Merge branch 'fix-agg-with-one-element-fuc-list-given-arg-kwagrs' of https://github.com/luke396/pandas into fix-agg-with-one-element-fuc-list-given-arg-kwagrs

Author: luke

.github/ISSUE_TEMPLATE/bug_report.yaml

@@ -17,9 +17,7 @@ body:
             [latest version](https://pandas.pydata.org/docs/whatsnew/index.html) of pandas.
           required: true
         - label: >
-            I have confirmed this bug exists on the [main branch]
-            (https://pandas.pydata.org/docs/dev/getting_started/install.html#installing-the-development-version-of-pandas)
-            of pandas.
+            I have confirmed this bug exists on the main branch of pandas.
   - type: textarea
     id: example
     attributes:

.github/workflows/python-dev.yml

@@ -73,7 +73,7 @@ jobs:
       run: |
         python --version
         python -m pip install --upgrade pip setuptools wheel
-        python -m pip install --pre --extra-index-url https://pypi.anaconda.org/scipy-wheels-nightly/simple numpy
+        python -m pip install --extra-index-url https://pypi.anaconda.org/scipy-wheels-nightly/simple numpy
         python -m pip install git+https://github.com/nedbat/coveragepy.git
         python -m pip install versioneer[toml]
         python -m pip install python-dateutil pytz cython hypothesis>=6.34.2 pytest>=7.0.0 pytest-xdist>=2.2.0 pytest-cov pytest-asyncio>=0.17

doc/source/getting_started/install.rst

@@ -201,22 +201,6 @@ Installing from source
 
 See the :ref:`contributing guide <contributing>` for complete instructions on building from the git source tree. Further, see :ref:`creating a development environment <contributing_environment>` if you wish to create a pandas development environment.
 
-Installing the development version of pandas
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-
-Installing a nightly build is the quickest way to:
-
-* Try a new feature that will be shipped in the next release (that is, a feature from a pull-request that was recently merged to the main branch).
-* Check whether a bug you encountered has been fixed since the last release.
-
-You can install the nightly build of pandas using the scipy-wheels-nightly index from the PyPI registry of anaconda.org with the following command::
-
-    pip install --pre --extra-index https://pypi.anaconda.org/scipy-wheels-nightly/simple pandas
-
-Note that first uninstalling pandas might be required to be able to install nightly builds::
-
-    pip uninstall pandas -y
-
 Running the test suite
 ----------------------
 

doc/source/whatsnew/v2.0.0.rst

@@ -83,44 +83,34 @@ be set to ``"pyarrow"`` to return pyarrow-backed, nullable :class:`ArrowDtype` (
         df_pyarrow = pd.read_csv(data, use_nullable_dtypes=True, engine="pyarrow")
     df_pyarrow.dtypes
 
-Copy-on-Write improvements
+Copy on write improvements
 ^^^^^^^^^^^^^^^^^^^^^^^^^^
 
