightly wheel build, allow picking up NumPy 2.0 dev wheels:
-            if [[ "$IS_SCHEDULE_DISPATCH" == "true" || "$IS_PUSH" != 'true' ]]; then
-                export CIBW_ENVIRONMENT="PIP_EXTRA_INDEX_URL=https://pypi.anaconda.org/scientific-python-nightly-wheels/simple"
-            fi
             cibuildwheel --prerelease-pythons --output-dir wheelhouse
 
           environment:

.github/workflows/code-checks.yml

@@ -85,7 +85,7 @@ jobs:
         echo "PYTHONPATH=$PYTHONPATH" >> $GITHUB_ENV
       if: ${{ steps.build.outcome == 'success' && always() }}
 
-    - name: Typing + pylint
+    - name: Typing
       uses: pre-commit/action@v3.0.1
       with:
         extra_args: --verbose --hook-stage manual --all-files

.github/workflows/wheels.yml

@@ -139,27 +139,14 @@ jobs:
         shell: bash -el {0}
         run: echo "sdist_name=$(cd ./dist && ls -d */)" >> "$GITHUB_ENV"
 
-      - name: Build normal wheels
-        if: ${{ (env.IS_SCHEDULE_DISPATCH != 'true' || env.IS_PUSH == 'true') }}
+      - name: Build wheels
         uses: pypa/cibuildwheel@v2.17.0
         with:
          package-dir: ./dist/${{ startsWith(matrix.buildplat[1], 'macosx') && env.sdist_name || needs.build_sdist.outputs.sdist_file }}
         env:
           CIBW_PRERELEASE_PYTHONS: True
           CIBW_BUILD: ${{ matrix.python[0] }}-${{ matrix.buildplat[1] }}
 
-      - name: Build nightly wheels (with NumPy pre-release)
-        if: ${{ (env.IS_SCHEDULE_DISPATCH == 'true' && env.IS_PUSH != 'true') }}
-        uses: pypa/cibuildwheel@v2.17.0
-        with:
-         package-dir: ./dist/${{ startsWith(matrix.buildplat[1], 'macosx') && env.sdist_name || needs.build_sdist.outputs.sdist_file }}
-        env:
-          # The nightly wheels should be build witht he NumPy 2.0 pre-releases
-          # which requires the additional URL.
-          CIBW_ENVIRONMENT: PIP_EXTRA_INDEX_URL=https://pypi.anaconda.org/scientific-python-nightly-wheels/simple
-          CIBW_PRERELEASE_PYTHONS: True
-          CIBW_BUILD: ${{ matrix.python[0] }}-${{ matrix.buildplat[1] }}
-
       - name: Set up Python
         uses: mamba-org/setup-micromamba@v1
         with:

.pre-commit-config.yaml

@@ -16,10 +16,10 @@ ci:
     autofix_prs: false
     autoupdate_schedule: monthly
     # manual stage hooks
-    skip: [pylint, pyright, mypy]
+    skip: [pyright, mypy]
 repos:
 -   repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.3.1
+    rev: v0.3.4
     hooks:
     -   id: ruff
         args: [--exit-non-zero-on-fix]
@@ -30,16 +30,10 @@ repos:
         files: ^pandas
         exclude: ^pandas/tests
         args: [--select, "ANN001,ANN2", --fix-only, --exit-non-zero-on-fix]
-    -   id: ruff
-        name: ruff-use-pd_array-in-core
-        alias: ruff-use-pd_array-in-core
-        files: ^pandas/core/
-        exclude: ^pandas/core/api\.py$
-        args: [--select, "ICN001", --exit-non-zero-on-fix]
     -   id: ruff-format
         exclude: ^scripts
 -   repo: https://github.com/jendrikseipp/vulture
-    rev: 'v2.10'
+    rev: 'v2.11'
     hooks:
       - id: vulture
         entry: python scripts/run_vulture.py
@@ -73,31 +67,12 @@ repos:
     -   id: fix-encoding-pragma
         args: [--remove]
     -   id: trailing-whitespace
--   repo: https://github.com/pylint-dev/pylint
-    rev: v3.0.1
-    hooks:
-    -   id: pylint
-        stages: [manual]
-        args: [--load-plugins=pylint.extensions.redefined_loop_name, --fail-on=I0021]
-    -   id: pylint
-        alias: redefined-outer-name
-        name: Redefining name from outer scope
-        files: ^pandas/
-        exclude: |
-            (?x)
-            ^pandas/tests  # keep excluded
-            |/_testing/  # keep excluded
-            |^pandas/util/_test_decorators\.py  # keep excluded
-            |^pandas/_version\.py  # keep excluded
-            |^pandas/conftest\.py  # keep excluded
-        args: [--disable=all, --enable=redefined-outer-name]
-        stages: [manual]
 -   repo: https://github.com/PyCQA/isort
-    rev: 5.12.0
+    rev: 5.13.2
     hooks:
     -   id: isort
 -   repo: https://github.com/asottile/pyupgrade
-    rev: v3.15.0
+    rev: v3.15.2
     hooks:
     -   id: pyupgrade
         args: [--py39-plus]
@@ -116,7 +91,7 @@ repos:
     hooks:
     - id: sphinx-lint
 -   repo: https://github.com/pre-commit/mirrors-clang-format
-    rev: v17.0.6
+    rev: v18.1.2
     hooks:
     - id: clang-format
       files: ^pandas/_libs/src|^pandas/_libs/include

