Merge remote-tracking branch 'upstream/main' into eval_div

Author: yuanx749

ci/code_checks.sh

@@ -100,21 +100,15 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Timedelta.max PR02" \
         -i "pandas.Timedelta.min PR02" \
         -i "pandas.Timedelta.resolution PR02" \
-        -i "pandas.TimedeltaIndex.to_pytimedelta RT03,SA01" \
         -i "pandas.Timestamp.max PR02" \
         -i "pandas.Timestamp.min PR02" \
         -i "pandas.Timestamp.nanosecond GL08" \
         -i "pandas.Timestamp.resolution PR02" \
         -i "pandas.Timestamp.tzinfo GL08" \
         -i "pandas.Timestamp.year GL08" \
-        -i "pandas.api.types.is_dict_like PR07,SA01" \
-        -i "pandas.api.types.is_file_like PR07,SA01" \
         -i "pandas.api.types.is_float PR01,SA01" \
-        -i "pandas.api.types.is_hashable PR01,RT03,SA01" \
         -i "pandas.api.types.is_integer PR01,SA01" \
         -i "pandas.api.types.is_iterator PR07,SA01" \
-        -i "pandas.api.types.is_named_tuple PR07,SA01" \
-        -i "pandas.api.types.is_re PR07,SA01" \
         -i "pandas.api.types.is_re_compilable PR07,SA01" \
         -i "pandas.api.types.pandas_dtype PR07,RT03,SA01" \
         -i "pandas.arrays.ArrowExtensionArray PR07,SA01" \
@@ -165,7 +159,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.errors.CSSWarning SA01" \
         -i "pandas.errors.CategoricalConversionWarning SA01" \
         -i "pandas.errors.ChainedAssignmentError SA01" \
-        -i "pandas.errors.ClosedFileError SA01" \
         -i "pandas.errors.DataError SA01" \
         -i "pandas.errors.DuplicateLabelError SA01" \
         -i "pandas.errors.IntCastingNaNError SA01" \
@@ -175,7 +168,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.errors.NumExprClobberingError SA01" \
         -i "pandas.errors.NumbaUtilError SA01" \
         -i "pandas.errors.OptionError SA01" \
-        -i "pandas.errors.OutOfBoundsDatetime SA01" \
         -i "pandas.errors.OutOfBoundsTimedelta SA01" \
         -i "pandas.errors.PerformanceWarning SA01" \
         -i "pandas.errors.PossibleDataLossError SA01" \

doc/source/getting_started/intro_tutorials/08_combine_dataframes.rst

@@ -271,7 +271,7 @@ Add the parameters' full description and name, provided by the parameters metada
 
 Compared to the previous example, there is no common column name.
 However, the ``parameter`` column in the ``air_quality`` table and the
-``id`` column in the ``air_quality_parameters_name`` both provide the
+``id`` column in the ``air_quality_parameters`` table both provide the
 measured variable in a common format. The ``left_on`` and ``right_on``
 arguments are used here (instead of just ``on``) to make the link
 between the two tables.

