Merge branch 'main' of https://github.com/pandas-dev/pandas into factorize_na_v2

� Conflicts:
�	pandas/core/arrays/_mixins.py

Author: rhshadrach

.github/workflows/code-checks.yml

@@ -140,22 +140,8 @@ jobs:
     - name: Run ASV benchmarks
       run: |
         cd asv_bench
-        asv check -E existing
-        git remote add upstream https://github.com/pandas-dev/pandas.git
-        git fetch upstream
         asv machine --yes
-        asv dev | sed "/failed$/ s/^/##[error]/" | tee benchmarks.log
-        if grep "failed" benchmarks.log > /dev/null ; then
-            exit 1
-        fi
-      if: ${{ steps.build.outcome == 'success' }}
-
-    - name: Publish benchmarks artifact
-      uses: actions/upload-artifact@v3
-      with:
-        name: Benchmarks log
-        path: asv_bench/benchmarks.log
-      if: failure()
+        asv run --quick --dry-run --strict --durations=30 --python=same
 
   build_docker_dev_environment:
     name: Build Docker Dev Environment

.github/workflows/posix.yml

@@ -61,7 +61,7 @@ jobs:
             env_file: actions-310-numpydev.yaml
             pattern: "not slow and not network and not single_cpu"
             pandas_testing_mode: "deprecate"
-            test_args: "-W error"
+            test_args: "-W error::DeprecationWarning:numpy"
       fail-fast: false
     name: ${{ matrix.name || format('{0} pyarrow={1} {2}', matrix.env_file, matrix.pyarrow_version, matrix.pattern) }}
     env:
@@ -174,7 +174,7 @@ jobs:
       if: always()
 
     - name: Build Version
-      run: pushd /tmp && python -c "import pandas; pandas.show_versions();" && popd
+      run: conda list
 
     - name: Publish test results
       uses: actions/upload-artifact@v3

.pre-commit-config.yaml

@@ -70,6 +70,10 @@ repos:
       - id: rst-inline-touching-normal
         types: [text]  # overwrite types: [rst]
         types_or: [python, rst]
+-   repo: https://github.com/sphinx-contrib/sphinx-lint
+    rev: v0.2
+    hooks:
+    - id: sphinx-lint
 -   repo: https://github.com/asottile/yesqa
     rev: v1.3.0
     hooks:
@@ -172,6 +176,13 @@ repos:
         files: ^pandas/core/
         exclude: ^pandas/core/api\.py$
         types: [python]
+    -   id: use-io-common-urlopen
+        name: Use pandas.io.common.urlopen instead of urllib.request.urlopen
+        language: python
+        entry: python scripts/use_io_common_urlopen.py
+        files: ^pandas/
+        exclude: ^pandas/tests/
+        types: [python]
     -   id: no-bool-in-core-generic
         name: Use bool_t instead of bool in pandas/core/generic.py
         entry: python scripts/no_bool_in_generic.py

LICENSES/KLIB_LICENSE

@@ -0,0 +1,23 @@
+The MIT License
+
+Copyright (c) 2008-     Attractive Chaos <attractor@live.co.uk>
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

LICENSES/OTHER

@@ -1,8 +1,3 @@
-numpydoc license
-----------------
-
-The numpydoc license is in pandas/doc/sphinxext/LICENSE.txt
-
 Bottleneck license
 ------------------
 
@@ -77,4 +72,4 @@ DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
 LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
 ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
 (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
-SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

MANIFEST.in

@@ -1,4 +1,5 @@
 include RELEASE.md
+include versioneer.py
 
 graft doc
 prune doc/build
@@ -54,9 +55,6 @@ global-exclude *.pxi
 # exclude the whole directory to avoid running related tests in sdist
 prune pandas/tests/io/parser/data
 
-include versioneer.py
-include pandas/_version.py
-include pandas/io/formats/templates/*.tpl
-
+# Selectively re-add *.cxx files that were excluded above
 graft pandas/_libs/src
 graft pandas/_libs/tslibs/src

ci/code_checks.sh

@@ -78,8 +78,8 @@ fi
 ### DOCSTRINGS ###
 if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
 
-    MSG='Validate docstrings (EX04, GL01, GL02, GL03, GL04, GL05, GL06, GL07, GL09, GL10, PR03, PR04, PR05, PR06, PR08, PR09, PR10, RT01, RT04, RT05, SA02, SA03, SS01, SS02, SS03, SS04, SS05)' ; echo $MSG
-    $BASE_DIR/scripts/validate_docstrings.py --format=actions --errors=EX04,GL01,GL02,GL03,GL04,GL05,GL06,GL07,GL09,GL10,PR03,PR04,PR05,PR06,PR08,PR09,PR10,RT01,RT04,RT05,SA02,SA03,SS01,SS02,SS03,SS04,SS05
+    MSG='Validate docstrings (EX04, GL01, GL02, GL03, GL04, GL05, GL06, GL07, GL09, GL10, PR03, PR04, PR05, PR06, PR08, PR09, PR10, RT01, RT04, RT05, SA02, SA03, SA04, SS01, SS02, SS03, SS04, SS05)' ; echo $MSG
+    $BASE_DIR/scripts/validate_docstrings.py --format=actions --errors=EX04,GL01,GL02,GL03,GL04,GL05,GL06,GL07,GL09,GL10,PR03,PR04,PR05,PR06,PR08,PR09,PR10,RT01,RT04,RT05,SA02,SA03,SA04,SS01,SS02,SS03,SS04,SS05
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
 fi