asv_bench/asv.conf.json

@@ -41,6 +41,7 @@
     // pip (with all the conda available packages installed first,
     // followed by the pip installed packages).
     "matrix": {
+        "pip+build": [],
         "Cython": ["3.0"],
         "matplotlib": [],
         "sqlalchemy": [],

asv_bench/benchmarks/categoricals.py

@@ -24,7 +24,7 @@ def setup(self):
         self.codes = np.tile(range(len(self.categories)), N)
 
         self.datetimes = pd.Series(
-            pd.date_range("1995-01-01 00:00:00", periods=N / 10, freq="s")
+            pd.date_range("1995-01-01 00:00:00", periods=N // 10, freq="s")
         )
         self.datetimes_with_nat = self.datetimes.copy()
         self.datetimes_with_nat.iloc[-1] = pd.NaT

asv_bench/benchmarks/frame_methods.py

@@ -862,4 +862,28 @@ def time_last_valid_index(self, dtype):
         self.df.last_valid_index()
 
 
+class Update:
+    def setup(self):
+        rng = np.random.default_rng()
+        self.df = DataFrame(rng.uniform(size=(1_000_000, 10)))
+
+        idx = rng.choice(range(1_000_000), size=1_000_000, replace=False)
+        self.df_random = DataFrame(self.df, index=idx)
+
+        idx = rng.choice(range(1_000_000), size=100_000, replace=False)
+        cols = rng.choice(range(10), size=2, replace=False)
+        self.df_sample = DataFrame(
+            rng.uniform(size=(100_000, 2)), index=idx, columns=cols
+        )
+
+    def time_to_update_big_frame_small_arg(self):
+        self.df.update(self.df_sample)
+
+    def time_to_update_random_indices(self):
+        self.df_random.update(self.df_sample)
+
+    def time_to_update_small_frame_big_arg(self):
+        self.df_sample.update(self.df)
+
+
 from .pandas_vb_common import setup  # noqa: F401 isort:skip

asv_bench/benchmarks/timeseries.py

@@ -29,7 +29,7 @@ def setup(self, index_type):
             "dst": date_range(
                 start="10/29/2000 1:00:00", end="10/29/2000 1:59:59", freq="s"
             ),
-            "repeated": date_range(start="2000", periods=N / 10, freq="s").repeat(10),
+            "repeated": date_range(start="2000", periods=N // 10, freq="s").repeat(10),
             "tz_aware": date_range(start="2000", periods=N, freq="s", tz="US/Eastern"),
             "tz_local": date_range(
                 start="2000", periods=N, freq="s", tz=dateutil.tz.tzlocal()

