Merge remote-tracking branch 'upstream/master' into GH10285

Author: avinashpancham

.github/workflows/autoupdate-pre-commit-config.yml

@@ -0,0 +1,33 @@
+name: "Update pre-commit config"
+
+on:
+  schedule:
+    - cron: "0 7 * * 1" # At 07:00 on each Monday.
+  workflow_dispatch:
+
+jobs:
+  update-pre-commit:
+    if: github.repository_owner == 'pandas-dev'
+    name: Autoupdate pre-commit config
+    runs-on: ubuntu-latest
+    steps:
+      - name: Set up Python
+        uses: actions/setup-python@v2
+      - name: Cache multiple paths
+        uses: actions/cache@v2
+        with:
+          path: |
+            ~/.cache/pre-commit
+            ~/.cache/pip
+          key: pre-commit-autoupdate-${{ runner.os }}-build
+      - name: Update pre-commit config packages
+        uses: technote-space/create-pr-action@v2
+        with:
+          GITHUB_TOKEN: ${{ secrets.ACTION_TRIGGER_TOKEN }}
+          EXECUTE_COMMANDS: |
+            pip install pre-commit
+            pre-commit autoupdate || (exit 0);
+            pre-commit run -a || (exit 0);
+          COMMIT_MESSAGE: "⬆️ UPGRADE: Autoupdate pre-commit config"
+          PR_BRANCH_NAME: "pre-commit-config-update-${PR_ID}"
+          PR_TITLE: "⬆️ UPGRADE: Autoupdate pre-commit config"

.pre-commit-config.yaml

@@ -18,15 +18,15 @@ repos:
         types: [text]
         args: [--append-config=flake8/cython-template.cfg]
 -   repo: https://github.com/PyCQA/isort
-    rev: 5.6.3
+    rev: 5.6.4
     hooks:
     -   id: isort
         name: isort (python)
     -   id: isort
         name: isort (cython)
         types: [cython]
 -   repo: https://github.com/asottile/pyupgrade
-    rev: v2.7.2
+    rev: v2.7.3
     hooks:
     -   id: pyupgrade
         args: [--py37-plus]
@@ -124,7 +124,7 @@ repos:
     hooks:
     -   id: yesqa
 -   repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v3.2.0
+    rev: v3.3.0
     hooks:
     -   id: end-of-file-fixer
         exclude: ^LICENSES/|\.(html|csv|txt|svg|py)$

doc/source/user_guide/timeseries.rst

@@ -879,7 +879,7 @@ into ``freq`` keyword arguments. The available date offsets and associated frequ
     :header: "Date Offset", "Frequency String", "Description"
     :widths: 15, 15, 65
 
-    :class:`~pandas.tseries.offsets.DateOffset`, None, "Generic offset class, defaults to 1 calendar day"
+    :class:`~pandas.tseries.offsets.DateOffset`, None, "Generic offset class, defaults to absolute 24 hours"
     :class:`~pandas.tseries.offsets.BDay` or :class:`~pandas.tseries.offsets.BusinessDay`, ``'B'``,"business day (weekday)"
     :class:`~pandas.tseries.offsets.CDay` or :class:`~pandas.tseries.offsets.CustomBusinessDay`, ``'C'``, "custom business day"
     :class:`~pandas.tseries.offsets.Week`, ``'W'``, "one week, optionally anchored on a day of the week"

doc/source/whatsnew/v1.2.0.rst

@@ -392,6 +392,7 @@ Datetimelike
 - Bug in :meth:`DatetimeIndex.equals` and :meth:`TimedeltaIndex.equals` incorrectly considering ``int64`` indexes as equal (:issue:`36744`)
 - Bug in :meth:`TimedeltaIndex.sum` and :meth:`Series.sum` with ``timedelta64`` dtype on an empty index or series returning ``NaT`` instead of ``Timedelta(0)`` (:issue:`31751`)
 - Bug in :meth:`DatetimeArray.shift` incorrectly allowing ``fill_value`` with a mismatched timezone (:issue:`37299`)
+- Bug in adding a :class:`BusinessDay` with nonzero ``offset`` to a non-scalar other (:issue:`37457`)
 
