Merge branch 'main' into bug-factorize

Author: jbrockmendel

ci/code_checks.sh

@@ -161,7 +161,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Series.str.zfill RT03" \
         -i "pandas.Series.struct.dtypes SA01" \
         -i "pandas.Series.to_markdown SA01" \
-        -i "pandas.Series.update PR07,SA01" \
         -i "pandas.Timedelta.asm8 SA01" \
         -i "pandas.Timedelta.ceil SA01" \
         -i "pandas.Timedelta.components SA01" \
@@ -191,9 +190,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Timestamp.nanosecond GL08" \
         -i "pandas.Timestamp.resolution PR02" \
         -i "pandas.Timestamp.second GL08" \
-        -i "pandas.Timestamp.strptime PR01,SA01" \
-        -i "pandas.Timestamp.timetz SA01" \
-        -i "pandas.Timestamp.to_datetime64 SA01" \
         -i "pandas.Timestamp.tzinfo GL08" \
         -i "pandas.Timestamp.value GL08" \
         -i "pandas.Timestamp.year GL08" \

doc/source/whatsnew/v3.0.0.rst

@@ -31,6 +31,7 @@ Other enhancements
 - :class:`pandas.api.typing.FrozenList` is available for typing the outputs of :attr:`MultiIndex.names`, :attr:`MultiIndex.codes` and :attr:`MultiIndex.levels` (:issue:`58237`)
 - :class:`pandas.api.typing.SASReader` is available for typing the output of :func:`read_sas` (:issue:`55689`)
 - :func:`DataFrame.to_excel` now raises an ``UserWarning`` when the character count in a cell exceeds Excel's limitation of 32767 characters (:issue:`56954`)
+- :func:`pandas.merge` now validates the ``how`` parameter input (merge type) (:issue:`59435`)
 - :func:`read_stata` now returns ``datetime64`` resolutions better matching those natively stored in the stata format (:issue:`55642`)
 - :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`)
@@ -632,6 +633,7 @@ Period
 Plotting
 ^^^^^^^^
 - Bug in :meth:`.DataFrameGroupBy.boxplot` failed when there were multiple groupings (:issue:`14701`)
+- Bug in :meth:`DataFrame.plot.line` raising ``ValueError`` when set both color and a ``dict`` style (:issue:`59461`)
 - Bug in :meth:`DataFrame.plot` that causes a shift to the right when the frequency multiplier is greater than one. (:issue:`57587`)
 - Bug in :meth:`Series.plot` with ``kind="pie"`` with :class:`ArrowDtype` (:issue:`59192`)
 
@@ -650,6 +652,7 @@ Groupby/resample/rolling
 - Bug in :meth:`DataFrameGroupBy.cumsum` where it did not return the correct dtype when the label contained ``None``. (:issue:`58811`)
 - Bug in :meth:`DataFrameGroupby.transform` and :meth:`SeriesGroupby.transform` with a reducer and ``observed=False`` that coerces dtype to float when there are unobserved categories. (:issue:`55326`)
 - Bug in :meth:`Rolling.apply` where the applied function could be called on fewer than ``min_period`` periods if ``method="table"``. (:issue:`58868`)
+- Bug in :meth:`Series.resample` could raise when the the date range ended shortly before a non-existent time. (:issue:`58380`)
 
 Reshaping
 ^^^^^^^^^

pandas/_libs/lib.pyx

@@ -2699,16 +2699,16 @@ def maybe_convert_objects(ndarray[object] objects,
         seen.object_ = True
 
     elif seen.str_:
-        if using_string_dtype() and is_string_array(objects, skipna=True):
+        if convert_to_nullable_dtype and is_string_array(objects, skipna=True):
             from pandas.core.arrays.string_ import StringDtype
 
-            dtype = StringDtype(na_value=np.nan)
+            dtype = StringDtype()
             return dtype.construct_array_type()._from_sequence(objects, dtype=dtype)
 
-        elif convert_to_nullable_dtype and is_string_array(objects, skipna=True):
+        elif using_string_dtype() and is_string_array(objects, skipna=True):
             from pandas.core.arrays.string_ import StringDtype
 