doc/source/user_guide/10min.rst

@@ -177,7 +177,7 @@ See the indexing documentation :ref:`Indexing and Selecting Data <indexing>` and
 Getitem (``[]``)
 ~~~~~~~~~~~~~~~~
 
-For a :class:`DataFrame`, passing a single label selects a columns and
+For a :class:`DataFrame`, passing a single label selects a column and
 yields a :class:`Series` equivalent to ``df.A``:
 
 .. ipython:: python

doc/source/user_guide/dsintro.rst

@@ -87,8 +87,9 @@ index will be pulled out.
 
 **From scalar value**
 
-If ``data`` is a scalar value, an index must be
-provided. The value will be repeated to match the length of **index**.
+If ``data`` is a scalar value, the value will be repeated to match
+the length of **index**.  If the **index** is not provided, it defaults
+to ``RangeIndex(1)``.
 
 .. ipython:: python
 

pandas/_libs/src/vendored/ujson/python/JSONtoObj.c

@@ -38,9 +38,11 @@ Numeric decoder derived from TCL library
 
 // Licence at LICENSES/ULTRAJSON_LICENSE
 
-#include "pandas/vendored/ujson/lib/ultrajson.h"
+// clang-format off
 #define PY_SSIZE_T_CLEAN
 #include <Python.h>
+#include "pandas/vendored/ujson/lib/ultrajson.h"
+// clang-format on
 
 static int Object_objectAddKey(void *Py_UNUSED(prv), JSOBJ obj, JSOBJ name,
                                JSOBJ value) {

pandas/_libs/tslibs/nattype.pyx

@@ -500,6 +500,8 @@ class NaTType(_NaT):
         --------
         to_timedelta : Convert argument to timedelta.
         Timedelta : Represents a duration, the difference between two dates or times.
+        Timedelta.seconds : Returns the seconds component of the timedelta.
+        Timedelta.microseconds : Returns the microseconds component of the timedelta.
 
         Examples
         --------

pandas/_libs/tslibs/np_datetime.pyx

@@ -176,6 +176,15 @@ class OutOfBoundsDatetime(ValueError):
     """
     Raised when the datetime is outside the range that can be represented.
 
+    This error occurs when attempting to convert or parse a datetime value
+    that exceeds the bounds supported by pandas' internal datetime
+    representation.
+
+    See Also
+    --------
+    to_datetime : Convert argument to datetime.
+    Timestamp : Pandas replacement for python ``datetime.datetime`` object.
+
     Examples
     --------
     >>> pd.to_datetime("08335394550")

pandas/_libs/tslibs/timedeltas.pyx

@@ -1196,6 +1196,8 @@ cdef class _Timedelta(timedelta):
         --------
         to_timedelta : Convert argument to timedelta.
         Timedelta : Represents a duration, the difference between two dates or times.
+        Timedelta.seconds : Returns the seconds component of the timedelta.
+        Timedelta.microseconds : Returns the microseconds component of the timedelta.
 
         Examples
         --------
@@ -1493,6 +1495,7 @@ cdef class _Timedelta(timedelta):
 
         See Also
         --------
+        Timedelta.asm8 : Return a numpy timedelta64 array scalar view.
         numpy.ndarray.view : Returns a view of an array with the same data.
         Timedelta.to_numpy : Converts the Timedelta to a NumPy timedelta64.
         Timedelta.total_seconds : Returns the total duration of the Timedelta

pandas/core/arrays/timedeltas.py

@@ -790,6 +790,19 @@ def to_pytimedelta(self) -> npt.NDArray[np.object_]:
         Returns
         -------
         numpy.ndarray
+            A NumPy ``timedelta64`` object representing the same duration as the
+            original pandas ``Timedelta`` object. The precision of the resulting
+            object is in nanoseconds, which is the default
+            time resolution used by pandas for ``Timedelta`` objects, ensuring
+            high precision for time-based calculations.
+
+        See Also
+        --------
+        to_timedelta : Convert argument to timedelta format.
+        Timedelta : Represents a duration between two dates or times.
+        DatetimeIndex: Index of datetime64 data.
+        Timedelta.components : Return a components namedtuple-like
+                               of a single timedelta.
 
         Examples
         --------
@@ -800,6 +813,14 @@ def to_pytimedelta(self) -> npt.NDArray[np.object_]:
         >>> tdelta_idx.to_pytimedelta()
         array([datetime.timedelta(days=1), datetime.timedelta(days=2),
                datetime.timedelta(days=3)], dtype=object)
+
+        >>> tidx = pd.TimedeltaIndex(data=["1 days 02:30:45", "3 days 04:15:10"])
