Merge remote-tracking branch 'upstream/main' into fix-doc-data-struct…

…ures
pandas-dev · Sep 30, 2024 · f332995 · f332995
2 parents 01a85b7 + 90c26ce
commit f332995
Show file tree

Hide file tree

Showing 85 changed files with 1,097 additions and 581 deletions.
diff --git a/.github/actions/setup-conda/action.yml b/.github/actions/setup-conda/action.yml
@@ -9,6 +9,8 @@ runs:
     - name: Install ${{ inputs.environment-file }}
       uses: mamba-org/setup-micromamba@v1
       with:
+        # Pinning to avoid 2.0 failures
+        micromamba-version: '1.5.10-0'
         environment-file: ${{ inputs.environment-file }}
         environment-name: test
         condarc-file: ci/.condarc

diff --git a/ci/code_checks.sh b/ci/code_checks.sh
@@ -73,7 +73,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Period.freq GL08" \
         -i "pandas.Period.ordinal GL08" \
         -i "pandas.RangeIndex.from_range PR01,SA01" \
-        -i "pandas.RangeIndex.step SA01" \
         -i "pandas.Series.cat.add_categories PR01,PR02" \
         -i "pandas.Series.cat.as_ordered PR01" \
         -i "pandas.Series.cat.as_unordered PR01" \
@@ -97,50 +96,32 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Series.dt.tz_localize PR01,PR02" \
         -i "pandas.Series.dt.unit GL08" \
         -i "pandas.Series.pad PR01,SA01" \
-        -i "pandas.Series.sparse.fill_value SA01" \
         -i "pandas.Series.sparse.from_coo PR07,SA01" \
-        -i "pandas.Series.sparse.npoints SA01" \
-        -i "pandas.Series.sparse.sp_values SA01" \
         -i "pandas.Timedelta.max PR02" \
         -i "pandas.Timedelta.min PR02" \
         -i "pandas.Timedelta.resolution PR02" \
-        -i "pandas.Timedelta.to_timedelta64 SA01" \
         -i "pandas.TimedeltaIndex.to_pytimedelta RT03,SA01" \
         -i "pandas.Timestamp.max PR02" \
         -i "pandas.Timestamp.min PR02" \
         -i "pandas.Timestamp.nanosecond GL08" \
         -i "pandas.Timestamp.resolution PR02" \
         -i "pandas.Timestamp.tzinfo GL08" \
         -i "pandas.Timestamp.year GL08" \
-        -i "pandas.api.types.is_dict_like PR07,SA01" \
-        -i "pandas.api.types.is_file_like PR07,SA01" \
         -i "pandas.api.types.is_float PR01,SA01" \
-        -i "pandas.api.types.is_float_dtype SA01" \
-        -i "pandas.api.types.is_hashable PR01,RT03,SA01" \
-        -i "pandas.api.types.is_int64_dtype SA01" \
         -i "pandas.api.types.is_integer PR01,SA01" \
-        -i "pandas.api.types.is_interval_dtype SA01" \
         -i "pandas.api.types.is_iterator PR07,SA01" \
-        -i "pandas.api.types.is_list_like SA01" \
-        -i "pandas.api.types.is_named_tuple PR07,SA01" \
-        -i "pandas.api.types.is_object_dtype SA01" \
-        -i "pandas.api.types.is_re PR07,SA01" \
         -i "pandas.api.types.is_re_compilable PR07,SA01" \
         -i "pandas.api.types.pandas_dtype PR07,RT03,SA01" \
         -i "pandas.arrays.ArrowExtensionArray PR07,SA01" \