-            dtype = StringDtype()
+            dtype = StringDtype(na_value=np.nan)
             return dtype.construct_array_type()._from_sequence(objects, dtype=dtype)
 
         seen.object_ = True

pandas/_libs/tslibs/nattype.pyx

@@ -229,7 +229,17 @@ cdef class _NaT(datetime):
 
     def to_datetime64(self) -> np.datetime64:
         """
-        Return a numpy.datetime64 object with same precision.
+        Return a NumPy datetime64 object with same precision.
+
+        This method returns a numpy.datetime64 object with the same
+        date and time information and precision as the pd.Timestamp object.
+
+        See Also
+        --------
+        numpy.datetime64 : Class to represent dates and times with high precision.
+        Timestamp.to_numpy : Alias for this method.
+        Timestamp.asm8 : Alias for this method.
+        pd.to_datetime : Convert argument to datetime.
 
         Examples
         --------
@@ -764,6 +774,19 @@ class NaTType(_NaT):
         """
         Return time object with same time and tzinfo.
 
+        This method returns a datetime.time object with
+        the time and tzinfo corresponding to the pd.Timestamp
+        object, ignoring any information about the day/date.
+
+        See Also
+        --------
+        datetime.datetime.timetz : Return datetime.time object with the
+            same time attributes as the datetime object.
+        datetime.time : Class to represent the time of day, independent
+            of any particular day.
+        datetime.datetime.tzinfo : Attribute of datetime.datetime objects
+            representing the timezone of the datetime object.
+
         Examples
         --------
         >>> ts = pd.Timestamp('2023-01-01 10:00:00', tz='Europe/Brussels')
@@ -860,9 +883,27 @@ class NaTType(_NaT):
     strptime = _make_error_func(
         "strptime",
         """
-        Timestamp.strptime(string, format)
+        Convert string argument to datetime.
 
-        Function is not implemented. Use pd.to_datetime().
+        This method is not implemented; calling it will raise NotImplementedError.
+        Use pd.to_datetime() instead.
+
+        Parameters
+        ----------
+        date_string : str
+            String to convert to a datetime.
+        format : str, default None
+            The format string to parse time, e.g. "%d/%m/%Y".
+
+        See Also
+        --------
+        pd.to_datetime : Convert argument to datetime.
+        datetime.datetime.strptime : Return a datetime corresponding to a string
+            representing a date and time, parsed according to a separate
+            format string.
+        datetime.datetime.strftime : Return a string representing the date and
+            time, controlled by an explicit format string.
+        Timestamp.isoformat : Return the time formatted according to ISO 8601.
 
         Examples
         --------

pandas/_libs/tslibs/timestamps.pyx

@@ -1342,7 +1342,17 @@ cdef class _Timestamp(ABCTimestamp):
 
     cpdef to_datetime64(self):
         """
-        Return a numpy.datetime64 object with same precision.
+        Return a NumPy datetime64 object with same precision.
+
+        This method returns a numpy.datetime64 object with the same
+        date and time information and precision as the pd.Timestamp object.
+
+        See Also
+        --------
+        numpy.datetime64 : Class to represent dates and times with high precision.
+        Timestamp.to_numpy : Alias for this method.
+        Timestamp.asm8 : Alias for this method.
+        pd.to_datetime : Convert argument to datetime.
 
         Examples
         --------
@@ -2093,6 +2103,19 @@ class Timestamp(_Timestamp):
         """
         Return time object with same time and tzinfo.
 
+        This method returns a datetime.time object with
+        the time and tzinfo corresponding to the pd.Timestamp
+        object, ignoring any information about the day/date.
+
+        See Also
+        --------
+        datetime.datetime.timetz : Return datetime.time object with the
+            same time attributes as the datetime object.
+        datetime.time : Class to represent the time of day, independent
+            of any particular day.
+        datetime.datetime.tzinfo : Attribute of datetime.datetime objects
+            representing the timezone of the datetime object.
+
         Examples
         --------
         >>> ts = pd.Timestamp('2023-01-01 10:00:00', tz='Europe/Brussels')
@@ -2141,9 +2164,27 @@ class Timestamp(_Timestamp):
     @classmethod
     def strptime(cls, date_string, format):
         """
-        Timestamp.strptime(string, format)
+        Convert string argument to datetime.
 