-- A new lazy copy mechanism that defers the copy until the object in question is modified
-  was added to the following methods:
-
-  - :meth:`DataFrame.reset_index` / :meth:`Series.reset_index`
-  - :meth:`DataFrame.set_index` / :meth:`Series.set_index`
-  - :meth:`DataFrame.set_axis` / :meth:`Series.set_axis`
-  - :meth:`DataFrame.rename_axis` / :meth:`Series.rename_axis`
-  - :meth:`DataFrame.rename_columns`
-  - :meth:`DataFrame.reindex` / :meth:`Series.reindex`
-  - :meth:`DataFrame.reindex_like` / :meth:`Series.reindex_like`
-  - :meth:`DataFrame.assign`
-  - :meth:`DataFrame.drop`
-  - :meth:`DataFrame.dropna` / :meth:`Series.dropna`
-  - :meth:`DataFrame.select_dtypes`
-  - :meth:`DataFrame.align` / :meth:`Series.align`
-  - :meth:`Series.to_frame`
-  - :meth:`DataFrame.rename` / :meth:`Series.rename`
-  - :meth:`DataFrame.add_prefix` / :meth:`Series.add_prefix`
-  - :meth:`DataFrame.add_suffix` / :meth:`Series.add_suffix`
-  - :meth:`DataFrame.drop_duplicates` / :meth:`Series.drop_duplicates`
-  - :meth:`DataFrame.reorder_levels` / :meth:`Series.reorder_levels`
-
-  These methods return views when Copy-on-Write is enabled, which provides a significant
-  performance improvement compared to the regular execution (:issue:`49473`).
-
-- Accessing a single column of a DataFrame as a Series (e.g. ``df["col"]``) now always
-  returns a new object every time it is constructed when Copy-on-Write is enabled (not
-  returning multiple times an identical, cached Series object). This ensures that those
-  Series objects correctly follow the Copy-on-Write rules (:issue:`49450`)
-
-- The :class:`Series` constructor will now create a lazy copy (deferring the copy until
-  a modification to the data happens) when constructing a Series from an existing
-  Series with the default of ``copy=False`` (:issue:`50471`)
-
-Copy-on-Write can be enabled through
+A new lazy copy mechanism that defers the copy until the object in question is modified
+was added to the following methods:
+
+- :meth:`DataFrame.reset_index` / :meth:`Series.reset_index`
+- :meth:`DataFrame.set_index` / :meth:`Series.set_index`
+- :meth:`DataFrame.set_axis` / :meth:`Series.set_axis`
+- :meth:`DataFrame.rename_axis` / :meth:`Series.rename_axis`
+- :meth:`DataFrame.rename_columns`
+- :meth:`DataFrame.reindex` / :meth:`Series.reindex`
+- :meth:`DataFrame.reindex_like` / :meth:`Series.reindex_like`
+- :meth:`DataFrame.assign`
+- :meth:`DataFrame.drop`
+- :meth:`DataFrame.dropna` / :meth:`Series.dropna`
+- :meth:`DataFrame.select_dtypes`
+- :meth:`DataFrame.align` / :meth:`Series.align`
+- :meth:`Series.to_frame`
+- :meth:`DataFrame.rename` / :meth:`Series.rename`
+- :meth:`DataFrame.add_prefix` / :meth:`Series.add_prefix`
+- :meth:`DataFrame.add_suffix` / :meth:`Series.add_suffix`
+- :meth:`DataFrame.drop_duplicates` / :meth:`Series.drop_duplicates`
+- :meth:`DataFrame.reorder_levels` / :meth:`Series.reorder_levels`
+
+These methods return views when copy on write is enabled, which provides a significant
+performance improvement compared to the regular execution (:issue:`49473`). Copy on write
+can be enabled through
 
