Merge remote-tracking branch 'upstream/main' into sty/ruff

pandas-dev · Jan 31, 2024 · 65ac7cc · 65ac7cc
2 parents b40d961 + cad0d87
commit 65ac7cc
Show file tree

Hide file tree

Showing 47 changed files with 310 additions and 1,109 deletions.
diff --git a/.github/workflows/comment-commands.yml b/.github/workflows/comment-commands.yml
@@ -24,12 +24,10 @@ jobs:
     concurrency:
       group: ${{ github.actor }}-preview-docs
     steps:
-      - run: |
-          if curl --output /dev/null --silent --head --fail "https://pandas.pydata.org/preview/${{ github.event.issue.number }}/"; then
-            curl -H "Authorization: token ${{ secrets.GITHUB_TOKEN }}" -d '{"body": "Website preview of this PR available at: https://pandas.pydata.org/preview/${{ github.event.issue.number }}/"}' https://api.github.com/repos/${{ github.repository }}/issues/${{ github.event.issue.number }}/comments
-          else
-            curl -H "Authorization: token ${{ secrets.GITHUB_TOKEN }}" -d '{"body": "No preview found for PR #${{ github.event.issue.number }}. Did the docs build complete?"}' https://api.github.com/repos/${{ github.repository }}/issues/${{ github.event.issue.number }}/comments
-          fi
+      - uses: pandas-dev/github-doc-previewer@master
+        with:
+          previewer-server: "https://pandas.pydata.org/preview"
+          artifact-job: "Doc Build and Upload"
   asv_run:
     runs-on: ubuntu-22.04
     # TODO: Support more benchmarking options later, against different branches, against self, etc

diff --git a/.github/workflows/docbuild-and-upload.yml b/.github/workflows/docbuild-and-upload.yml
@@ -90,10 +90,3 @@ jobs:
         name: website
         path: web/build
         retention-days: 14
-
-    - name: Trigger web/doc preview
-      run: curl -X POST https://pandas.pydata.org/preview/submit/$RUN_ID/$PR_ID/
-      env:
-        RUN_ID: ${{ github.run_id }}
-        PR_ID: ${{ github.event.pull_request.number }}
-      if: github.event_name == 'pull_request'
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -100,8 +100,6 @@ repos:
 -   repo: https://github.com/pre-commit/pygrep-hooks
     rev: v1.10.0
     hooks:
-      - id: python-check-blanket-noqa
-      - id: python-check-blanket-type-ignore
       - id: rst-backticks
       - id: rst-directive-colons
         types: [text]  # overwrite types: [rst]

diff --git a/asv_bench/asv.conf.json b/asv_bench/asv.conf.json
@@ -41,7 +41,7 @@
     // pip (with all the conda available packages installed first,
     // followed by the pip installed packages).
     "matrix": {
-        "Cython": ["3.0.5"],
+        "Cython": ["3.0"],
         "matplotlib": [],
         "sqlalchemy": [],
         "scipy": [],

diff --git a/ci/code_checks.sh b/ci/code_checks.sh
@@ -93,7 +93,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         pandas.TimedeltaIndex.ceil\
         pandas.PeriodIndex\
         pandas.PeriodIndex.strftime\
-        pandas.Series.clip\
         pandas.Series.rename_axis\
         pandas.Series.dt.to_period\
         pandas.Series.dt.tz_localize\
@@ -115,7 +114,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         pandas.Series.plot.barh\
         pandas.Series.plot.line\
         pandas.Series.plot.pie\
-        pandas.DataFrame.clip\
         pandas.DataFrame.plot\
         pandas.DataFrame.plot.bar\
         pandas.DataFrame.plot.barh\
@@ -181,10 +179,10 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         pandas.core.groupby.SeriesGroupBy.rolling\
         pandas.core.groupby.DataFrameGroupBy.hist\
         pandas.core.groupby.DataFrameGroupBy.plot\
+        pandas.core.groupby.DataFrameGroupBy.corrwith\
         pandas.core.groupby.SeriesGroupBy.plot\
         pandas.core.window.rolling.Rolling.quantile\
-        pandas.core.window.expanding.Expanding.quantile\
-        pandas.api.extensions.ExtensionArray.argsort # There should be no backslash in the final line, please keep this comment in the last ignored function
+        pandas.core.window.expanding.Expanding.quantile # There should be no backslash in the final line, please keep this comment in the last ignored function
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
 fi

