Merge remote-tracking branch 'upstream/main' into string-dtype-predicates-nan-propagation

Author: jorisvandenbossche

asv_bench/benchmarks/indexing_engines.py

@@ -87,7 +87,7 @@ def setup(self, engine_and_dtype, index_type, unique, N):
                 arr = np.array([1, 2, 3], dtype=dtype).repeat(N)
 
         self.data = engine(arr)
-        # code belows avoids populating the mapping etc. while timing.
+        # code below avoids populating the mapping etc. while timing.
         self.data.get_loc(2)
 
         self.key_middle = arr[len(arr) // 2]
@@ -140,7 +140,7 @@ def setup(self, engine_and_dtype, index_type, unique, N):
             mask[-1] = True
 
         self.data = engine(BaseMaskedArray(arr, mask))
-        # code belows avoids populating the mapping etc. while timing.
+        # code below avoids populating the mapping etc. while timing.
         self.data.get_loc(2)
 
         self.key_middle = arr[len(arr) // 2]
@@ -169,7 +169,7 @@ def setup(self, index_type):
         }[index_type]
 
         self.data = libindex.ObjectEngine(arr)
-        # code belows avoids populating the mapping etc. while timing.
+        # code below avoids populating the mapping etc. while timing.
         self.data.get_loc("b")
 
     def time_get_loc(self, index_type):

ci/code_checks.sh

@@ -70,39 +70,11 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         --format=actions \
         -i ES01 `# For now it is ok if docstrings are missing the extended summary` \
         -i "pandas.Series.dt PR01" `# Accessors are implemented as classes, but we do not document the Parameters section` \
-        -i "pandas.MultiIndex.reorder_levels RT03,SA01" \
-        -i "pandas.MultiIndex.to_frame RT03" \
         -i "pandas.NA SA01" \
-        -i "pandas.NaT SA01" \
         -i "pandas.Period.freq GL08" \
-        -i "pandas.Period.freqstr SA01" \
         -i "pandas.Period.ordinal GL08" \
-        -i "pandas.Period.strftime PR01,SA01" \
         -i "pandas.Period.to_timestamp SA01" \
-        -i "pandas.PeriodDtype SA01" \
         -i "pandas.PeriodDtype.freq SA01" \
-        -i "pandas.PeriodIndex.day SA01" \
-        -i "pandas.PeriodIndex.day_of_week SA01" \
-        -i "pandas.PeriodIndex.day_of_year SA01" \
-        -i "pandas.PeriodIndex.dayofweek SA01" \
-        -i "pandas.PeriodIndex.dayofyear SA01" \
-        -i "pandas.PeriodIndex.days_in_month SA01" \
-        -i "pandas.PeriodIndex.daysinmonth SA01" \
-        -i "pandas.PeriodIndex.from_fields PR07,SA01" \
-        -i "pandas.PeriodIndex.from_ordinals SA01" \
-        -i "pandas.PeriodIndex.hour SA01" \
-        -i "pandas.PeriodIndex.is_leap_year SA01" \
-        -i "pandas.PeriodIndex.minute SA01" \
-        -i "pandas.PeriodIndex.month SA01" \
-        -i "pandas.PeriodIndex.quarter SA01" \
-        -i "pandas.PeriodIndex.qyear GL08" \
-        -i "pandas.PeriodIndex.second SA01" \
-        -i "pandas.PeriodIndex.to_timestamp RT03,SA01" \
-        -i "pandas.PeriodIndex.week SA01" \
-        -i "pandas.PeriodIndex.weekday SA01" \
-        -i "pandas.PeriodIndex.weekofyear SA01" \
-        -i "pandas.PeriodIndex.year SA01" \
-        -i "pandas.RangeIndex PR07" \
         -i "pandas.RangeIndex.from_range PR01,SA01" \
         -i "pandas.RangeIndex.start SA01" \
         -i "pandas.RangeIndex.step SA01" \
@@ -124,7 +96,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Series.dt.month_name PR01,PR02" \
         -i "pandas.Series.dt.nanoseconds SA01" \
         -i "pandas.Series.dt.normalize PR01" \
-        -i "pandas.Series.dt.qyear GL08" \
         -i "pandas.Series.dt.round PR01,PR02" \
         -i "pandas.Series.dt.seconds SA01" \
         -i "pandas.Series.dt.strftime PR01,PR02" \
@@ -134,14 +105,10 @@ 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.sem PR01,RT03,SA01" \
-        -i "pandas.Series.sparse 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.Series.sparse.to_coo PR07,RT03,SA01" \
-        -i "pandas.Series.std PR01,RT03,SA01" \
         -i "pandas.Timedelta.asm8 SA01" \
         -i "pandas.Timedelta.ceil SA01" \
         -i "pandas.Timedelta.components SA01" \
@@ -154,22 +121,15 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Timedelta.to_timedelta64 SA01" \
         -i "pandas.Timedelta.total_seconds SA01" \
         -i "pandas.Timedelta.view SA01" \
-        -i "pandas.TimedeltaIndex.as_unit RT03,SA01" \
         -i "pandas.TimedeltaIndex.components SA01" \
         -i "pandas.TimedeltaIndex.microseconds SA01" \
         -i "pandas.TimedeltaIndex.nanoseconds SA01" \
         -i "pandas.TimedeltaIndex.seconds SA01" \
         -i "pandas.TimedeltaIndex.to_pytimedelta RT03,SA01" \
-        -i "pandas.Timestamp.fold GL08" \
-        -i "pandas.Timestamp.hour GL08" \
         -i "pandas.Timestamp.max PR02" \
-        -i "pandas.Timestamp.microsecond GL08" \
         -i "pandas.Timestamp.min PR02" \
-        -i "pandas.Timestamp.minute GL08" \
-        -i "pandas.Timestamp.month GL08" \
         -i "pandas.Timestamp.nanosecond GL08" \
         -i "pandas.Timestamp.resolution PR02" \
-        -i "pandas.Timestamp.second GL08" \
         -i "pandas.Timestamp.tzinfo GL08" \
         -i "pandas.Timestamp.value GL08" \
         -i "pandas.Timestamp.year GL08" \
@@ -260,13 +220,7 @@ 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.core.window.expanding.Expanding.corr PR01" \
-        -i "pandas.core.window.expanding.Expanding.count PR01" \
-        -i "pandas.core.window.rolling.Rolling.max PR01" \
-        -i "pandas.core.window.rolling.Window.std PR01" \
-        -i "pandas.core.window.rolling.Window.var PR01" \
         -i "pandas.date_range RT03" \
-        -i "pandas.errors.AbstractMethodError PR01,SA01" \
         -i "pandas.errors.AttributeConflictWarning SA01" \
         -i "pandas.errors.CSSWarning SA01" \
         -i "pandas.errors.CategoricalConversionWarning SA01" \

