Merge branch 'main' into lock-block-values-refs

Author: lysnikolaou

.circleci/config.yml

@@ -61,7 +61,6 @@ pandas/_version.py export-subst
 *.pxi export-ignore
 
 # Ignoring stuff from the top level
-.circleci export-ignore
 .github export-ignore
 asv_bench export-ignore
 ci export-ignore

.gitattributes

@@ -146,15 +146,13 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.tseries.offsets.CustomBusinessMonthBegin PR02" \
         -i "pandas.tseries.offsets.CustomBusinessMonthBegin.calendar GL08" \
         -i "pandas.tseries.offsets.CustomBusinessMonthBegin.holidays GL08" \
-        -i "pandas.tseries.offsets.CustomBusinessMonthBegin.is_on_offset SA01" \
         -i "pandas.tseries.offsets.CustomBusinessMonthBegin.m_offset GL08" \
         -i "pandas.tseries.offsets.CustomBusinessMonthBegin.n GL08" \
         -i "pandas.tseries.offsets.CustomBusinessMonthBegin.normalize GL08" \
         -i "pandas.tseries.offsets.CustomBusinessMonthBegin.weekmask GL08" \
         -i "pandas.tseries.offsets.CustomBusinessMonthEnd PR02" \
         -i "pandas.tseries.offsets.CustomBusinessMonthEnd.calendar GL08" \
         -i "pandas.tseries.offsets.CustomBusinessMonthEnd.holidays GL08" \
-        -i "pandas.tseries.offsets.CustomBusinessMonthEnd.is_on_offset SA01" \
         -i "pandas.tseries.offsets.CustomBusinessMonthEnd.m_offset GL08" \
         -i "pandas.tseries.offsets.CustomBusinessMonthEnd.n GL08" \
         -i "pandas.tseries.offsets.CustomBusinessMonthEnd.normalize GL08" \
@@ -191,7 +189,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.tseries.offsets.Hour.is_on_offset GL08" \
         -i "pandas.tseries.offsets.Hour.n GL08" \
         -i "pandas.tseries.offsets.Hour.normalize GL08" \
-        -i "pandas.tseries.offsets.LastWeekOfMonth SA01" \
         -i "pandas.tseries.offsets.LastWeekOfMonth.is_on_offset GL08" \
         -i "pandas.tseries.offsets.LastWeekOfMonth.n GL08" \
         -i "pandas.tseries.offsets.LastWeekOfMonth.normalize GL08" \

ci/code_checks.sh

@@ -112,7 +112,7 @@ Various tutorials
 
 * `Wes McKinney's (pandas BDFL) blog <https://wesmckinney.com/archives.html>`_
 * `Statistical analysis made easy in Python with SciPy and pandas DataFrames, by Randal Olson <http://www.randalolson.com/2012/08/06/statistical-analysis-made-easy-in-python/>`_
-* `Statistical Data Analysis in Python, tutorial videos, by Christopher Fonnesbeck from SciPy 2013 <https://conference.scipy.org/scipy2013/tutorial_detail.php?id=109>`_
+* `Statistical Data Analysis in Python, tutorial by Christopher Fonnesbeck from SciPy 2013 <https://github.com/fonnesbeck/statistical-analysis-python-tutorial>`_
 * `Financial analysis in Python, by Thomas Wiecki <https://nbviewer.org/github/twiecki/financial-analysis-python-tutorial/blob/master/1.%20Pandas%20Basics.ipynb>`_
 * `Intro to pandas data structures, by Greg Reda <http://www.gregreda.com/2013/10/26/intro-to-pandas-data-structures/>`_
 * `Pandas DataFrames Tutorial, by Karlijn Willems <https://www.datacamp.com/community/tutorials/pandas-tutorial-dataframe-python>`_

ci/deps/circle-311-arm64.yaml

@@ -720,11 +720,24 @@ cdef class BaseOffset:
         """
         Return boolean whether a timestamp intersects with this frequency.
 