diff --git a/doc/source/reference/arrays.rst b/doc/source/reference/arrays.rst
@@ -539,6 +539,21 @@ To create a Series of dtype ``category``, use ``cat = s.astype(dtype)`` or
 If the :class:`Series` is of dtype :class:`CategoricalDtype`, ``Series.cat`` can be used to change the categorical
 data. See :ref:`api.series.cat` for more.
 
+More methods are available on :class:`Categorical`:
+
+.. autosummary::
+   :toctree: api/
+
+   Categorical.as_ordered
+   Categorical.as_unordered
+   Categorical.set_categories
+   Categorical.rename_categories
+   Categorical.reorder_categories
+   Categorical.add_categories
+   Categorical.remove_categories
+   Categorical.remove_unused_categories
+   Categorical.map
+
 .. _api.arrays.sparse:
 
 Sparse

diff --git a/doc/source/reference/groupby.rst b/doc/source/reference/groupby.rst
@@ -80,7 +80,6 @@ Function application
    DataFrameGroupBy.describe
    DataFrameGroupBy.diff
    DataFrameGroupBy.ffill
-   DataFrameGroupBy.fillna
    DataFrameGroupBy.first
    DataFrameGroupBy.head
    DataFrameGroupBy.idxmax
@@ -131,7 +130,6 @@ Function application
    SeriesGroupBy.describe
    SeriesGroupBy.diff
    SeriesGroupBy.ffill
-   SeriesGroupBy.fillna
    SeriesGroupBy.first
    SeriesGroupBy.head
    SeriesGroupBy.last

diff --git a/doc/source/reference/index.rst b/doc/source/reference/index.rst
@@ -24,13 +24,14 @@ The following subpackages are public.
   `pandas-stubs <https://github.com/pandas-dev/pandas-stubs>`_ package
   which has classes in addition to those that occur in pandas for type-hinting.
 
-In addition, public functions in ``pandas.io`` and ``pandas.tseries`` submodules
-are mentioned in the documentation.
+In addition, public functions in ``pandas.io``, ``pandas.tseries``, ``pandas.util`` submodules
+are explicitly mentioned in the documentation. Further APIs in these modules are not guaranteed
+to be stable.
 
 
 .. warning::
 
-    The ``pandas.core``, ``pandas.compat``, and ``pandas.util`` top-level modules are PRIVATE. Stable functionality in such modules is not guaranteed.
+    The ``pandas.core``, ``pandas.compat`` top-level modules are PRIVATE. Stable functionality in such modules is not guaranteed.
 
 .. If you update this toctree, also update the manual toctree in the
 .. main index.rst.template

diff --git a/doc/source/user_guide/groupby.rst b/doc/source/user_guide/groupby.rst
@@ -289,7 +289,7 @@ the number of groups, which is the same as the length of the ``groups`` dictiona
    In [1]: gb.<TAB>  # noqa: E225, E999
    gb.agg        gb.boxplot    gb.cummin     gb.describe   gb.filter     gb.get_group  gb.height     gb.last       gb.median     gb.ngroups    gb.plot       gb.rank       gb.std        gb.transform
    gb.aggregate  gb.count      gb.cumprod    gb.dtype      gb.first      gb.groups     gb.hist       gb.max        gb.min        gb.nth        gb.prod       gb.resample   gb.sum        gb.var
-   gb.apply      gb.cummax     gb.cumsum     gb.fillna     gb.gender     gb.head       gb.indices    gb.mean       gb.name       gb.ohlc       gb.quantile   gb.size       gb.tail       gb.weight
+   gb.apply      gb.cummax     gb.cumsum     gb.gender     gb.head       gb.indices    gb.mean       gb.name       gb.ohlc       gb.quantile   gb.size       gb.tail       gb.weight
 