doc/source/development/contributing_codebase.rst

@@ -605,7 +605,7 @@ The ``temp_file`` pytest fixture creates a temporary file :py:class:`Pathlib` ob
         pd.DataFrame([1]).to_csv(str(temp_file))
 
 Please reference `pytest's documentation <https://docs.pytest.org/en/latest/how-to/tmp_path.html#the-default-base-temporary-directory>`_
-for the file retension policy.
+for the file retention policy.
 
 Testing involving network connectivity
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

doc/source/development/debugging_extensions.rst

@@ -30,7 +30,7 @@ By specifying ``builddir="debug"`` all of the targets will be built and placed i
 Using Docker
 ------------
 
-To simplify the debugging process, pandas has created a Docker image with a debug build of Python and the gdb/Cython debuggers pre-installed. You may either ``docker pull pandas/pandas-debug`` to get access to this image or build it from the ``tooling/debug`` folder locallly.
+To simplify the debugging process, pandas has created a Docker image with a debug build of Python and the gdb/Cython debuggers pre-installed. You may either ``docker pull pandas/pandas-debug`` to get access to this image or build it from the ``tooling/debug`` folder locally.
 
 You can then mount your pandas repository into this image via:
 

doc/source/getting_started/index.rst

@@ -613,7 +613,7 @@ the pandas-equivalent operations compared to software you already know:
 
         Users of `Excel <https://en.wikipedia.org/wiki/Microsoft_Excel>`__
         or other spreadsheet programs will find that many of the concepts are
-        transferrable to pandas.
+        transferable to pandas.
 