+        >>> tidx
+        TimedeltaIndex(['1 days 02:30:45', '3 days 04:15:10'],
+               dtype='timedelta64[ns]', freq=None)
+        >>> tidx.to_pytimedelta()
+        array([datetime.timedelta(days=1, seconds=9045),
+                datetime.timedelta(days=3, seconds=15310)], dtype=object)
         """
         return ints_to_pytimedelta(self._ndarray)
 

pandas/core/dtypes/inference.py

@@ -113,13 +113,24 @@ def is_file_like(obj: object) -> bool:
 
     Parameters
     ----------
-    obj : The object to check
+    obj : object
+        The object to check for file-like properties.
+        This can be any Python object, and the function will
+        check if it has attributes typically associated with
+        file-like objects (e.g., `read`, `write`, `__iter__`).
 
     Returns
     -------
     bool
         Whether `obj` has file-like properties.
 
+    See Also
+    --------
+    api.types.is_dict_like : Check if the object is dict-like.
+    api.types.is_hashable : Return True if hash(obj) will succeed, False otherwise.
+    api.types.is_named_tuple : Check if the object is a named tuple.
+    api.types.is_iterator : Check if the object is an iterator.
+
     Examples
     --------
     >>> import io
@@ -142,13 +153,24 @@ def is_re(obj: object) -> TypeGuard[Pattern]:
 
     Parameters
     ----------
-    obj : The object to check
+    obj : object
+        The object to check for being a regex pattern. Typically,
+        this would be an object that you expect to be a compiled
+        pattern from the `re` module.
 
     Returns
     -------
     bool
         Whether `obj` is a regex pattern.
 
+    See Also
+    --------
+    api.types.is_float : Return True if given object is float.
+    api.types.is_iterator : Check if the object is an iterator.
+    api.types.is_integer : Return True if given object is integer.
+    api.types.is_re_compilable : Check if the object can be compiled
+                                into a regex pattern instance.
+
     Examples
     --------
     >>> from pandas.api.types import is_re
@@ -275,13 +297,22 @@ def is_dict_like(obj: object) -> bool:
 
     Parameters
     ----------
-    obj : The object to check
+    obj : object
+        The object to check. This can be any Python object,
+        and the function will determine whether it
+        behaves like a dictionary.
 
     Returns
     -------
     bool
         Whether `obj` has dict-like properties.
 
+    See Also
+    --------
+    api.types.is_list_like : Check if the object is list-like.
+    api.types.is_file_like : Check if the object is a file-like.
+    api.types.is_named_tuple : Check if the object is a named tuple.
+
     Examples
     --------
     >>> from pandas.api.types import is_dict_like
@@ -308,13 +339,22 @@ def is_named_tuple(obj: object) -> bool:
 
     Parameters
     ----------
-    obj : The object to check
+    obj : object
+        The object that will be checked to determine
+        whether it is a named tuple.
 
     Returns
     -------
     bool
         Whether `obj` is a named tuple.
 
+    See Also
+    --------
+    api.types.is_dict_like: Check if the object is dict-like.
+    api.types.is_hashable: Return True if hash(obj)
+                                  will succeed, False otherwise.
+    api.types.is_categorical_dtype : Check if the dtype is categorical.
+
     Examples
     --------
     >>> from collections import namedtuple
@@ -340,9 +380,24 @@ def is_hashable(obj: object) -> TypeGuard[Hashable]:
     Distinguish between these and other types by trying the call to hash() and
     seeing if they raise TypeError.
 
+    Parameters
+    ----------
+    obj : object
+        The object to check for hashability. Any Python object can be passed here.
+
     Returns
     -------
     bool
+        True if object can be hashed (i.e., does not raise TypeError when
+        passed to hash()), and False otherwise (e.g., if object is mutable
+        like a list or dictionary).
+
+    See Also
+    --------
+    api.types.is_float : Return True if given object is float.
+    api.types.is_iterator : Check if the object is an iterator.
+    api.types.is_list_like : Check if the object is list-like.
+    api.types.is_dict_like : Check if the object is dict-like.
 
     Examples
     --------