ci/code_checks.sh

@@ -83,8 +83,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.DataFrame.__iter__ SA01" \
         -i "pandas.DataFrame.assign SA01" \
         -i "pandas.DataFrame.at_time PR01" \
-        -i "pandas.DataFrame.axes SA01" \
-        -i "pandas.DataFrame.backfill PR01,SA01" \
         -i "pandas.DataFrame.bfill SA01" \
         -i "pandas.DataFrame.columns SA01" \
         -i "pandas.DataFrame.copy SA01" \
@@ -99,12 +97,10 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.DataFrame.kurt RT03,SA01" \
         -i "pandas.DataFrame.kurtosis RT03,SA01" \
         -i "pandas.DataFrame.last_valid_index SA01" \
-        -i "pandas.DataFrame.mask RT03" \
         -i "pandas.DataFrame.max RT03" \
         -i "pandas.DataFrame.mean RT03,SA01" \
         -i "pandas.DataFrame.median RT03,SA01" \
         -i "pandas.DataFrame.min RT03" \
-        -i "pandas.DataFrame.pad PR01,SA01" \
         -i "pandas.DataFrame.plot PR02,SA01" \
         -i "pandas.DataFrame.pop SA01" \
         -i "pandas.DataFrame.prod RT03" \
@@ -119,19 +115,11 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.DataFrame.sparse.to_dense SA01" \
         -i "pandas.DataFrame.std PR01,RT03,SA01" \
         -i "pandas.DataFrame.sum RT03" \
-        -i "pandas.DataFrame.swapaxes PR01,SA01" \
         -i "pandas.DataFrame.swaplevel SA01" \
         -i "pandas.DataFrame.to_feather SA01" \
         -i "pandas.DataFrame.to_markdown SA01" \
         -i "pandas.DataFrame.to_parquet RT03" \
-        -i "pandas.DataFrame.to_period SA01" \
-        -i "pandas.DataFrame.to_timestamp SA01" \
-        -i "pandas.DataFrame.tz_convert SA01" \
-        -i "pandas.DataFrame.tz_localize SA01" \
-        -i "pandas.DataFrame.unstack RT03" \
-        -i "pandas.DataFrame.value_counts RT03" \
         -i "pandas.DataFrame.var PR01,RT03,SA01" \
-        -i "pandas.DataFrame.where RT03" \
         -i "pandas.DatetimeIndex.ceil SA01" \
         -i "pandas.DatetimeIndex.date SA01" \
         -i "pandas.DatetimeIndex.day SA01" \
@@ -165,11 +153,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.DatetimeTZDtype SA01" \
         -i "pandas.DatetimeTZDtype.tz SA01" \
         -i "pandas.DatetimeTZDtype.unit SA01" \
-        -i "pandas.ExcelFile PR01,SA01" \
-        -i "pandas.ExcelFile.parse PR01,SA01" \
-        -i "pandas.ExcelWriter SA01" \
-        -i "pandas.Float32Dtype SA01" \
-        -i "pandas.Float64Dtype SA01" \
         -i "pandas.Grouper PR02,SA01" \
         -i "pandas.HDFStore.append PR01,SA01" \
         -i "pandas.HDFStore.get SA01" \
@@ -226,7 +209,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Index.to_list RT03" \
         -i "pandas.Index.union PR07,RT03,SA01" \
         -i "pandas.Index.unique RT03" \
-        -i "pandas.Index.value_counts RT03" \
         -i "pandas.Index.view GL08" \
         -i "pandas.Int16Dtype SA01" \
         -i "pandas.Int32Dtype SA01" \
@@ -400,7 +382,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Series.list.flatten SA01" \
         -i "pandas.Series.list.len SA01" \
         -i "pandas.Series.lt PR07,SA01" \
-        -i "pandas.Series.mask RT03" \
         -i "pandas.Series.max RT03" \
         -i "pandas.Series.mean RT03,SA01" \
         -i "pandas.Series.median RT03,SA01" \
@@ -477,17 +458,10 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Series.to_frame SA01" \
         -i "pandas.Series.to_list RT03" \
         -i "pandas.Series.to_markdown SA01" \
-        -i "pandas.Series.to_period SA01" \
         -i "pandas.Series.to_string SA01" \
-        -i "pandas.Series.to_timestamp RT03,SA01" \
         -i "pandas.Series.truediv PR07" \
-        -i "pandas.Series.tz_convert SA01" \
-        -i "pandas.Series.tz_localize SA01" \
-        -i "pandas.Series.unstack SA01" \
         -i "pandas.Series.update PR07,SA01" \
-        -i "pandas.Series.value_counts RT03" \
         -i "pandas.Series.var PR01,RT03,SA01" \
-        -i "pandas.Series.where RT03" \
         -i "pandas.SparseDtype SA01" \
         -i "pandas.Timedelta PR07,SA01" \
         -i "pandas.Timedelta.as_unit SA01" \