 .. code-block:: python
 
@@ -573,7 +563,8 @@ Deprecations
 ~~~~~~~~~~~~
 - Deprecated argument ``infer_datetime_format`` in :func:`to_datetime` and :func:`read_csv`, as a strict version of it is now the default (:issue:`48621`)
 - Deprecated :func:`pandas.io.sql.execute`(:issue:`50185`)
-- :meth:`Index.is_integer` has been deprecated. Use :func:`pandas.api.types.is_integer_dtype` instead (:issue:`50042`)
+-
+
 - :meth:`Index.is_floating` has been deprecated. Use :func:`pandas.api.types.is_float_dtype` instead (:issue:`50042`)
 
 .. ---------------------------------------------------------------------------
@@ -918,8 +909,6 @@ Timezones
 - Bug in :meth:`Series.astype` and :meth:`DataFrame.astype` with object-dtype containing multiple timezone-aware ``datetime`` objects with heterogeneous timezones to a :class:`DatetimeTZDtype` incorrectly raising (:issue:`32581`)
 - Bug in :func:`to_datetime` was failing to parse date strings with timezone name when ``format`` was specified with ``%Z`` (:issue:`49748`)
 - Better error message when passing invalid values to ``ambiguous`` parameter in :meth:`Timestamp.tz_localize` (:issue:`49565`)
-- Bug in string parsing incorrectly allowing a :class:`Timestamp` to be constructed with an invalid timezone, which would raise when trying to print (:issue:`50668`)
--
 
 Numeric
 ^^^^^^^
@@ -958,7 +947,6 @@ Indexing
 - Bug in :meth:`DataFrame.__setitem__` raising when indexer is a :class:`DataFrame` with ``boolean`` dtype (:issue:`47125`)
 - Bug in :meth:`DataFrame.reindex` filling with wrong values when indexing columns and index for ``uint`` dtypes (:issue:`48184`)
 - Bug in :meth:`DataFrame.loc` when setting :class:`DataFrame` with different dtypes coercing values to single dtype (:issue:`50467`)
-- Bug in :meth:`DataFrame.sort_values` where ``None`` was not returned when ``by`` is empty list and ``inplace=True`` (:issue:`50643`)
 - Bug in :meth:`DataFrame.loc` coercing dtypes when setting values with a list indexer (:issue:`49159`)
 - Bug in :meth:`Series.loc` raising error for out of bounds end of slice indexer (:issue:`50161`)
 - Bug in :meth:`DataFrame.loc` raising ``ValueError`` with ``bool`` indexer and :class:`MultiIndex` (:issue:`47687`)

pandas/_libs/tslib.pyx

@@ -770,15 +770,6 @@ cdef _array_to_datetime_object(
                 oresult[i] = "NaT"
                 cnp.PyArray_MultiIter_NEXT(mi)
                 continue
-            elif val == "now":
-                oresult[i] = datetime.now()
-                cnp.PyArray_MultiIter_NEXT(mi)
-                continue
-            elif val == "today":
-                oresult[i] = datetime.today()
-                cnp.PyArray_MultiIter_NEXT(mi)
-                continue
-
             try:
                 oresult[i] = parse_datetime_string(val, dayfirst=dayfirst,
                                                    yearfirst=yearfirst)

pandas/_libs/tslibs/parsing.pyi

@@ -2,6 +2,7 @@ from datetime import datetime
 
 import numpy as np
 
+from pandas._libs.tslibs.offsets import BaseOffset
 from pandas._typing import npt
 
 class DateParseError(ValueError): ...
@@ -11,9 +12,9 @@ def parse_datetime_string(
     dayfirst: bool = ...,
     yearfirst: bool = ...,
 ) -> datetime: ...
-def parse_datetime_string_with_reso(
-    date_string: str,
-    freq: str | None = ...,
+def parse_time_string(
+    arg: str,
+    freq: BaseOffset | str | None = ...,
     dayfirst: bool | None = ...,
     yearfirst: bool | None = ...,
 ) -> tuple[datetime, str]: ...

pandas/_libs/tslibs/parsing.pyx

@@ -59,6 +59,7 @@ from pandas._libs.tslibs.np_datetime cimport (
     npy_datetimestruct,
     string_to_dts,
 )
+from pandas._libs.tslibs.offsets cimport is_offset_object
 from pandas._libs.tslibs.strptime import array_strptime
 from pandas._libs.tslibs.util cimport (
     get_c_string_buf_and_size,
@@ -256,10 +257,6 @@ def parse_datetime_string(
     Returns
     -------
     datetime
-
-    Notes
-    -----
-    Does not handle "today" or "now", which caller is responsible for handling.
     """
 
     cdef:
@@ -278,6 +275,14 @@ def parse_datetime_string(
     if dt is not None:
         return dt
 
+    # Handling special case strings today & now
+    if date_string == "now":
+        dt = datetime.now()
+        return dt
+    elif date_string == "today":
+        dt = datetime.today()
+        return dt
+
     try:
         dt, _ = _parse_dateabbr_string(date_string, _DEFAULT_DATETIME, freq=None)
         return dt
@@ -299,39 +304,20 @@ def parse_datetime_string(
         raise OutOfBoundsDatetime(
             f'Parsing "{date_string}" to datetime overflows'
             ) from err
-    if dt.tzinfo is not None:
-        # dateutil can return a datetime with a tzoffset outside of (-24H, 24H)
-        #  bounds, which is invalid (can be constructed, but raises if we call
-        #  str(dt)).  Check that and raise here if necessary.
-        try:
-            dt.utcoffset()
-        except ValueError as err:
-            # offset must be a timedelta strictly between -timedelta(hours=24)
-            #  and timedelta(hours=24)
-            raise ValueError(
-                f'Parsed string "{date_string}" gives an invalid tzoffset, '
-                "which must be between -timedelta(hours=24) and timedelta(hours=24)"
-            )
 
     return dt
 
 
-def parse_datetime_string_with_reso(
-    str date_string, str freq=None, dayfirst=None, yearfirst=None
-):