 Timedelta
 ^^^^^^^^^
@@ -547,6 +548,7 @@ ExtensionArray
 - Fixed bug where ``astype()`` with equal dtype and ``copy=False`` would return a new object (:issue:`284881`)
 - Fixed bug when applying a NumPy ufunc with multiple outputs to a :class:`pandas.arrays.IntegerArray` returning None (:issue:`36913`)
 - Fixed an inconsistency in :class:`PeriodArray`'s ``__init__`` signature to those of :class:`DatetimeArray` and :class:`TimedeltaArray` (:issue:`37289`)
+- Reductions for :class:`BooleanArray`, :class:`Categorical`, :class:`DatetimeArray`, :class:`FloatingArray`, :class:`IntegerArray`, :class:`PeriodArray`, :class:`TimedeltaArray`, and :class:`PandasArray` are now keyword-only methods (:issue:`37541`)
 
 Other
 ^^^^^

pandas/_libs/tslibs/offsets.pyx

@@ -1388,7 +1388,11 @@ cdef class BusinessDay(BusinessMixin):
     @apply_array_wraps
     def _apply_array(self, dtarr):
         i8other = dtarr.view("i8")
-        return shift_bdays(i8other, self.n)
+        res = _shift_bdays(i8other, self.n)
+        if self.offset:
+            res = res.view("M8[ns]") + Timedelta(self.offset)
+            res = res.view("i8")
+        return res
 
     def is_on_offset(self, dt: datetime) -> bool:
         if self.normalize and not _is_normalized(dt):
@@ -3778,7 +3782,7 @@ cdef inline void _shift_quarters(const int64_t[:] dtindex,
         out[i] = dtstruct_to_dt64(&dts)
 
 
-cdef ndarray[int64_t] shift_bdays(const int64_t[:] i8other, int periods):
+cdef ndarray[int64_t] _shift_bdays(const int64_t[:] i8other, int periods):
     """
     Implementation of BusinessDay.apply_offset.
 

pandas/_typing.py

@@ -35,8 +35,11 @@
     from pandas.core.arrays.base import ExtensionArray  # noqa: F401
     from pandas.core.frame import DataFrame
     from pandas.core.generic import NDFrame  # noqa: F401
+    from pandas.core.groupby.generic import DataFrameGroupBy, SeriesGroupBy
     from pandas.core.indexes.base import Index
+    from pandas.core.resample import Resampler
     from pandas.core.series import Series
+    from pandas.core.window.rolling import BaseWindow
 
     from pandas.io.formats.format import EngFormatter
 
@@ -115,6 +118,14 @@
     List[AggFuncTypeBase],
     AggFuncTypeDict,
 ]
+AggObjType = Union[
+    "Series",
+    "DataFrame",
+    "SeriesGroupBy",
+    "DataFrameGroupBy",
+    "BaseWindow",
+    "Resampler",
+]
 
 
 # for arbitrary kwargs passed during reading/writing files

pandas/core/aggregation.py

@@ -24,6 +24,7 @@
     AggFuncType,
     AggFuncTypeBase,
     AggFuncTypeDict,
+    AggObjType,
     Axis,
     FrameOrSeries,
     FrameOrSeriesUnion,
@@ -530,7 +531,7 @@ def transform_str_or_callable(
 
 
 def aggregate(
-    obj,
+    obj: AggObjType,
     arg: AggFuncType,
     *args,
     **kwargs,
@@ -580,7 +581,7 @@ def aggregate(
 
 
 def agg_list_like(
-    obj,
+    obj: AggObjType,
     arg: List[AggFuncTypeBase],
     _axis: int,
 ) -> FrameOrSeriesUnion:
@@ -672,7 +673,7 @@ def agg_list_like(
 
 
 def agg_dict_like(
-    obj,
+    obj: AggObjType,
     arg: AggFuncTypeDict,
     _axis: int,
 ) -> FrameOrSeriesUnion:

pandas/core/arrays/boolean.py

@@ -424,7 +424,7 @@ def _values_for_argsort(self) -> np.ndarray:
         data[self._mask] = -1
         return data
 
-    def any(self, skipna: bool = True, **kwargs):
+    def any(self, *, skipna: bool = True, **kwargs):
         """
         Return whether any element is True.
 
@@ -492,7 +492,7 @@ def any(self, skipna: bool = True, **kwargs):
             else:
                 return self.dtype.na_value
 
-    def all(self, skipna: bool = True, **kwargs):
+    def all(self, *, skipna: bool = True, **kwargs):
         """
         Return whether all elements are True.
 

pandas/core/arrays/categorical.py

@@ -1945,7 +1945,7 @@ def _reverse_indexer(self) -> Dict[Hashable, np.ndarray]:
     # Reductions
 
     @deprecate_kwarg(old_arg_name="numeric_only", new_arg_name="skipna")
-    def min(self, skipna=True, **kwargs):
+    def min(self, *, skipna=True, **kwargs):
         """
         The minimum value of the object.
 