ci/deps/actions-310.yaml

@@ -9,7 +9,6 @@ dependencies:
   - pytest>=6.0
   - pytest-cov
   - pytest-xdist>=1.31
-  - hypothesis>=5.5.3
   - psutil
   - pytest-asyncio>=0.17
   - boto3
@@ -27,6 +26,7 @@ dependencies:
   - fastparquet
   - fsspec
   - html5lib
+  - hypothesis
   - gcsfs
   - jinja2
   - lxml

ci/deps/actions-38-downstream_compat.yaml

@@ -10,7 +10,6 @@ dependencies:
   - pytest>=6.0
   - pytest-cov
   - pytest-xdist>=1.31
-  - hypothesis>=5.5.3
   - psutil
   - pytest-asyncio>=0.17
   - boto3
@@ -28,6 +27,7 @@ dependencies:
   - fastparquet
   - fsspec
   - html5lib
+  - hypothesis
   - gcsfs
   - jinja2
   - lxml
@@ -60,7 +60,7 @@ dependencies:
   - cftime
   - dask
   - ipython
-  - geopandas
+  - geopandas-base
   - seaborn
   - scikit-learn
   - statsmodels

ci/deps/actions-38-minimum_versions.yaml

@@ -11,7 +11,6 @@ dependencies:
   - pytest>=6.0
   - pytest-cov
   - pytest-xdist>=1.31
-  - hypothesis>=5.5.3
   - psutil
   - pytest-asyncio>=0.17
   - boto3
@@ -29,6 +28,7 @@ dependencies:
   - fastparquet=0.4.0
   - fsspec=0.7.4
   - html5lib=1.1
+  - hypothesis=5.5.3
   - gcsfs=0.6.0
   - jinja2=2.11
   - lxml=4.5.0

ci/deps/actions-38.yaml

@@ -9,7 +9,6 @@ dependencies:
   - pytest>=6.0
   - pytest-cov
   - pytest-xdist>=1.31
-  - hypothesis>=5.5.3
   - psutil
   - pytest-asyncio>=0.17
   - boto3
@@ -27,6 +26,7 @@ dependencies:
   - fastparquet
   - fsspec
   - html5lib
+  - hypothesis
   - gcsfs
   - jinja2
   - lxml

ci/deps/actions-39.yaml

@@ -9,7 +9,6 @@ dependencies:
   - pytest>=6.0
   - pytest-cov
   - pytest-xdist>=1.31
-  - hypothesis>=5.5.3
   - psutil
   - pytest-asyncio>=0.17
   - boto3
@@ -27,6 +26,7 @@ dependencies:
   - fastparquet
   - fsspec
   - html5lib
+  - hypothesis
   - gcsfs
   - jinja2
   - lxml

ci/deps/circle-38-arm64.yaml

@@ -9,7 +9,6 @@ dependencies:
   - pytest>=6.0
   - pytest-cov
   - pytest-xdist>=1.31
-  - hypothesis>=5.5.3
   - psutil
   - pytest-asyncio>=0.17
   - boto3
@@ -27,6 +26,7 @@ dependencies:
   - fastparquet
   - fsspec
   - html5lib
+  - hypothesis
   - gcsfs
   - jinja2
   - lxml

doc/source/development/code_style.rst

@@ -37,15 +37,14 @@ In addition to ``./ci/code_checks.sh``, some extra checks are run by
 ``pre-commit`` - see :ref:`here <contributing.pre-commit>` for how to
 run them.
 
-Additional standards are outlined on the :ref:`pandas code style guide <code_style>`.
-
 .. _contributing.pre-commit:
 
 Pre-commit
 ----------
 
 Additionally, :ref:`Continuous Integration <contributing.ci>` will run code formatting checks
-like ``black``, ``flake8``, ``isort``, and ``cpplint`` and more using `pre-commit hooks <https://pre-commit.com/>`_
+like ``black``, ``flake8`` (including a `pandas-dev-flaker <https://github.com/pandas-dev/pandas-dev-flaker>`_ plugin),
+``isort``, and ``cpplint`` and more using `pre-commit hooks <https://pre-commit.com/>`_
 Any warnings from these checks will cause the :ref:`Continuous Integration <contributing.ci>` to fail; therefore,
 it is helpful to run the check yourself before submitting code. This
 can be done by installing ``pre-commit``::
@@ -223,7 +222,7 @@ In some cases you may be tempted to use ``cast`` from the typing module when you
            ...
        else:  # Reasonably only str objects would reach this but...
            obj = cast(str, obj)  # Mypy complains without this!
-	   return obj.upper()
+           return obj.upper()
 
 The limitation here is that while a human can reasonably understand that ``is_number`` would catch the ``int`` and ``float`` types mypy cannot make that same inference just yet (see `mypy #5206 <https://github.com/python/mypy/issues/5206>`_. While the above works, the use of ``cast`` is **strongly discouraged**. Where applicable a refactor of the code to appease static analysis is preferable
 

doc/source/development/contributing_codebase.rst

@@ -85,10 +85,10 @@ You will need `Build Tools for Visual Studio 2019
 <https://visualstudio.microsoft.com/downloads/>`_.
 