-        -i "pandas.arrays.BooleanArray SA01" \
         -i "pandas.arrays.DatetimeArray SA01" \
         -i "pandas.arrays.IntegerArray SA01" \
         -i "pandas.arrays.IntervalArray.left SA01" \
         -i "pandas.arrays.IntervalArray.length SA01" \
-        -i "pandas.arrays.IntervalArray.mid SA01" \
         -i "pandas.arrays.IntervalArray.right SA01" \
         -i "pandas.arrays.NumpyExtensionArray SA01" \
         -i "pandas.arrays.SparseArray PR07,SA01" \
         -i "pandas.arrays.TimedeltaArray PR07,SA01" \
         -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.boxplot PR07,RT03,SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.get_group RT03,SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.groups SA01" \
@@ -151,8 +132,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.core.groupby.DataFrameGroupBy.plot PR02" \
         -i "pandas.core.groupby.DataFrameGroupBy.sem SA01" \
         -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.get_group RT03,SA01" \
         -i "pandas.core.groupby.SeriesGroupBy.groups SA01" \
         -i "pandas.core.groupby.SeriesGroupBy.indices SA01" \
@@ -163,7 +142,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.core.groupby.SeriesGroupBy.plot PR02" \
         -i "pandas.core.groupby.SeriesGroupBy.sem SA01" \
         -i "pandas.core.resample.Resampler.__iter__ RT03,SA01" \
-        -i "pandas.core.resample.Resampler.ffill RT03" \
         -i "pandas.core.resample.Resampler.get_group RT03,SA01" \
         -i "pandas.core.resample.Resampler.groups SA01" \
         -i "pandas.core.resample.Resampler.indices SA01" \
@@ -178,15 +156,13 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.core.resample.Resampler.sum SA01" \
         -i "pandas.core.resample.Resampler.transform PR01,RT03,SA01" \
         -i "pandas.core.resample.Resampler.var SA01" \
-        -i "pandas.date_range RT03" \
         -i "pandas.errors.AttributeConflictWarning SA01" \
         -i "pandas.errors.CSSWarning SA01" \
         -i "pandas.errors.CategoricalConversionWarning SA01" \
         -i "pandas.errors.ChainedAssignmentError SA01" \
         -i "pandas.errors.ClosedFileError SA01" \
         -i "pandas.errors.DataError SA01" \
         -i "pandas.errors.DuplicateLabelError SA01" \
-        -i "pandas.errors.EmptyDataError SA01" \
         -i "pandas.errors.IntCastingNaNError SA01" \
         -i "pandas.errors.InvalidIndexError SA01" \
         -i "pandas.errors.InvalidVersion SA01" \
@@ -368,7 +344,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.tseries.offsets.SemiMonthBegin.n GL08" \
         -i "pandas.tseries.offsets.SemiMonthBegin.normalize GL08" \
         -i "pandas.tseries.offsets.SemiMonthBegin.rule_code GL08" \
-        -i "pandas.tseries.offsets.SemiMonthEnd SA01" \
         -i "pandas.tseries.offsets.SemiMonthEnd.day_of_month GL08" \
         -i "pandas.tseries.offsets.SemiMonthEnd.is_on_offset GL08" \
         -i "pandas.tseries.offsets.SemiMonthEnd.n GL08" \