-    # NB: This will break with np.str_ (GH#45580) even though
-    #  isinstance(npstrobj, str) evaluates to True, so caller must ensure
-    #  the argument is *exactly* 'str'
+def parse_time_string(arg, freq=None, dayfirst=None, yearfirst=None):
     """
     Try hard to parse datetime string, leveraging dateutil plus some extra
     goodies like quarter recognition.
 
     Parameters
     ----------
-    date_string : str
-    freq : str or None, default None
+    arg : str
+    freq : str or DateOffset, default None
         Helps with interpreting time string if supplied
-        Corresponds to `offset.rule_code`
     dayfirst : bool, default None
         If None uses default from print_config
     yearfirst : bool, default None
@@ -342,21 +328,50 @@ def parse_datetime_string_with_reso(
     datetime
     str
         Describing resolution of parsed string.
-
-    Raises
-    ------
-    ValueError : preliminary check suggests string is not datetime
-    DateParseError : error within dateutil
     """
+    if type(arg) is not str:
+        # GH#45580 np.str_ satisfies isinstance(obj, str) but if we annotate
+        #  arg as "str" this raises here
+        if not isinstance(arg, np.str_):
+            raise TypeError(
+                "Argument 'arg' has incorrect type "
+                f"(expected str, got {type(arg).__name__})"
+            )
+        arg = str(arg)
+
+    if is_offset_object(freq):
+        freq = freq.rule_code
 
     if dayfirst is None:
         dayfirst = get_option("display.date_dayfirst")
     if yearfirst is None:
         yearfirst = get_option("display.date_yearfirst")
 
+    res = parse_datetime_string_with_reso(arg, freq=freq,
+                                          dayfirst=dayfirst,
+                                          yearfirst=yearfirst)
+    return res
+
+
+cdef parse_datetime_string_with_reso(
+    str date_string, str freq=None, bint dayfirst=False, bint yearfirst=False,
+):
+    """
+    Parse datetime string and try to identify its resolution.
+
+    Returns
+    -------
+    datetime
+    str
+        Inferred resolution of the parsed string.
+
+    Raises
+    ------
+    ValueError : preliminary check suggests string is not datetime
+    DateParseError : error within dateutil
+    """
     cdef:
-        datetime parsed
-        str reso
+        object parsed, reso
         bint string_to_dts_failed
         npy_datetimestruct dts
         NPY_DATETIMEUNIT out_bestunit
@@ -468,7 +483,7 @@ cpdef bint _does_string_look_like_datetime(str py_string):
 cdef object _parse_dateabbr_string(object date_string, datetime default,
                                    str freq=None):
     cdef:
-        datetime ret
+        object ret
         # year initialized to prevent compiler warnings
         int year = -1, quarter = -1, month
         Py_ssize_t date_len
@@ -490,8 +505,8 @@ cdef object _parse_dateabbr_string(object date_string, datetime default,
         except ValueError:
             pass
 
-    if 4 <= date_len <= 7:
-        try:
+    try:
+        if 4 <= date_len <= 7:
             i = date_string.index("Q", 1, 6)
             if i == 1:
                 quarter = int(date_string[0])
@@ -538,21 +553,19 @@ cdef object _parse_dateabbr_string(object date_string, datetime default,
             ret = default.replace(year=year, month=month)
             return ret, "quarter"
 
-        except DateParseError:
-            raise
-        except ValueError:
-            # e.g. if "Q" is not in date_string and .index raised
-            pass
+    except DateParseError:
+        raise
+    except ValueError:
+        pass
 
     if date_len == 6 and freq == "M":
         year = int(date_string[:4])
         month = int(date_string[4:6])
         try:
             ret = default.replace(year=year, month=month)
             return ret, "month"
-        except ValueError as err:
-            # We can infer that none of the patterns below will match
-            raise ValueError(f"Unable to parse {date_string}") from err
+        except ValueError:
+            pass
 
     for pat in ["%Y-%m", "%b %Y", "%b-%Y"]:
         try:

pandas/_libs/tslibs/period.pyx

@@ -88,7 +88,7 @@ from pandas._libs.tslibs.dtypes cimport (
 )
 from pandas._libs.tslibs.parsing cimport quarter_to_myear
 
-from pandas._libs.tslibs.parsing import parse_datetime_string_with_reso
+from pandas._libs.tslibs.parsing import parse_time_string
 
 from pandas._libs.tslibs.nattype cimport (
     NPY_NAT,
@@ -2589,9 +2589,7 @@ class Period(_Period):
 
                 value = str(value)
             value = value.upper()
-
-            freqstr = freq.rule_code if freq is not None else None
-            dt, reso = parse_datetime_string_with_reso(value, freqstr)
+            dt, reso = parse_time_string(value, freq)
             try:
                 ts = Timestamp(value)
             except ValueError:

pandas/_testing/asserters.py

@@ -15,7 +15,6 @@
     is_bool,
     is_categorical_dtype,
     is_extension_array_dtype,
-    is_integer_dtype,
     is_interval_dtype,
     is_number,
     is_numeric_dtype,
@@ -1336,7 +1335,7 @@ def assert_indexing_slices_equivalent(ser: Series, l_slc: slice, i_slc: slice) -
 
     assert_series_equal(ser.loc[l_slc], expected)
 
-    if not is_integer_dtype(ser.index):
+    if not ser.index.is_integer():
         # For integer indices, .loc and plain getitem are position-based.
         assert_series_equal(ser[l_slc], expected)