Skip to content

Commit eb9d386

Browse files
NavaneetthaSundararajNavaneetthaSundararaj
authored
Merge branch 'main' into main
2 parents d3d9943 + 350904c commit eb9d386

File tree

121 files changed

+1703
-995
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

121 files changed

+1703
-995
lines changed

‎asv_bench/benchmarks/indexing_engines.py

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -87,7 +87,7 @@ def setup(self, engine_and_dtype, index_type, unique, N):
8787
arr = np.array([1, 2, 3], dtype=dtype).repeat(N)
8888

8989
self.data = engine(arr)
90-
# code belows avoids populating the mapping etc. while timing.
90+
# code below avoids populating the mapping etc. while timing.
9191
self.data.get_loc(2)
9292

9393
self.key_middle = arr[len(arr) // 2]
@@ -140,7 +140,7 @@ def setup(self, engine_and_dtype, index_type, unique, N):
140140
mask[-1] = True
141141

142142
self.data = engine(BaseMaskedArray(arr, mask))
143-
# code belows avoids populating the mapping etc. while timing.
143+
# code below avoids populating the mapping etc. while timing.
144144
self.data.get_loc(2)
145145

146146
self.key_middle = arr[len(arr) // 2]
@@ -169,7 +169,7 @@ def setup(self, index_type):
169169
}[index_type]
170170

171171
self.data = libindex.ObjectEngine(arr)
172-
# code belows avoids populating the mapping etc. while timing.
172+
# code below avoids populating the mapping etc. while timing.
173173
self.data.get_loc("b")
174174

175175
def time_get_loc(self, index_type):