@@ -681,60 +655,40 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.core.groupby.DataFrameGroupBy.__iter__ RT03,SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.agg RT03" \
         -i "pandas.core.groupby.DataFrameGroupBy.aggregate RT03" \
-        -i "pandas.core.groupby.DataFrameGroupBy.apply RT03" \
         -i "pandas.core.groupby.DataFrameGroupBy.boxplot PR07,RT03,SA01" \
-        -i "pandas.core.groupby.DataFrameGroupBy.cummax RT03" \
-        -i "pandas.core.groupby.DataFrameGroupBy.cummin RT03" \
-        -i "pandas.core.groupby.DataFrameGroupBy.cumprod RT03" \
-        -i "pandas.core.groupby.DataFrameGroupBy.cumsum RT03" \
-        -i "pandas.core.groupby.DataFrameGroupBy.filter RT03,SA01" \
+        -i "pandas.core.groupby.DataFrameGroupBy.filter SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.get_group RT03,SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.groups SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.hist RT03" \
         -i "pandas.core.groupby.DataFrameGroupBy.indices SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.max SA01" \
-        -i "pandas.core.groupby.DataFrameGroupBy.mean RT03" \
         -i "pandas.core.groupby.DataFrameGroupBy.median SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.min SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.nth PR02" \
-        -i "pandas.core.groupby.DataFrameGroupBy.nunique RT03,SA01" \
+        -i "pandas.core.groupby.DataFrameGroupBy.nunique SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.ohlc SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.plot PR02,SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.prod SA01" \
-        -i "pandas.core.groupby.DataFrameGroupBy.rank RT03" \
-        -i "pandas.core.groupby.DataFrameGroupBy.resample RT03" \
         -i "pandas.core.groupby.DataFrameGroupBy.sem SA01" \
-        -i "pandas.core.groupby.DataFrameGroupBy.skew RT03" \
         -i "pandas.core.groupby.DataFrameGroupBy.sum SA01" \
-        -i "pandas.core.groupby.DataFrameGroupBy.transform RT03" \
         -i "pandas.core.groupby.SeriesGroupBy.__iter__ RT03,SA01" \
         -i "pandas.core.groupby.SeriesGroupBy.agg RT03" \
         -i "pandas.core.groupby.SeriesGroupBy.aggregate RT03" \
-        -i "pandas.core.groupby.SeriesGroupBy.apply RT03" \
-        -i "pandas.core.groupby.SeriesGroupBy.cummax RT03" \
-        -i "pandas.core.groupby.SeriesGroupBy.cummin RT03" \
-        -i "pandas.core.groupby.SeriesGroupBy.cumprod RT03" \
-        -i "pandas.core.groupby.SeriesGroupBy.cumsum RT03" \
-        -i "pandas.core.groupby.SeriesGroupBy.filter PR01,RT03,SA01" \
+        -i "pandas.core.groupby.SeriesGroupBy.filter PR01,SA01" \
         -i "pandas.core.groupby.SeriesGroupBy.get_group RT03,SA01" \
         -i "pandas.core.groupby.SeriesGroupBy.groups SA01" \
         -i "pandas.core.groupby.SeriesGroupBy.indices SA01" \
         -i "pandas.core.groupby.SeriesGroupBy.is_monotonic_decreasing SA01" \
         -i "pandas.core.groupby.SeriesGroupBy.is_monotonic_increasing SA01" \
         -i "pandas.core.groupby.SeriesGroupBy.max SA01" \
-        -i "pandas.core.groupby.SeriesGroupBy.mean RT03" \
         -i "pandas.core.groupby.SeriesGroupBy.median SA01" \
         -i "pandas.core.groupby.SeriesGroupBy.min SA01" \
         -i "pandas.core.groupby.SeriesGroupBy.nth PR02" \
         -i "pandas.core.groupby.SeriesGroupBy.ohlc SA01" \
         -i "pandas.core.groupby.SeriesGroupBy.plot PR02,SA01" \
         -i "pandas.core.groupby.SeriesGroupBy.prod SA01" \
-        -i "pandas.core.groupby.SeriesGroupBy.rank RT03" \
-        -i "pandas.core.groupby.SeriesGroupBy.resample RT03" \
         -i "pandas.core.groupby.SeriesGroupBy.sem SA01" \
-        -i "pandas.core.groupby.SeriesGroupBy.skew RT03" \
         -i "pandas.core.groupby.SeriesGroupBy.sum SA01" \
-        -i "pandas.core.groupby.SeriesGroupBy.transform RT03" \
         -i "pandas.core.resample.Resampler.__iter__ RT03,SA01" \
         -i "pandas.core.resample.Resampler.ffill RT03" \
         -i "pandas.core.resample.Resampler.get_group RT03,SA01" \

