Merge branch 'main' into na_values_doc

Author: kushagr96

.github/workflows/unit-tests.yml

@@ -57,6 +57,9 @@ jobs:
             # Also install zh_CN (its encoding is gb2312) but do not activate it.
             # It will be temporarily activated during tests with locale.setlocale
             extra_loc: "zh_CN"
+          - name: "Future infer strings"
+            env_file: actions-311.yaml
+            pandas_future_infer_string: "1"
           - name: "Pypy"
             env_file: actions-pypy-39.yaml
             pattern: "not slow and not network and not single_cpu"
@@ -75,6 +78,7 @@ jobs:
       LANG: ${{ matrix.lang || 'C.UTF-8' }}
       LC_ALL: ${{ matrix.lc_all || '' }}
       PANDAS_CI: '1'
+      PANDAS_FUTURE_INFER_STRING: ${{ matrix.pandas_future_infer_string || '0' }}
       TEST_ARGS: ${{ matrix.test_args || '' }}
       PYTEST_WORKERS: 'auto'
       PYTEST_TARGET: ${{ matrix.pytest_target || 'pandas' }}

README.md

@@ -96,7 +96,7 @@ The source code is currently hosted on GitHub at:
 https://github.com/pandas-dev/pandas
 
 Binary installers for the latest released version are available at the [Python
-Package Index (PyPI)](https://pypi.org/project/pandas) and on [Conda](https://docs.conda.io/en/latest/).
+Package Index (PyPI)](https://pypi.org/project/pandas) and on [Conda](https://anaconda.org/conda-forge/pandas).
 
 ```sh
 # conda

ci/code_checks.sh

@@ -70,16 +70,10 @@ 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.append PR07,SA01" \
-        -i "pandas.MultiIndex.copy PR07,RT03,SA01" \
         -i "pandas.MultiIndex.get_level_values SA01" \
-        -i "pandas.MultiIndex.get_loc PR07" \
         -i "pandas.MultiIndex.get_loc_level PR07" \
-        -i "pandas.MultiIndex.levshape SA01" \
         -i "pandas.MultiIndex.names SA01" \
-        -i "pandas.MultiIndex.remove_unused_levels RT03,SA01" \
         -i "pandas.MultiIndex.reorder_levels RT03,SA01" \
-        -i "pandas.MultiIndex.set_levels RT03,SA01" \
         -i "pandas.MultiIndex.sortlevel PR07,SA01" \
         -i "pandas.MultiIndex.to_frame RT03" \
         -i "pandas.NA SA01" \
@@ -223,7 +217,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Timestamp.fromordinal SA01" \
         -i "pandas.Timestamp.fromtimestamp PR01,SA01" \
         -i "pandas.Timestamp.hour GL08" \
-        -i "pandas.Timestamp.isoweekday SA01" \
         -i "pandas.Timestamp.max PR02" \
         -i "pandas.Timestamp.microsecond GL08" \
         -i "pandas.Timestamp.min PR02" \
@@ -304,10 +297,8 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.api.types.is_re PR07,SA01" \
         -i "pandas.api.types.is_re_compilable PR07,SA01" \
         -i "pandas.api.types.is_sparse SA01" \
-        -i "pandas.api.types.is_string_dtype SA01" \
         -i "pandas.api.types.is_timedelta64_ns_dtype SA01" \
         -i "pandas.api.types.pandas_dtype PR07,RT03,SA01" \
-        -i "pandas.api.types.union_categoricals RT03,SA01" \
         -i "pandas.arrays.ArrowExtensionArray PR07,SA01" \
         -i "pandas.arrays.BooleanArray SA01" \
         -i "pandas.arrays.DatetimeArray SA01" \
@@ -330,7 +321,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.core.groupby.DataFrameGroupBy.hist RT03" \
         -i "pandas.core.groupby.DataFrameGroupBy.indices SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.max SA01" \
-        -i "pandas.core.groupby.DataFrameGroupBy.median SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.min SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.nth PR02" \
         -i "pandas.core.groupby.DataFrameGroupBy.nunique SA01" \
@@ -349,7 +339,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.core.groupby.SeriesGroupBy.is_monotonic_decreasing SA01" \
         -i "pandas.core.groupby.SeriesGroupBy.is_monotonic_increasing SA01" \
         -i "pandas.core.groupby.SeriesGroupBy.max SA01" \
-        -i "pandas.core.groupby.SeriesGroupBy.median SA01" \
         -i "pandas.core.groupby.SeriesGroupBy.min SA01" \
         -i "pandas.core.groupby.SeriesGroupBy.nth PR02" \
         -i "pandas.core.groupby.SeriesGroupBy.ohlc SA01" \
@@ -364,7 +353,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.core.resample.Resampler.indices SA01" \
         -i "pandas.core.resample.Resampler.max PR01,RT03,SA01" \
         -i "pandas.core.resample.Resampler.mean SA01" \
-        -i "pandas.core.resample.Resampler.median SA01" \
         -i "pandas.core.resample.Resampler.min PR01,RT03,SA01" \
         -i "pandas.core.resample.Resampler.ohlc SA01" \
         -i "pandas.core.resample.Resampler.prod SA01" \

doc/source/getting_started/comparison/comparison_with_sql.rst

@@ -505,7 +505,7 @@ DELETE
     DELETE FROM tips
     WHERE tip > 9;
 
-In pandas we select the rows that should remain instead of deleting them:
+In pandas we select the rows that should remain instead of deleting the rows that should be removed:
 
 .. ipython:: python
 

doc/source/user_guide/pyarrow.rst

@@ -159,9 +159,11 @@ PyArrow also provides IO reading functionality that has been integrated into sev
 functions provide an ``engine`` keyword that can dispatch to PyArrow to accelerate reading from an IO source.
 
 * :func:`read_csv`
+* :func:`read_feather`
 * :func:`read_json`
 * :func:`read_orc`
-* :func:`read_feather`