‎ci/code_checks.sh

Lines changed: 2 additions & 99 deletions
Original file line numberDiff line numberDiff line change
@@ -70,38 +70,13 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
7070
--format=actions \
7171
-i ES01 `# For now it is ok if docstrings are missing the extended summary` \
7272
-i "pandas.Series.dt PR01" `# Accessors are implemented as classes, but we do not document the Parameters section` \
73-
-i "pandas.MultiIndex.reorder_levels RT03,SA01" \
74-
-i "pandas.MultiIndex.to_frame RT03" \
7573
-i "pandas.NA SA01" \
76-
-i "pandas.NaT SA01" \
7774
-i "pandas.Period.freq GL08" \
78-
-i "pandas.Period.freqstr SA01" \
7975
-i "pandas.Period.ordinal GL08" \
8076
-i "pandas.Period.strftime PR01,SA01" \
8177
-i "pandas.Period.to_timestamp SA01" \
8278
-i "pandas.PeriodDtype SA01" \
8379
-i "pandas.PeriodDtype.freq SA01" \
84-
-i "pandas.PeriodIndex.day SA01" \
85-
-i "pandas.PeriodIndex.day_of_week SA01" \
86-
-i "pandas.PeriodIndex.day_of_year SA01" \
87-
-i "pandas.PeriodIndex.dayofweek SA01" \
88-
-i "pandas.PeriodIndex.dayofyear SA01" \
89-
-i "pandas.PeriodIndex.days_in_month SA01" \
90-
-i "pandas.PeriodIndex.daysinmonth SA01" \
91-
-i "pandas.PeriodIndex.from_fields PR07,SA01" \
92-
-i "pandas.PeriodIndex.from_ordinals SA01" \
93-
-i "pandas.PeriodIndex.hour SA01" \
94-
-i "pandas.PeriodIndex.is_leap_year SA01" \
95-
-i "pandas.PeriodIndex.minute SA01" \
96-
-i "pandas.PeriodIndex.month SA01" \
97-
-i "pandas.PeriodIndex.quarter SA01" \
98-
-i "pandas.PeriodIndex.qyear GL08" \
99-
-i "pandas.PeriodIndex.second SA01" \
100-
-i "pandas.PeriodIndex.to_timestamp RT03,SA01" \
101-
-i "pandas.PeriodIndex.week SA01" \
102-
-i "pandas.PeriodIndex.weekday SA01" \
103-
-i "pandas.PeriodIndex.weekofyear SA01" \
104-
-i "pandas.PeriodIndex.year SA01" \
10580
-i "pandas.RangeIndex PR07" \
10681
-i "pandas.RangeIndex.from_range PR01,SA01" \
10782
-i "pandas.RangeIndex.start SA01" \
@@ -124,7 +99,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
12499
-i "pandas.Series.dt.month_name PR01,PR02" \
125100
-i "pandas.Series.dt.nanoseconds SA01" \
126101
-i "pandas.Series.dt.normalize PR01" \
127-
-i "pandas.Series.dt.qyear GL08" \
128102
-i "pandas.Series.dt.round PR01,PR02" \
129103
-i "pandas.Series.dt.seconds SA01" \
130104
-i "pandas.Series.dt.strftime PR01,PR02" \
@@ -133,34 +107,11 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
133107
-i "pandas.Series.dt.tz_convert PR01,PR02" \
134108
-i "pandas.Series.dt.tz_localize PR01,PR02" \
135109
-i "pandas.Series.dt.unit GL08" \
136-
-i "pandas.Series.gt SA01" \
137-
-i "pandas.Series.list.__getitem__ SA01" \
138-
-i "pandas.Series.list.flatten SA01" \
139-
-i "pandas.Series.list.len SA01" \
140-
-i "pandas.Series.lt SA01" \
141-
-i "pandas.Series.ne SA01" \
142110
-i "pandas.Series.pad PR01,SA01" \
143-
-i "pandas.Series.pop SA01" \
144-
-i "pandas.Series.prod RT03" \
145-
-i "pandas.Series.product RT03" \
146-
-i "pandas.Series.reorder_levels RT03,SA01" \
147-
-i "pandas.Series.sem PR01,RT03,SA01" \
148-
-i "pandas.Series.sparse PR01,SA01" \
149-
-i "pandas.Series.sparse.density SA01" \
150111
-i "pandas.Series.sparse.fill_value SA01" \
151112
-i "pandas.Series.sparse.from_coo PR07,SA01" \
152113
-i "pandas.Series.sparse.npoints SA01" \
153114
-i "pandas.Series.sparse.sp_values SA01" \
154-
-i "pandas.Series.sparse.to_coo PR07,RT03,SA01" \
155-
-i "pandas.Series.std PR01,RT03,SA01" \
156-
-i "pandas.Series.str.match RT03" \
157-
-i "pandas.Series.str.normalize RT03,SA01" \
158-
-i "pandas.Series.str.repeat SA01" \
159-
-i "pandas.Series.str.replace SA01" \
160-
-i "pandas.Series.str.wrap RT03,SA01" \
161-
-i "pandas.Series.str.zfill RT03" \
162-
-i "pandas.Series.struct.dtypes SA01" \
163-
-i "pandas.Series.to_markdown SA01" \
164115
-i "pandas.Timedelta.asm8 SA01" \
165116
-i "pandas.Timedelta.ceil SA01" \
166117
-i "pandas.Timedelta.components SA01" \
@@ -173,7 +124,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
173124
-i "pandas.Timedelta.to_timedelta64 SA01" \
174125
-i "pandas.Timedelta.total_seconds SA01" \
175126
-i "pandas.Timedelta.view SA01" \
176-
-i "pandas.TimedeltaIndex.as_unit RT03,SA01" \
177127
-i "pandas.TimedeltaIndex.components SA01" \
178128
-i "pandas.TimedeltaIndex.microseconds SA01" \
179129
-i "pandas.TimedeltaIndex.nanoseconds SA01" \
@@ -183,26 +133,14 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
183133
-i "pandas.Timestamp.fold GL08" \
184134
-i "pandas.Timestamp.minute GL08" \
185135
-i "pandas.Timestamp.month GL08" \
136+
-i "pandas.Timestamp.max PR02" \
137+
-i "pandas.Timestamp.min PR02" \
186138
-i "pandas.Timestamp.nanosecond GL08" \
187139
-i "pandas.Timestamp.resolution PR02" \
188-
-i "pandas.Timestamp.second GL08" \
189140
-i "pandas.Timestamp.tzinfo GL08" \
190141
-i "pandas.Timestamp.value GL08" \
191142
-i "pandas.Timestamp.year GL08" \
192-
