Merge branch 'main' into example

Author: Uvi-12

ci/code_checks.sh

@@ -83,22 +83,18 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Timestamp.resolution PR02" \
         -i "pandas.Timestamp.tzinfo GL08" \
         -i "pandas.arrays.ArrowExtensionArray PR07,SA01" \
-        -i "pandas.arrays.IntegerArray SA01" \
         -i "pandas.arrays.IntervalArray.length SA01" \
         -i "pandas.arrays.NumpyExtensionArray SA01" \
         -i "pandas.arrays.TimedeltaArray PR07,SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.boxplot PR07,RT03,SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.get_group RT03,SA01" \
-        -i "pandas.core.groupby.DataFrameGroupBy.indices SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.nunique SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.plot PR02" \
         -i "pandas.core.groupby.DataFrameGroupBy.sem SA01" \
         -i "pandas.core.groupby.SeriesGroupBy.get_group RT03,SA01" \
-        -i "pandas.core.groupby.SeriesGroupBy.indices SA01" \
         -i "pandas.core.groupby.SeriesGroupBy.plot PR02" \
         -i "pandas.core.groupby.SeriesGroupBy.sem SA01" \
         -i "pandas.core.resample.Resampler.get_group RT03,SA01" \
-        -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.min PR01,RT03,SA01" \
@@ -108,15 +104,12 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.core.resample.Resampler.std SA01" \
         -i "pandas.core.resample.Resampler.transform PR01,RT03,SA01" \
         -i "pandas.core.resample.Resampler.var SA01" \
-        -i "pandas.errors.IntCastingNaNError SA01" \
         -i "pandas.errors.NullFrequencyError SA01" \
         -i "pandas.errors.NumbaUtilError SA01" \
         -i "pandas.errors.PerformanceWarning SA01" \
         -i "pandas.errors.UndefinedVariableError PR01,SA01" \
         -i "pandas.errors.ValueLabelTypeMismatch SA01" \
-        -i "pandas.infer_freq SA01" \
         -i "pandas.io.json.build_table_schema PR07,RT03,SA01" \
-        -i "pandas.io.stata.StataWriter.write_file SA01" \
         -i "pandas.plotting.andrews_curves RT03,SA01" \
         -i "pandas.plotting.scatter_matrix PR07,SA01" \
         -i "pandas.tseries.offsets.BDay PR02,SA01" \

environment.yml

@@ -87,7 +87,7 @@ dependencies:
   - google-auth
   - natsort  # DataFrame.sort_values doctest
   - numpydoc
-  - pydata-sphinx-theme=0.14
+  - pydata-sphinx-theme=0.16
   - pytest-cython  # doctest
   - sphinx
   - sphinx-design

pandas/_config/config.py

@@ -188,6 +188,11 @@ def set_option(*args) -> None:
     """
     Set the value of the specified option or options.
 
+    This method allows fine-grained control over the behavior and display settings
+    of pandas. Options affect various functionalities such as output formatting,
+    display limits, and operational behavior. Settings can be modified at runtime
+    without requiring changes to global configurations or environment variables.
+
     Parameters
     ----------
     *args : str | object

pandas/core/arrays/integer.py

@@ -105,6 +105,12 @@ class IntegerArray(NumericArray):
     -------
     IntegerArray
 
+    See Also
+    --------
+    array : Create an array using the appropriate dtype, including ``IntegerArray``.
+    Int32Dtype : An ExtensionDtype for int32 integer data.
+    UInt16Dtype : An ExtensionDtype for uint16 integer data.
+
     Examples
     --------
     Create an IntegerArray with :func:`pandas.array`.

pandas/core/groupby/groupby.py

@@ -515,6 +515,15 @@ def indices(self) -> dict[Hashable, npt.NDArray[np.intp]]:
         """
         Dict {group name -> group indices}.
 
+        See Also
+        --------
+        core.groupby.DataFrameGroupBy.indices : Provides a mapping of group rows to
+            positions of the elements.
+        core.groupby.SeriesGroupBy.indices : Provides a mapping of group rows to
+            positions of the elements.
+        core.resample.Resampler.indices : Provides a mapping of group rows to
+            positions of the elements.
+
         Examples
         --------
 

pandas/errors/__init__.py

@@ -20,6 +20,16 @@ class IntCastingNaNError(ValueError):
     """
     Exception raised when converting (``astype``) an array with NaN to an integer type.
 
+    This error occurs when attempting to cast a data structure containing non-finite
+    values (such as NaN or infinity) to an integer data type. Integer types do not
+    support non-finite values, so such conversions are explicitly disallowed to
+    prevent silent data corruption or unexpected behavior.
+
+    See Also
+    --------
+    DataFrame.astype : Method to cast a pandas DataFrame object to a specified dtype.
+    Series.astype : Method to cast a pandas Series object to a specified dtype.
+
     Examples
     --------
     >>> pd.DataFrame(np.array([[1, np.nan], [2, 3]]), dtype="i8")

pandas/io/stata.py

@@ -2748,6 +2748,18 @@ def write_file(self) -> None:
         """
         Export DataFrame object to Stata dta format.
 
+        This method writes the contents of a pandas DataFrame to a `.dta` file
+        compatible with Stata. It includes features for handling value labels,
+        variable types, and metadata like timestamps and data labels. The output
+        file can then be read and used in Stata or other compatible statistical
+        tools.
+
+        See Also
+        --------
+        read_stata : Read Stata file into DataFrame.
+        DataFrame.to_stata : Export DataFrame object to Stata dta format.
+        io.stata.StataWriter : A class for writing Stata binary dta files.
+
         Examples
         --------
         >>> df = pd.DataFrame(

pandas/tseries/frequencies.py

@@ -89,6 +89,11 @@ def infer_freq(
     """
     Infer the most likely frequency given the input index.
 
+    This method attempts to deduce the most probable frequency (e.g., 'D' for daily,
+    'H' for hourly) from a sequence of datetime-like objects. It is particularly useful
+    when the frequency of a time series is not explicitly set or known but can be
+    inferred from its values.
+
     Parameters
     ----------
     index : DatetimeIndex, TimedeltaIndex, Series or array-like
@@ -106,6 +111,13 @@ def infer_freq(
     ValueError
         If there are fewer than three values.
 
+    See Also
+    --------
+    date_range : Return a fixed frequency DatetimeIndex.
+    timedelta_range : Return a fixed frequency TimedeltaIndex with day as the default.
+    period_range : Return a fixed frequency PeriodIndex.
+    DatetimeIndex.freq : Return the frequency object if it is set, otherwise None.
+
     Examples
     --------
     >>> idx = pd.date_range(start="2020/12/01", end="2020/12/30", periods=30)

requirements-dev.txt

@@ -62,7 +62,7 @@ gitdb
 google-auth
 natsort
 numpydoc
-pydata-sphinx-theme==0.14
+pydata-sphinx-theme==0.16
 pytest-cython
 sphinx
 sphinx-design