 .. _groupby.multiindex:
 

diff --git a/doc/source/whatsnew/v2.0.0.rst b/doc/source/whatsnew/v2.0.0.rst
@@ -732,7 +732,7 @@ or, if your formats are all ISO8601 (but possibly not identically-formatted) ::
 
 Other API changes
 ^^^^^^^^^^^^^^^^^
-- The ``freq``, ``tz``, ``nanosecond``, and ``unit`` keywords in the :class:`Timestamp` constructor are now keyword-only (:issue:`45307`, :issue:`32526`)
+- The ``tz``, ``nanosecond``, and ``unit`` keywords in the :class:`Timestamp` constructor are now keyword-only (:issue:`45307`, :issue:`32526`)
 - Passing ``nanoseconds`` greater than 999 or less than 0 in :class:`Timestamp` now raises a ``ValueError`` (:issue:`48538`, :issue:`48255`)
 - :func:`read_csv`: specifying an incorrect number of columns with ``index_col`` of now raises ``ParserError`` instead of ``IndexError`` when using the c parser.
 - Default value of ``dtype`` in :func:`get_dummies` is changed to ``bool`` from ``uint8`` (:issue:`45848`)

diff --git a/doc/source/whatsnew/v2.2.1.rst b/doc/source/whatsnew/v2.2.1.rst
@@ -18,6 +18,8 @@ Fixed regressions
 - Fixed regression in :func:`merge_ordered` raising ``TypeError`` for ``fill_method="ffill"`` and ``how="left"`` (:issue:`57010`)
 - Fixed regression in :func:`wide_to_long` raising an ``AttributeError`` for string columns (:issue:`57066`)
 - Fixed regression in :meth:`DataFrame.loc` raising ``IndexError`` for non-unique, masked dtype indexes where result has more than 10,000 rows (:issue:`57027`)
+- Fixed regression in :meth:`DataFrame.sort_index` not producing a stable sort for a index with duplicates (:issue:`57151`)
+- Fixed regression in :meth:`DataFrame.to_dict` with ``orient='list'`` and datetime or timedelta types returning integers (:issue:`54824`)
 - Fixed regression in :meth:`DataFrameGroupBy.idxmin`, :meth:`DataFrameGroupBy.idxmax`, :meth:`SeriesGroupBy.idxmin`, :meth:`SeriesGroupBy.idxmax` ignoring the ``skipna`` argument (:issue:`57040`)
 - Fixed regression in :meth:`DataFrameGroupBy.idxmin`, :meth:`DataFrameGroupBy.idxmax`, :meth:`SeriesGroupBy.idxmin`, :meth:`SeriesGroupBy.idxmax` where values containing the minimum or maximum value for the dtype could produce incorrect results (:issue:`57040`)
 - Fixed regression in :meth:`Index.join` raising ``TypeError`` when joining an empty index to a non-empty index containing mixed dtype values (:issue:`57048`)
@@ -28,6 +30,7 @@ Fixed regressions
 