-        Function is not implemented. Use pd.to_datetime().
+        This method is not implemented; calling it will raise NotImplementedError.
+        Use pd.to_datetime() instead.
+
+        Parameters
+        ----------
+        date_string : str
+            String to convert to a datetime.
+        format : str, default None
+            The format string to parse time, e.g. "%d/%m/%Y".
+
+        See Also
+        --------
+        pd.to_datetime : Convert argument to datetime.
+        datetime.datetime.strptime : Return a datetime corresponding to a string
+            representing a date and time, parsed according to a separate
+            format string.
+        datetime.datetime.strftime : Return a string representing the date and
+            time, controlled by an explicit format string.
+        Timestamp.isoformat : Return the time formatted according to ISO 8601.
 
         Examples
         --------
@@ -3073,7 +3114,8 @@ default 'raise'
         """
         Convert TimeStamp to a Julian Date.
 
-        0 Julian date is noon January 1, 4713 BC.
+        This method returns the number of days as a float since
+        0 Julian date, which is noon January 1, 4713 BC.
 
         See Also
         --------

pandas/core/generic.py

@@ -600,9 +600,10 @@ def _get_cleaned_column_resolvers(self) -> dict[Hashable, Series]:
         if isinstance(self, ABCSeries):
             return {clean_column_name(self.name): self}
 
+        dtypes = self.dtypes
         return {
             clean_column_name(k): Series(
-                v, copy=False, index=self.index, name=k, dtype=self.dtypes[k]
+                v, copy=False, index=self.index, name=k, dtype=dtypes[k]
             ).__finalize__(self)
             for k, v in zip(self.columns, self._iter_column_arrays())
             if not isinstance(k, int)
@@ -7486,9 +7487,13 @@ def replace(
                 if inplace:
                     return None
                 return self.copy(deep=False)
-
             if is_dict_like(to_replace):
                 if is_dict_like(value):  # {'A' : NA} -> {'A' : 0}
+                    if isinstance(self, ABCSeries):
+                        raise ValueError(
+                            "to_replace and value cannot be dict-like for "
+                            "Series.replace"
+                        )
                     # Note: Checking below for `in foo.keys()` instead of
                     #  `in foo` is needed for when we have a Series and not dict
                     mapping = {

pandas/core/resample.py

@@ -2466,7 +2466,7 @@ def _get_timestamp_range_edges(
         )
         if isinstance(freq, Day):
             first = first.tz_localize(index_tz)
-            last = last.tz_localize(index_tz)
+            last = last.tz_localize(index_tz, nonexistent="shift_forward")
     else:
         first = first.normalize()
         last = last.normalize()

pandas/core/reshape/merge.py

@@ -982,6 +982,14 @@ def __init__(
             )
             raise MergeError(msg)
 
+        # GH 59435: raise when "how" is not a valid Merge type
+        merge_type = {"left", "right", "inner", "outer", "cross", "asof"}
+        if how not in merge_type:
+            raise ValueError(
+                f"'{how}' is not a valid Merge type: "
+                f"left, right, inner, outer, cross, asof"
+            )
+
         self.left_on, self.right_on = self._validate_left_right_on(left_on, right_on)
 
         (

pandas/core/series.py

@@ -3211,6 +3211,13 @@ def update(self, other: Series | Sequence | Mapping) -> None:
         Parameters
         ----------
         other : Series, or object coercible into Series
+            Other Series that provides values to update the current Series.
+
+        See Also
+        --------
+        Series.combine : Perform element-wise operation on two Series
+            using a given function.
+        Series.transform: Modify a Series using a function.
 
         Examples
         --------

pandas/io/_util.py

@@ -27,6 +27,8 @@ def _arrow_dtype_mapping() -> dict:
         pa.string(): pd.StringDtype(),
         pa.float32(): pd.Float32Dtype(),
         pa.float64(): pd.Float64Dtype(),
+        pa.string(): pd.StringDtype(),
+        pa.large_string(): pd.StringDtype(),
     }