+        This method determines if a given timestamp aligns with the start
+        of a custom business month, as defined by this offset. It accounts
+        for custom rules, such as skipping weekends or other non-business days,
+        and checks whether the provided datetime falls on a valid business day
+        that marks the beginning of the custom business month.
+
         Parameters
         ----------
         dt : datetime.datetime
             Timestamp to check intersections with frequency.
 
+        See Also
+        --------
+        tseries.offsets.CustomBusinessMonthBegin : Represents the start of a custom
+            business month.
+        tseries.offsets.CustomBusinessMonthEnd : Represents the end of a custom
+            business month.
+
         Examples
         --------
         >>> ts = pd.Timestamp(2022, 1, 1)
@@ -3710,6 +3723,15 @@ cdef class LastWeekOfMonth(WeekOfMonthMixin):
         - 5 is Saturday
         - 6 is Sunday.
 
+    See Also
+    --------
+    tseries.offsets.WeekOfMonth :
+        Date offset for a specific weekday in a month.
+    tseries.offsets.MonthEnd :
+        Date offset for the end of the month.
+    tseries.offsets.BMonthEnd :
+        Date offset for the last business day of the month.
+
     Examples
     --------
     >>> ts = pd.Timestamp(2022, 1, 1)

doc/source/getting_started/tutorials.rst

@@ -1398,7 +1398,7 @@ def _to_datetimearray(self) -> DatetimeArray:
         np_dtype = np.dtype(f"M8[{pa_type.unit}]")
         dtype = tz_to_dtype(pa_type.tz, pa_type.unit)
         np_array = self._pa_array.to_numpy()
-        np_array = np_array.astype(np_dtype)
+        np_array = np_array.astype(np_dtype, copy=False)
         return DatetimeArray._simple_new(np_array, dtype=dtype)
 
     def _to_timedeltaarray(self) -> TimedeltaArray:
@@ -1409,7 +1409,7 @@ def _to_timedeltaarray(self) -> TimedeltaArray:
         assert pa.types.is_duration(pa_type)
         np_dtype = np.dtype(f"m8[{pa_type.unit}]")
         np_array = self._pa_array.to_numpy()
-        np_array = np_array.astype(np_dtype)
+        np_array = np_array.astype(np_dtype, copy=False)
         return TimedeltaArray._simple_new(np_array, dtype=np_dtype)
 
     def _values_for_json(self) -> np.ndarray:

pandas/_libs/tslibs/offsets.pyx

@@ -596,6 +596,8 @@ def sanitize_array(
         # create an extension array from its dtype
         _sanitize_non_ordered(data)
         cls = dtype.construct_array_type()
+        if not hasattr(data, "__array__"):
+            data = list(data)
         subarr = cls._from_sequence(data, dtype=dtype, copy=copy)
 
     # GH#846

pandas/core/arrays/arrow/array.py

@@ -165,7 +165,8 @@ def _finalize_pandas_output(self, frame: DataFrame) -> DataFrame:
                 # The only way self.names is not the same length as number of cols is
                 # if we have int index_col. We should just pad the names(they will get
                 # removed anyways) to expected length then.
-                self.names = list(range(num_cols - len(self.names))) + self.names
+                columns_prefix = [str(x) for x in range(num_cols - len(self.names))]
+                self.names = columns_prefix + self.names
                 multi_index_named = False
             frame.columns = self.names
 

pandas/core/construction.py

@@ -179,3 +179,14 @@ def test_constructor_datetime_nonns(self, constructor):
         arr.flags.writeable = False
         result = constructor(arr)
         tm.assert_equal(result, expected)
+
+    def test_constructor_from_dict_keys(self, constructor, using_infer_string):
+        # https://github.com/pandas-dev/pandas/issues/60343
+        d = {"a": 1, "b": 2}
+        result = constructor(d.keys(), dtype="str")
+        if using_infer_string:
+            assert result.dtype == "str"
+        else:
+            assert result.dtype == "object"
+        expected = constructor(list(d.keys()), dtype="str")
+        tm.assert_equal(result, expected)