         +++
 

doc/source/user_guide/cookbook.rst

@@ -914,7 +914,7 @@ Using TimeGrouper and another grouping to create subgroups, then apply a custom
 <https://stackoverflow.com/questions/15408156/resampling-with-custom-periods>`__
 
 `Resample intraday frame without adding new days
-<https://stackoverflow.com/questions/14898574/resample-intrday-pandas-dataframe-without-add-new-days>`__
+<https://stackoverflow.com/questions/14898574/resample-intraday-pandas-dataframe-without-add-new-days>`__
 
 `Resample minute data
 <https://stackoverflow.com/questions/14861023/resampling-minute-data>`__

doc/source/user_guide/io.rst

@@ -169,7 +169,7 @@ dtype_backend : {"numpy_nullable", "pyarrow"}, defaults to NumPy backed DataFram
   implementation when "numpy_nullable" is set, pyarrow is used for all
   dtypes if "pyarrow" is set.
 
-  The dtype_backends are still experimential.
+  The dtype_backends are still experimental.
 
   .. versionadded:: 2.0
 
@@ -2893,7 +2893,7 @@ Read in the content of the "books.xml" as instance of ``StringIO`` or
    df
 
 Even read XML from AWS S3 buckets such as NIH NCBI PMC Article Datasets providing
-Biomedical and Life Science Jorurnals:
+Biomedical and Life Science Journals:
 
 .. code-block:: python
 

doc/source/user_guide/style.ipynb

@@ -1182,7 +1182,7 @@
     "Some styling functions are common enough that we've \"built them in\" to the `Styler`, so you don't have to write them and apply them yourself. The current list of such functions is:\n",
     "\n",
     " - [.highlight_null][nullfunc]: for use with identifying missing data. \n",
-    " - [.highlight_min][minfunc] and [.highlight_max][maxfunc]: for use with identifying extremeties in data.\n",
+    " - [.highlight_min][minfunc] and [.highlight_max][maxfunc]: for use with identifying extremities in data.\n",
     " - [.highlight_between][betweenfunc] and [.highlight_quantile][quantilefunc]: for use with identifying classes within data.\n",
     " - [.background_gradient][bgfunc]: a flexible method for highlighting cells based on their, or other, values on a numeric scale.\n",
     " - [.text_gradient][textfunc]: similar method for highlighting text based on their, or other, values on a numeric scale.\n",

doc/source/user_guide/visualization.rst

@@ -1504,7 +1504,7 @@ Plotting with error bars
 
 Plotting with error bars is supported in :meth:`DataFrame.plot` and :meth:`Series.plot`.
 
-Horizontal and vertical error bars can be supplied to the ``xerr`` and ``yerr`` keyword arguments to :meth:`~DataFrame.plot()`. The error values can be specified using a variety of formats:
+Horizontal and vertical error bars can be supplied to the ``xerr`` and ``yerr`` keyword arguments to :meth:`~DataFrame.plot`. The error values can be specified using a variety of formats:
 
 * As a :class:`DataFrame` or ``dict`` of errors with column names matching the ``columns`` attribute of the plotting :class:`DataFrame` or matching the ``name`` attribute of the :class:`Series`.
 * As a ``str`` indicating which of the columns of plotting :class:`DataFrame` contain the error values.

doc/source/whatsnew/index.rst

@@ -18,6 +18,13 @@ Version 3.0
 
    v3.0.0
 
+Version 2.3
+-----------
+
+.. toctree::
+   :maxdepth: 2
+
+   v2.3.0
 
 Version 2.2
 -----------

doc/source/whatsnew/v0.15.0.rst

@@ -490,7 +490,7 @@ Rolling/expanding moments improvements
   ``ddof`` argument (with a default value of ``1``) was previously undocumented. (:issue:`8064`)
 
 - :func:`ewma`, :func:`ewmstd`, :func:`ewmvol`, :func:`ewmvar`, :func:`ewmcov`, and :func:`ewmcorr`
-  now interpret ``min_periods`` in the same manner that the :func:`rolling_*()` and :func:`expanding_*()` functions do:
+  now interpret ``min_periods`` in the same manner that the :func:`rolling_*` and :func:`expanding_*` functions do:
   a given result entry will be ``NaN`` if the (expanding, in this case) window does not contain
   at least ``min_periods`` values. The previous behavior was to set to ``NaN`` the ``min_periods`` entries
   starting with the first non- ``NaN`` value. (:issue:`7977`)
@@ -567,7 +567,7 @@ Rolling/expanding moments improvements
 
   .. warning::
 