doc/redirects.csv

@@ -1422,7 +1422,6 @@ reference/api/pandas.Series.transpose,pandas.Series.T
 reference/api/pandas.Index.transpose,pandas.Index.T
 reference/api/pandas.Index.notnull,pandas.Index.notna
 reference/api/pandas.Index.tolist,pandas.Index.to_list
-reference/api/pandas.arrays.PandasArray,pandas.arrays.NumpyExtensionArray
 reference/api/pandas.core.groupby.DataFrameGroupBy.backfill,pandas.core.groupby.DataFrameGroupBy.bfill
 reference/api/pandas.core.groupby.GroupBy.backfill,pandas.core.groupby.DataFrameGroupBy.bfill
 reference/api/pandas.core.resample.Resampler.backfill,pandas.core.resample.Resampler.bfill

doc/source/getting_started/install.rst

@@ -269,6 +269,8 @@ SciPy                     1.10.0             computation     Miscellaneous stati
 xarray                    2022.12.0          computation     pandas-like API for N-dimensional data
 ========================= ================== =============== =============================================================
 
+.. _install.excel_dependencies:
+
 Excel files
 ^^^^^^^^^^^
 

doc/source/getting_started/intro_tutorials/02_read_write.rst

@@ -111,6 +111,12 @@ strings (``object``).
 
 My colleague requested the Titanic data as a spreadsheet.
 
+.. note::
+    If you want to use :func:`~pandas.to_excel` and :func:`~pandas.read_excel`,
+    you need to install an Excel reader as outlined in the
+    :ref:`Excel files <install.excel_dependencies>` section of the
+    installation documentation.
+
 .. ipython:: python
 
     titanic.to_excel("titanic.xlsx", sheet_name="passengers", index=False)

doc/source/user_guide/basics.rst

@@ -476,15 +476,15 @@ For example:
 .. ipython:: python
 
    df
-   df.mean(0)
-   df.mean(1)
+   df.mean(axis=0)
+   df.mean(axis=1)
 
 All such methods have a ``skipna`` option signaling whether to exclude missing
 data (``True`` by default):
 
 .. ipython:: python
 
-   df.sum(0, skipna=False)
+   df.sum(axis=0, skipna=False)
    df.sum(axis=1, skipna=True)
 
 Combined with the broadcasting / arithmetic behavior, one can describe various
@@ -495,8 +495,8 @@ standard deviation of 1), very concisely:
 
    ts_stand = (df - df.mean()) / df.std()
    ts_stand.std()
-   xs_stand = df.sub(df.mean(1), axis=0).div(df.std(1), axis=0)
-   xs_stand.std(1)
+   xs_stand = df.sub(df.mean(axis=1), axis=0).div(df.std(axis=1), axis=0)
+   xs_stand.std(axis=1)
 
 Note that methods like :meth:`~DataFrame.cumsum` and :meth:`~DataFrame.cumprod`
 preserve the location of ``NaN`` values. This is somewhat different from