diff --git a/doc/source/development/contributing.rst b/doc/source/development/contributing.rst
@@ -305,15 +305,15 @@ It is important to periodically update your local ``main`` branch with updates f
 branch and update your development environment to reflect any changes to the various packages that
 are used during development.
 
-If using :ref:`mamba <contributing.mamba>`, run:
+If using :ref:`conda <contributing.conda>`, run:
 
 .. code-block:: shell
 
     git checkout main
     git fetch upstream
     git merge upstream/main
-    mamba activate pandas-dev
-    mamba env update -f environment.yml --prune
+    conda activate pandas-dev
+    conda env update -f environment.yml --prune
 
 If using :ref:`pip <contributing.pip>` , do:
 

diff --git a/doc/source/development/contributing_codebase.rst b/doc/source/development/contributing_codebase.rst
@@ -244,7 +244,7 @@ in your python environment.
 
 .. warning::
 
-    * Please be aware that the above commands will use the current python environment. If your python packages are older/newer than those installed by the pandas CI, the above commands might fail. This is often the case when the ``mypy`` or ``numpy`` versions do not match. Please see :ref:`how to setup the python environment <contributing.mamba>` or select a `recently succeeded workflow <https://github.com/pandas-dev/pandas/actions/workflows/code-checks.yml?query=branch%3Amain+is%3Asuccess>`_, select the "Docstring validation, typing, and other manual pre-commit hooks" job, then click on "Set up Conda" and "Environment info" to see which versions the pandas CI installs.
+    * Please be aware that the above commands will use the current python environment. If your python packages are older/newer than those installed by the pandas CI, the above commands might fail. This is often the case when the ``mypy`` or ``numpy`` versions do not match. Please see :ref:`how to setup the python environment <contributing.conda>` or select a `recently succeeded workflow <https://github.com/pandas-dev/pandas/actions/workflows/code-checks.yml?query=branch%3Amain+is%3Asuccess>`_, select the "Docstring validation, typing, and other manual pre-commit hooks" job, then click on "Set up Conda" and "Environment info" to see which versions the pandas CI installs.
 
 .. _contributing.ci:
 

diff --git a/doc/source/development/contributing_environment.rst b/doc/source/development/contributing_environment.rst
@@ -43,17 +43,17 @@ and consult the ``Linux`` instructions below.
 
 **macOS**
 
-To use the :ref:`mamba <contributing.mamba>`-based compilers, you will need to install the
+To use the :ref:`conda <contributing.conda>`-based compilers, you will need to install the
 Developer Tools using ``xcode-select --install``.
 
 If you prefer to use a different compiler, general information can be found here:
 https://devguide.python.org/setup/#macos
 
 **Linux**
 
-For Linux-based :ref:`mamba <contributing.mamba>` installations, you won't have to install any
-additional components outside of the mamba environment. The instructions
-below are only needed if your setup isn't based on mamba environments.
+For Linux-based :ref:`conda <contributing.conda>` installations, you won't have to install any
+additional components outside of the conda environment. The instructions
+below are only needed if your setup isn't based on conda environments.
 
 Some Linux distributions will come with a pre-installed C compiler. To find out
 which compilers (and versions) are installed on your system::
@@ -82,19 +82,18 @@ Before we begin, please:
 * Make sure that you have :any:`cloned the repository <contributing.forking>`
 * ``cd`` to the pandas source directory you just created with the clone command
 
-.. _contributing.mamba:
+.. _contributing.conda:
 
-Option 1: using mamba (recommended)
+Option 1: using conda (recommended)
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-* Install miniforge to get `mamba <https://mamba.readthedocs.io/en/latest/installation/mamba-installation.html>`_
-* Make sure your mamba is up to date (``mamba update mamba``)
-* Create and activate the ``pandas-dev`` mamba environment using the following commands:
+* Install miniforge to get `conda <https://github.com/conda-forge/miniforge?tab=readme-ov-file#download>`_
+* Create and activate the ``pandas-dev`` conda environment using the following commands:
 
-.. code-block:: none
+.. code-block:: bash
 
-   mamba env create --file environment.yml
-   mamba activate pandas-dev
+   conda env create --file environment.yml
+   conda activate pandas-dev
 
 .. _contributing.pip:
 

diff --git a/doc/source/development/maintaining.rst b/doc/source/development/maintaining.rst
@@ -344,7 +344,7 @@ in the next places:
 - Git repo with a `new tag <https://github.com/pandas-dev/pandas/tags>`_
 - Source distribution in a `GitHub release <https://github.com/pandas-dev/pandas/releases>`_
 - Pip packages in the `PyPI <https://pypi.org/project/pandas/>`_
-- Conda/Mamba packages in `conda-forge <https://anaconda.org/conda-forge/pandas>`_
+- Conda packages in `conda-forge <https://anaconda.org/conda-forge/pandas>`_
 
 The process for releasing a new version of pandas is detailed next section.
 

diff --git a/doc/source/getting_started/index.rst b/doc/source/getting_started/index.rst
@@ -17,8 +17,7 @@ Installation
         :columns: 12 12 6 6
         :padding: 3
 
-        pandas is part of the `Anaconda <https://docs.continuum.io/anaconda/>`__
-        distribution and can be installed with Anaconda or Miniconda:
+        pandas can be installed via conda from `conda-forge <https://anaconda.org/conda-forge/pandas>`__.
 
         ++++++++++++++++++++++