-     By default (``ignore_na=False``) the :func:`ewm*()` functions' weights calculation
+     By default (``ignore_na=False``) the :func:`ewm*` functions' weights calculation
      in the presence of missing values is different than in pre-0.15.0 versions.
      To reproduce the pre-0.15.0 calculation of weights in the presence of missing values
      one must specify explicitly ``ignore_na=True``.
@@ -576,7 +576,7 @@ Rolling/expanding moments improvements
   returning results with columns sorted by name and producing an error for non-unique columns;
   now handles non-unique columns and returns columns in original order
   (except for the case of two DataFrames with ``pairwise=False``, where behavior is unchanged) (:issue:`7542`)
-- Bug in :func:`rolling_count` and :func:`expanding_*()` functions unnecessarily producing error message for zero-length data (:issue:`8056`)
+- Bug in :func:`rolling_count` and :func:`expanding_*` functions unnecessarily producing error message for zero-length data (:issue:`8056`)
 - Bug in :func:`rolling_apply` and :func:`expanding_apply` interpreting ``min_periods=0`` as ``min_periods=1`` (:issue:`8080`)
 - Bug in :func:`expanding_std` and :func:`expanding_var` for a single value producing a confusing error message (:issue:`7900`)
 - Bug in :func:`rolling_std` and :func:`rolling_var` for a single value producing ``0`` rather than ``NaN`` (:issue:`7900`)
@@ -875,7 +875,7 @@ Other notable API changes:
   The behaviour of assigning a column to an existing dataframe as ``df['a'] = i``
   remains unchanged (this already returned an  ``object`` column with a timezone).
 
-- When passing multiple levels to :meth:`~pandas.DataFrame.stack()`, it will now raise a ``ValueError`` when the
+- When passing multiple levels to :meth:`~pandas.DataFrame.stack`, it will now raise a ``ValueError`` when the
   levels aren't all level names or all level numbers (:issue:`7660`). See
   :ref:`Reshaping by stacking and unstacking <reshaping.stack_multiple>`.
 
@@ -1110,7 +1110,7 @@ Other:
 
 - ``DataFrame.fillna`` can now accept a ``DataFrame`` as a fill value (:issue:`8377`)
 
-- Passing multiple levels to :meth:`~pandas.DataFrame.stack()` will now work when multiple level
+- Passing multiple levels to :meth:`~pandas.DataFrame.stack` will now work when multiple level
   numbers are passed (:issue:`7660`). See
   :ref:`Reshaping by stacking and unstacking <reshaping.stack_multiple>`.
 

doc/source/whatsnew/v0.15.1.rst

@@ -263,7 +263,7 @@ Enhancements
 
 - Raise errors in certain aggregation cases where an argument such as ``numeric_only`` is not handled (:issue:`8592`).
 
-- Added support for 3-character ISO and non-standard country codes in :func:`io.wb.download()` (:issue:`8482`)
+- Added support for 3-character ISO and non-standard country codes in :func:`io.wb.download` (:issue:`8482`)
 
 - World Bank data requests now will warn/raise based
   on an ``errors`` argument, as well as a list of hard-coded country codes and