+* :func:`read_parquet`
+* :func:`read_table` (experimental)
 
 .. ipython:: python
 

doc/source/user_guide/style.ipynb

@@ -351,7 +351,7 @@
     "\n",
     "- Using [.set_table_styles()][table] to control broader areas of the table with specified internal CSS. Although table styles allow the flexibility to add CSS selectors and properties controlling all individual parts of the table, they are unwieldy for individual cell specifications. Also, note that table styles cannot be exported to Excel. \n",
     "- Using [.set_td_classes()][td_class] to directly link either external CSS classes to your data cells or link the internal CSS classes created by [.set_table_styles()][table]. See [here](#Setting-Classes-and-Linking-to-External-CSS). These cannot be used on column header rows or indexes, and also won't export to Excel. \n",
-    "- Using the [.apply()][apply] and [.map()][map] functions to add direct internal CSS to specific data cells. See [here](#Styler-Functions). As of v1.4.0 there are also methods that work directly on column header rows or indexes; [.apply_index()][applyindex] and [.map_index()][mapindex]. Note that only these methods add styles that will export to Excel. These methods work in a similar way to [DataFrame.apply()][dfapply] and [DataFrame.map()][dfmap].\n",
+    "- Using the [.apply()][apply] and [.map()][map] functions to add direct internal CSS to specific data cells. See [here](#Styler-Functions). As of v1.4.0 there are also methods that work directly on column header rows or indexes: [.apply_index()][applyindex] and [.map_index()][mapindex]. Note that only these methods add styles that will export to Excel. These methods work in a similar way to [DataFrame.apply()][dfapply] and [DataFrame.map()][dfmap].\n",
     "\n",
     "[table]: ../reference/api/pandas.io.formats.style.Styler.set_table_styles.rst\n",
     "[styler]: ../reference/api/pandas.io.formats.style.Styler.rst\n",

doc/source/whatsnew/v3.0.0.rst

@@ -35,6 +35,7 @@ Other enhancements
 - :meth:`DataFrame.agg` called with ``axis=1`` and a ``func`` which relabels the result index now raises a ``NotImplementedError`` (:issue:`58807`).
 - :meth:`Index.get_loc` now accepts also subclasses of ``tuple`` as keys (:issue:`57922`)
 - :meth:`Styler.set_tooltips` provides alternative method to storing tooltips by using title attribute of td elements. (:issue:`56981`)
+- Added missing parameter ``weights`` in :meth:`DataFrame.plot.kde` for the estimation of the PDF (:issue:`59337`)
 - Allow dictionaries to be passed to :meth:`pandas.Series.str.replace` via ``pat`` parameter (:issue:`51748`)
 - Support passing a :class:`Series` input to :func:`json_normalize` that retains the :class:`Series` :class:`Index` (:issue:`51452`)
 - Support reading value labels from Stata 108-format (Stata 6) and earlier files (:issue:`58154`)
@@ -583,6 +584,8 @@ I/O
 - Bug in :meth:`read_excel` raising ``ValueError`` when passing array of boolean values when ``dtype="boolean"``. (:issue:`58159`)
 - Bug in :meth:`read_json` not validating the ``typ`` argument to not be exactly ``"frame"`` or ``"series"`` (:issue:`59124`)
 - Bug in :meth:`read_stata` raising ``KeyError`` when input file is stored in big-endian format and contains strL data. (:issue:`58638`)
+- Bug in :meth:`read_stata` where extreme value integers were incorrectly interpreted as missing for format versions 111 and prior (:issue:`58130`)
+- Bug in :meth:`read_stata` where the missing code for double was not recognised for format versions 105 and prior (:issue:`58149`)
 
 Period
 ^^^^^^

pandas/_config/__init__.py

@@ -30,6 +30,6 @@
 from pandas._config.display import detect_console_encoding
 
 
-def using_pyarrow_string_dtype() -> bool:
+def using_string_dtype() -> bool:
     _mode_options = _global_config["future"]
     return _mode_options["infer_string"]

pandas/_libs/lib.pyx

@@ -37,7 +37,7 @@ from cython cimport (
     floating,
 )
 
-from pandas._config import using_pyarrow_string_dtype
+from pandas._config import using_string_dtype
 
 from pandas._libs.missing import check_na_tuples_nonequal
 
@@ -2699,10 +2699,10 @@ def maybe_convert_objects(ndarray[object] objects,
         seen.object_ = True
 
     elif seen.str_:
-        if using_pyarrow_string_dtype() and is_string_array(objects, skipna=True):
+        if using_string_dtype() and is_string_array(objects, skipna=True):
             from pandas.core.arrays.string_ import StringDtype
 
-            dtype = StringDtype(storage="pyarrow_numpy")
+            dtype = StringDtype(storage="pyarrow", na_value=np.nan)
             return dtype.construct_array_type()._from_sequence(objects, dtype=dtype)
 
         elif convert_to_nullable_dtype and is_string_array(objects, skipna=True):

pandas/_libs/tslibs/nattype.pyx

@@ -441,6 +441,13 @@ class NaTType(_NaT):
 
         Monday == 1 ... Sunday == 7.
 
+        See Also
+        --------
+        Timestamp.weekday : Return the day of the week with Monday=0, Sunday=6.
+        Timestamp.isocalendar : Return a tuple containing ISO year, week number
+            and weekday.
+        datetime.date.isoweekday : Equivalent method in datetime module.
+
         Examples
         --------
         >>> ts = pd.Timestamp('2023-01-01 10:00:00')