-i "pandas.api.extensions.ExtensionArray._pad_or_backfill PR01,RT03,SA01" \
193-
-i "pandas.api.extensions.ExtensionArray._reduce RT03,SA01" \
194-
-i "pandas.api.extensions.ExtensionArray._values_for_factorize SA01" \
195-
-i "pandas.api.extensions.ExtensionArray.astype SA01" \
196-
-i "pandas.api.extensions.ExtensionArray.dropna RT03,SA01" \
197-
-i "pandas.api.extensions.ExtensionArray.dtype SA01" \
198-
-i "pandas.api.extensions.ExtensionArray.duplicated RT03,SA01" \
199-
-i "pandas.api.extensions.ExtensionArray.fillna SA01" \
200-
-i "pandas.api.extensions.ExtensionArray.insert PR07,RT03,SA01" \
201143
-i "pandas.api.extensions.ExtensionArray.interpolate PR01,SA01" \
202-
-i "pandas.api.extensions.ExtensionArray.isin PR07,RT03,SA01" \
203-
-i "pandas.api.extensions.ExtensionArray.tolist RT03,SA01" \
204-
-i "pandas.api.extensions.ExtensionArray.unique RT03,SA01" \
205-
-i "pandas.api.extensions.ExtensionArray.view SA01" \
206144
-i "pandas.api.interchange.from_dataframe RT03,SA01" \
207145
-i "pandas.api.types.is_bool PR01,SA01" \
208146
-i "pandas.api.types.is_categorical_dtype SA01" \
@@ -255,7 +193,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
255193
-i "pandas.core.groupby.DataFrameGroupBy.nunique SA01" \
256194
-i "pandas.core.groupby.DataFrameGroupBy.ohlc SA01" \
257195
-i "pandas.core.groupby.DataFrameGroupBy.plot PR02" \
258-
-i "pandas.core.groupby.DataFrameGroupBy.prod SA01" \
259196
-i "pandas.core.groupby.DataFrameGroupBy.sem SA01" \
260197
-i "pandas.core.groupby.DataFrameGroupBy.sum SA01" \
261198
-i "pandas.core.groupby.SeriesGroupBy.__iter__ RT03,SA01" \
@@ -272,7 +209,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
272209
-i "pandas.core.groupby.SeriesGroupBy.nth PR02" \
273210
-i "pandas.core.groupby.SeriesGroupBy.ohlc SA01" \
274211
-i "pandas.core.groupby.SeriesGroupBy.plot PR02" \
275-
-i "pandas.core.groupby.SeriesGroupBy.prod SA01" \
276212
-i "pandas.core.groupby.SeriesGroupBy.sem SA01" \
277213
-i "pandas.core.groupby.SeriesGroupBy.sum SA01" \
278214
-i "pandas.core.resample.Resampler.__iter__ RT03,SA01" \
@@ -291,11 +227,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
291227
-i "pandas.core.resample.Resampler.sum SA01" \
292228
-i "pandas.core.resample.Resampler.transform PR01,RT03,SA01" \
293229
-i "pandas.core.resample.Resampler.var SA01" \
294-
-i "pandas.core.window.expanding.Expanding.corr PR01" \
295-
-i "pandas.core.window.expanding.Expanding.count PR01" \
296-
-i "pandas.core.window.rolling.Rolling.max PR01" \
297-
-i "pandas.core.window.rolling.Window.std PR01" \
298-
-i "pandas.core.window.rolling.Window.var PR01" \
299230
-i "pandas.date_range RT03" \
300231
-i "pandas.errors.AbstractMethodError PR01,SA01" \
301232
-i "pandas.errors.AttributeConflictWarning SA01" \
@@ -325,34 +256,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
325256
-i "pandas.errors.UnsupportedFunctionCall SA01" \
326257
-i "pandas.errors.ValueLabelTypeMismatch SA01" \
327258
-i "pandas.infer_freq SA01" \
328-
-i "pandas.io.formats.style.Styler.apply RT03" \
329-
-i "pandas.io.formats.style.Styler.apply_index RT03" \
330-
-i "pandas.io.formats.style.Styler.background_gradient RT03" \
331-
-i "pandas.io.formats.style.Styler.bar RT03,SA01" \
332-
-i "pandas.io.formats.style.Styler.clear SA01" \
333-
-i "pandas.io.formats.style.Styler.concat RT03,SA01" \
334-
-i "pandas.io.formats.style.Styler.export RT03" \
335-
-i "pandas.io.formats.style.Styler.from_custom_template SA01" \
336-
-i "pandas.io.formats.style.Styler.hide RT03,SA01" \
337-
-i "pandas.io.formats.style.Styler.highlight_between RT03" \
338-
-i "pandas.io.formats.style.Styler.highlight_max RT03" \
339-
-i "pandas.io.formats.style.Styler.highlight_min RT03" \
340-
-i "pandas.io.formats.style.Styler.highlight_null RT03" \
341-
-i "pandas.io.formats.style.Styler.highlight_quantile RT03" \
342-
-i "pandas.io.formats.style.Styler.map RT03" \
343-
-i "pandas.io.formats.style.Styler.map_index RT03" \
344-
-i "pandas.io.formats.style.Styler.set_caption RT03,SA01" \
345-
-i "pandas.io.formats.style.Styler.set_properties RT03,SA01" \
346-
-i "pandas.io.formats.style.Styler.set_sticky RT03,SA01" \
347-
-i "pandas.io.formats.style.Styler.set_table_attributes PR07,RT03" \
348-
-i "pandas.io.formats.style.Styler.set_table_styles RT03" \
349-
-i "pandas.io.formats.style.Styler.set_td_classes RT03" \
350-
-i "pandas.io.formats.style.Styler.set_tooltips RT03,SA01" \
351-
-i "pandas.io.formats.style.Styler.set_uuid PR07,RT03,SA01" \
352-
-i "pandas.io.formats.style.Styler.text_gradient RT03" \
353-
-i "pandas.io.formats.style.Styler.to_excel PR01" \
354-
-i "pandas.io.formats.style.Styler.to_string SA01" \
355-
-i "pandas.io.formats.style.Styler.use RT03" \
356259
-i "pandas.io.json.build_table_schema PR07,RT03,SA01" \
357260
-i "pandas.io.stata.StataReader.data_label SA01" \
358261
-i "pandas.io.stata.StataReader.value_labels RT03,SA01" \