doc/source/whatsnew/v0.21.0.rst

@@ -318,7 +318,7 @@ New keywords
 - :func:`Series.set_axis` and :func:`DataFrame.set_axis` now support the ``inplace`` parameter. (:issue:`14636`)
 - :func:`Series.to_pickle` and :func:`DataFrame.to_pickle` have gained a ``protocol`` parameter (:issue:`16252`). By default, this parameter is set to `HIGHEST_PROTOCOL <https://docs.python.org/3/library/pickle.html#data-stream-format>`__
 - :func:`read_feather` has gained the ``nthreads`` parameter for multi-threaded operations (:issue:`16359`)
-- :func:`DataFrame.clip()` and :func:`Series.clip()` have gained an ``inplace`` argument. (:issue:`15388`)
+- :func:`DataFrame.clip` and :func:`Series.clip` have gained an ``inplace`` argument. (:issue:`15388`)
 - :func:`crosstab` has gained a ``margins_name`` parameter to define the name of the row / column that will contain the totals when ``margins=True``. (:issue:`15972`)
 - :func:`read_json` now accepts a ``chunksize`` parameter that can be used when ``lines=True``. If ``chunksize`` is passed, read_json now returns an iterator which reads in ``chunksize`` lines with each iteration. (:issue:`17048`)
 - :func:`read_json` and :func:`~DataFrame.to_json` now accept a ``compression`` argument which allows them to transparently handle compressed files. (:issue:`17798`)
@@ -977,10 +977,10 @@ Other API changes
 Deprecations
 ~~~~~~~~~~~~
 
-- :meth:`DataFrame.from_csv` and :meth:`Series.from_csv` have been deprecated in favor of :func:`read_csv()` (:issue:`4191`)
-- :func:`read_excel()` has deprecated ``sheetname`` in favor of ``sheet_name`` for consistency with ``.to_excel()`` (:issue:`10559`).
-- :func:`read_excel()` has deprecated ``parse_cols`` in favor of ``usecols`` for consistency with :func:`read_csv` (:issue:`4988`)
-- :func:`read_csv()` has deprecated the ``tupleize_cols`` argument. Column tuples will always be converted to a ``MultiIndex`` (:issue:`17060`)
+- :meth:`DataFrame.from_csv` and :meth:`Series.from_csv` have been deprecated in favor of :func:`read_csv` (:issue:`4191`)
+- :func:`read_excel` has deprecated ``sheetname`` in favor of ``sheet_name`` for consistency with ``.to_excel()`` (:issue:`10559`).
+- :func:`read_excel` has deprecated ``parse_cols`` in favor of ``usecols`` for consistency with :func:`read_csv` (:issue:`4988`)
+- :func:`read_csv` has deprecated the ``tupleize_cols`` argument. Column tuples will always be converted to a ``MultiIndex`` (:issue:`17060`)
 - :meth:`DataFrame.to_csv` has deprecated the ``tupleize_cols`` argument. MultiIndex columns will be always written as rows in the CSV file (:issue:`17060`)
 - The ``convert`` parameter has been deprecated in the ``.take()`` method, as it was not being respected (:issue:`16948`)
 - ``pd.options.html.border`` has been deprecated in favor of ``pd.options.display.html.border`` (:issue:`15793`).
@@ -1045,7 +1045,7 @@ return the position of the maximum or minimum.
 Removal of prior version deprecations/changes
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-- :func:`read_excel()` has dropped the ``has_index_names`` parameter (:issue:`10967`)
+- :func:`read_excel` has dropped the ``has_index_names`` parameter (:issue:`10967`)
 - The ``pd.options.display.height`` configuration has been dropped (:issue:`3663`)
 - The ``pd.options.display.line_width`` configuration has been dropped (:issue:`2881`)
 - The ``pd.options.display.mpl_style`` configuration has been dropped (:issue:`12190`)
@@ -1154,7 +1154,7 @@ GroupBy/resample/rolling
 
 - Bug in ``DataFrame.resample(...).size()`` where an empty ``DataFrame`` did not return a ``Series`` (:issue:`14962`)
 - Bug in :func:`infer_freq` causing indices with 2-day gaps during the working week to be wrongly inferred as business daily (:issue:`16624`)
-- Bug in ``.rolling(...).quantile()`` which incorrectly used different defaults than :func:`Series.quantile()` and :func:`DataFrame.quantile()` (:issue:`9413`, :issue:`16211`)
+- Bug in ``.rolling(...).quantile()`` which incorrectly used different defaults than :func:`Series.quantile` and :func:`DataFrame.quantile` (:issue:`9413`, :issue:`16211`)
 - Bug in ``groupby.transform()`` that would coerce boolean dtypes back to float (:issue:`16875`)
 - Bug in ``Series.resample(...).apply()`` where an empty ``Series`` modified the source index and did not return the name of a ``Series`` (:issue:`14313`)
 - Bug in ``.rolling(...).apply(...)`` with a ``DataFrame`` with a ``DatetimeIndex``, a ``window`` of a timedelta-convertible and ``min_periods >= 1`` (:issue:`15305`)
@@ -1194,7 +1194,7 @@ Reshaping
 Numeric
 ^^^^^^^
 - Bug in ``.clip()`` with ``axis=1`` and a list-like for ``threshold`` is passed; previously this raised ``ValueError`` (:issue:`15390`)
-- :func:`Series.clip()` and :func:`DataFrame.clip()` now treat NA values for upper and lower arguments as ``None`` instead of raising ``ValueError`` (:issue:`17276`).
+- :func:`Series.clip` and :func:`DataFrame.clip` now treat NA values for upper and lower arguments as ``None`` instead of raising ``ValueError`` (:issue:`17276`).
 
 
 Categorical