 Bug fixes
 ~~~~~~~~~
+- Fixed bug in :func:`pandas.api.interchange.from_dataframe` which was raising for empty inputs (:issue:`56700`)
 - Fixed bug in :meth:`DataFrame.__getitem__` for empty :class:`DataFrame` with Copy-on-Write enabled (:issue:`57130`)
 
 .. ---------------------------------------------------------------------------

diff --git a/doc/source/whatsnew/v3.0.0.rst b/doc/source/whatsnew/v3.0.0.rst
@@ -96,6 +96,15 @@ Deprecations
 - Deprecated :meth:`Timestamp.utcnow`, use ``Timestamp.now("UTC")`` instead (:issue:`56680`)
 -
 
+.. ---------------------------------------------------------------------------
+.. _whatsnew_300.prior_deprecations:
+
+Removal of prior version deprecations/changes
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+- Removed :meth:`DataFrameGroupby.fillna` and :meth:`SeriesGroupBy.fillna` (:issue:`55719`)
+- Removed ``axis`` argument from all groupby operations (:issue:`50405`)
+- Removed deprecated argument ``obj`` in :meth:`.DataFrameGroupBy.get_group` and :meth:`.SeriesGroupBy.get_group` (:issue:`53545`)
+
 .. ---------------------------------------------------------------------------
 .. _whatsnew_300.performance:
 

diff --git a/environment.yml b/environment.yml
@@ -8,7 +8,7 @@ dependencies:
 
   # build dependencies
   - versioneer[toml]
-  - cython=3.0.5
+  - cython~=3.0.5
   - meson[ninja]=1.2.1
   - meson-python=0.13.1
 

diff --git a/pandas/core/arrays/base.py b/pandas/core/arrays/base.py
@@ -819,7 +819,7 @@ def argsort(
         na_position : {'first', 'last'}, default 'last'
             If ``'first'``, put ``NaN`` values at the beginning.
             If ``'last'``, put ``NaN`` values at the end.
-        *args, **kwargs:
+        **kwargs
             Passed through to :func:`numpy.argsort`.
 
         Returns

diff --git a/pandas/core/arrays/categorical.py b/pandas/core/arrays/categorical.py
@@ -293,6 +293,15 @@ class Categorical(NDArrayBackedExtensionArray, PandasObject, ObjectStringArrayMi
     Methods
     -------
     from_codes
+    as_ordered
+    as_unordered
+    set_categories
+    rename_categories
+    reorder_categories
+    add_categories
+    remove_categories
+    remove_unused_categories
+    map
     __array__
 
     Raises

diff --git a/pandas/core/frame.py b/pandas/core/frame.py
@@ -60,6 +60,8 @@
 from pandas.errors import (
     ChainedAssignmentError,
     InvalidIndexError,
+)
+from pandas.errors.cow import (
     _chained_assignment_method_msg,
     _chained_assignment_msg,
     _chained_assignment_warning_method_msg,
@@ -89,7 +91,6 @@
     find_common_type,
     infer_dtype_from_scalar,
     invalidate_string_dtypes,
-    maybe_box_native,
     maybe_downcast_to_dtype,
 )
 from pandas.core.dtypes.common import (
@@ -1987,28 +1988,6 @@ def to_numpy(
 
         return result
 
-    def _create_data_for_split_and_tight_to_dict(
-        self, are_all_object_dtype_cols: bool, object_dtype_indices: list[int]
-    ) -> list:
-        """
-        Simple helper method to create data for to ``to_dict(orient="split")`` and
-        ``to_dict(orient="tight")`` to create the main output data
-        """
-        if are_all_object_dtype_cols:
-            data = [
-                list(map(maybe_box_native, t))
-                for t in self.itertuples(index=False, name=None)
-            ]
-        else:
-            data = [list(t) for t in self.itertuples(index=False, name=None)]
-            if object_dtype_indices:
-                # If we have object_dtype_cols, apply maybe_box_naive after list
-                # comprehension for perf
-                for row in data:
-                    for i in object_dtype_indices:
-                        row[i] = maybe_box_native(row[i])
-        return data
-
     @overload
     def to_dict(
         self,

diff --git a/pandas/core/generic.py b/pandas/core/generic.py
@@ -101,6 +101,8 @@
     InvalidIndexError,
     SettingWithCopyError,
     SettingWithCopyWarning,
+)
+from pandas.errors.cow import (
     _chained_assignment_method_msg,
     _chained_assignment_warning_method_msg,
     _check_cacher,
@@ -9055,7 +9057,7 @@ def clip(
             For `Series` this parameter is unused and defaults to `None`.
         inplace : bool, default False
             Whether to perform the operation in place on the data.
-        *args, **kwargs
+        **kwargs
             Additional keywords have no effect but might be accepted
             for compatibility with numpy.
 

diff --git a/pandas/core/groupby/base.py b/pandas/core/groupby/base.py
@@ -70,7 +70,6 @@ class OutputKey:
         "cumsum",
         "diff",
         "ffill",
-        "fillna",
         "ngroup",
         "pct_change",
         "rank",