‎doc/source/development/contributing_codebase.rst

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -605,7 +605,7 @@ The ``temp_file`` pytest fixture creates a temporary file :py:class:`Pathlib` ob
605605
pd.DataFrame([1]).to_csv(str(temp_file))
606606
607607
Please reference `pytest's documentation <https://docs.pytest.org/en/latest/how-to/tmp_path.html#the-default-base-temporary-directory>`_
608-
for the file retension policy.
608+
for the file retention policy.
609609

610610
Testing involving network connectivity
611611
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

‎doc/source/development/debugging_extensions.rst

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -30,7 +30,7 @@ By specifying ``builddir="debug"`` all of the targets will be built and placed i
3030
Using Docker
3131
------------
3232

33-
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.
33+
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.
3434

3535
You can then mount your pandas repository into this image via:
3636

‎doc/source/getting_started/index.rst

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -613,7 +613,7 @@ the pandas-equivalent operations compared to software you already know:
613613

614614
Users of `Excel <https://en.wikipedia.org/wiki/Microsoft_Excel>`__
615615
or other spreadsheet programs will find that many of the concepts are
616-
transferrable to pandas.
616+
transferable to pandas.
617617

618618
+++
619619

‎doc/source/user_guide/cookbook.rst

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -914,7 +914,7 @@ Using TimeGrouper and another grouping to create subgroups, then apply a custom
914914
<https://stackoverflow.com/questions/15408156/resampling-with-custom-periods>`__
915915

916916
`Resample intraday frame without adding new days
917-
<https://stackoverflow.com/questions/14898574/resample-intrday-pandas-dataframe-without-add-new-days>`__
917+
<https://stackoverflow.com/questions/14898574/resample-intraday-pandas-dataframe-without-add-new-days>`__
918918

919919
`Resample minute data
920920
<https://stackoverflow.com/questions/14861023/resampling-minute-data>`__

‎doc/source/user_guide/io.rst

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -169,7 +169,7 @@ dtype_backend : {"numpy_nullable", "pyarrow"}, defaults to NumPy backed DataFram
169169
implementation when "numpy_nullable" is set, pyarrow is used for all
170170
dtypes if "pyarrow" is set.
171171

172-
The dtype_backends are still experimential.
172+
The dtype_backends are still experiential.
173173

174174
.. versionadded:: 2.0
175175

@@ -2893,7 +2893,7 @@ Read in the content of the "books.xml" as instance of ``StringIO`` or
28932893
df
28942894
28952895
Even read XML from AWS S3 buckets such as NIH NCBI PMC Article Datasets providing
2896-
Biomedical and Life Science Jorurnals:
2896+
Biomedical and Life Science Journals:
28972897

28982898
.. code-block:: python
28992899

‎doc/source/user_guide/style.ipynb

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1182,7 +1182,7 @@
11821182
"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",
11831183
"\n",
11841184
" - [.highlight_null][nullfunc]: for use with identifying missing data. \n",
1185-
" - [.highlight_min][minfunc] and [.highlight_max][maxfunc]: for use with identifying extremeties in data.\n",
1185+
" - [.highlight_min][minfunc] and [.highlight_max][maxfunc]: for use with identifying extremities in data.\n",
11861186
" - [.highlight_between][betweenfunc] and [.highlight_quantile][quantilefunc]: for use with identifying classes within data.\n",
11871187
" - [.background_gradient][bgfunc]: a flexible method for highlighting cells based on their, or other, values on a numeric scale.\n",
11881188
" - [.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

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1504,7 +1504,7 @@ Plotting with error bars
15041504

15051505
Plotting with error bars is supported in :meth:`DataFrame.plot` and :meth:`Series.plot`.
15061506

1507-
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:
1507+
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:
15081508

15091509
* 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`.
15101510
* As a ``str`` indicating which of the columns of plotting :class:`DataFrame` contain the error values.

‎doc/source/whatsnew/index.rst

Lines changed: 7 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -18,6 +18,13 @@ Version 3.0
1818

1919
v3.0.0
2020

21+
Version 2.3
22+
-----------
23+
24+
.. toctree::
25+
:maxdepth: 2
26+
27+
v2.3.0
2128

2229
Version 2.2
2330
-----------

0 commit comments

Comments
 (0)