 .. warning::
-	You DO NOT need to install Visual Studio 2019.
-	You only need "Build Tools for Visual Studio 2019" found by
-	scrolling down to "All downloads" -> "Tools for Visual Studio 2019".
-	In the installer, select the "C++ build tools" workload.
+        You DO NOT need to install Visual Studio 2019.
+        You only need "Build Tools for Visual Studio 2019" found by
+        scrolling down to "All downloads" -> "Tools for Visual Studio 2019".
+        In the installer, select the "C++ build tools" workload.
 
 You can install the necessary components on the commandline using
 `vs_buildtools.exe <https://download.visualstudio.microsoft.com/download/pr/9a26f37e-6001-429b-a5db-c5455b93953c/460d80ab276046de2455a4115cc4e2f1e6529c9e6cb99501844ecafd16c619c4/vs_BuildTools.exe>`_:

doc/source/development/contributing_environment.rst

@@ -16,7 +16,6 @@ Development
     contributing_environment
     contributing_documentation
     contributing_codebase
-    code_style
     maintaining
     internals
     test_writing

doc/source/development/index.rst

@@ -540,15 +540,15 @@ Pandas-Genomics provides extension types, extension arrays, and extension access
 `Pint-Pandas`_
 ~~~~~~~~~~~~~~
 
-``Pint-Pandas <https://github.com/hgrecco/pint-pandas>`` provides an extension type for
+`Pint-Pandas <https://github.com/hgrecco/pint-pandas>`_ provides an extension type for
 storing numeric arrays with units. These arrays can be stored inside pandas'
 Series and DataFrame. Operations between Series and DataFrame columns which
 use pint's extension array are then units aware.
 
 `Text Extensions for Pandas`_
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-``Text Extensions for Pandas <https://ibm.biz/text-extensions-for-pandas>``
+`Text Extensions for Pandas <https://ibm.biz/text-extensions-for-pandas>`_
 provides extension types to cover common data structures for representing natural language
 data, plus library integrations that convert the outputs of popular natural language
 processing libraries into Pandas DataFrames.

doc/source/ecosystem.rst

@@ -132,9 +132,7 @@ The following methods are available only for ``SeriesGroupBy`` objects.
    SeriesGroupBy.hist
    SeriesGroupBy.nlargest
    SeriesGroupBy.nsmallest
-   SeriesGroupBy.nunique
    SeriesGroupBy.unique
-   SeriesGroupBy.value_counts
    SeriesGroupBy.is_monotonic_increasing
    SeriesGroupBy.is_monotonic_decreasing
 

doc/source/reference/groupby.rst

@@ -342,6 +342,7 @@ Datetime methods
    :toctree: api/
    :template: autosummary/accessor_method.rst
 
+   Series.dt.isocalendar
    Series.dt.to_period
    Series.dt.to_pydatetime
    Series.dt.tz_localize

doc/source/reference/series.rst

@@ -1082,14 +1082,14 @@ of :ref:`frequency aliases <timeseries.offset_aliases>` with datetime-like inter
 
    pd.interval_range(start=pd.Timedelta("0 days"), periods=3, freq="9H")
 
-Additionally, the ``closed`` parameter can be used to specify which side(s) the intervals
-are closed on.  Intervals are closed on the right side by default.
+Additionally, the ``inclusive`` parameter can be used to specify which side(s) the intervals
+are closed on.  Intervals are closed on the both side by default.
 
 .. ipython:: python
 
-   pd.interval_range(start=0, end=4, closed="both")
+   pd.interval_range(start=0, end=4, inclusive="both")
 
-   pd.interval_range(start=0, end=4, closed="neither")
+   pd.interval_range(start=0, end=4, inclusive="neither")
 
 Specifying ``start``, ``end``, and ``periods`` will generate a range of evenly spaced
 intervals from ``start`` to ``end`` inclusively, with ``periods`` number of elements

doc/source/user_guide/advanced.rst

@@ -423,7 +423,7 @@ Fill forward a reversed timeseries
    )
    df.loc[df.index[3], "A"] = np.nan
    df
-   df.reindex(df.index[::-1]).ffill()
+   df.bfill()
 
 `cumsum reset at NaN values
 <https://stackoverflow.com/questions/18196811/cumsum-reset-at-nan>`__

doc/source/user_guide/cookbook.rst

@@ -678,7 +678,7 @@ Boolean operators operate element-wise as well:
 Transposing
 ~~~~~~~~~~~
 
-To transpose, access the ``T`` attribute or :meth:`DataFrame.transpose``,
+To transpose, access the ``T`` attribute or :meth:`DataFrame.transpose`,
 similar to an ndarray:
 
 .. ipython:: python