@@ -1981,7 +1981,7 @@ def min(self, skipna=True, **kwargs):
         return self.categories[pointer]
 
     @deprecate_kwarg(old_arg_name="numeric_only", new_arg_name="skipna")
-    def max(self, skipna=True, **kwargs):
+    def max(self, *, skipna=True, **kwargs):
         """
         The maximum value of the object.
 

pandas/core/arrays/datetimelike.py

@@ -1245,7 +1245,7 @@ def __isub__(self, other):
     # --------------------------------------------------------------
     # Reductions
 
-    def min(self, axis=None, skipna=True, *args, **kwargs):
+    def min(self, *, axis=None, skipna=True, **kwargs):
         """
         Return the minimum value of the Array or minimum along
         an axis.
@@ -1256,7 +1256,7 @@ def min(self, axis=None, skipna=True, *args, **kwargs):
         Index.min : Return the minimum value in an Index.
         Series.min : Return the minimum value in a Series.
         """
-        nv.validate_min(args, kwargs)
+        nv.validate_min((), kwargs)
         nv.validate_minmax_axis(axis, self.ndim)
 
         if is_period_dtype(self.dtype):
@@ -1276,7 +1276,7 @@ def min(self, axis=None, skipna=True, *args, **kwargs):
             return self._box_func(result)
         return self._from_backing_data(result)
 
-    def max(self, axis=None, skipna=True, *args, **kwargs):
+    def max(self, *, axis=None, skipna=True, **kwargs):
         """
         Return the maximum value of the Array or maximum along
         an axis.
@@ -1289,7 +1289,7 @@ def max(self, axis=None, skipna=True, *args, **kwargs):
         """
         # TODO: skipna is broken with max.
         # See https://github.com/pandas-dev/pandas/issues/24265
-        nv.validate_max(args, kwargs)
+        nv.validate_max((), kwargs)
         nv.validate_minmax_axis(axis, self.ndim)
 
         if is_period_dtype(self.dtype):
@@ -1309,7 +1309,7 @@ def max(self, axis=None, skipna=True, *args, **kwargs):
             return self._box_func(result)
         return self._from_backing_data(result)
 
-    def mean(self, skipna=True, axis: Optional[int] = 0):
+    def mean(self, *, skipna=True, axis: Optional[int] = 0):
         """
         Return the mean value of the Array.
 
@@ -1350,8 +1350,8 @@ def mean(self, skipna=True, axis: Optional[int] = 0):
             return self._box_func(result)
         return self._from_backing_data(result)
 
-    def median(self, axis: Optional[int] = None, skipna: bool = True, *args, **kwargs):
-        nv.validate_median(args, kwargs)
+    def median(self, *, axis: Optional[int] = None, skipna: bool = True, **kwargs):
+        nv.validate_median((), kwargs)
 
         if axis is not None and abs(axis) >= self.ndim:
             raise ValueError("abs(axis) must be less than ndim")

pandas/core/arrays/floating.py

@@ -439,19 +439,19 @@ def _cmp_method(self, other, op):
 
         return BooleanArray(result, mask)
 
-    def sum(self, skipna=True, min_count=0, **kwargs):
+    def sum(self, *, skipna=True, min_count=0, **kwargs):
         nv.validate_sum((), kwargs)
         return super()._reduce("sum", skipna=skipna, min_count=min_count)
 
-    def prod(self, skipna=True, min_count=0, **kwargs):
+    def prod(self, *, skipna=True, min_count=0, **kwargs):
         nv.validate_prod((), kwargs)
         return super()._reduce("prod", skipna=skipna, min_count=min_count)
 
-    def min(self, skipna=True, **kwargs):
+    def min(self, *, skipna=True, **kwargs):
         nv.validate_min((), kwargs)
         return super()._reduce("min", skipna=skipna)
 
-    def max(self, skipna=True, **kwargs):
+    def max(self, *, skipna=True, **kwargs):
         nv.validate_max((), kwargs)
         return super()._reduce("max", skipna=skipna)
 

pandas/core/arrays/integer.py

@@ -603,19 +603,19 @@ def _arith_method(self, other, op):
 
         return self._maybe_mask_result(result, mask, other, op_name)
 
-    def sum(self, skipna=True, min_count=0, **kwargs):
+    def sum(self, *, skipna=True, min_count=0, **kwargs):
         nv.validate_sum((), kwargs)
         return super()._reduce("sum", skipna=skipna, min_count=min_count)
 
-    def prod(self, skipna=True, min_count=0, **kwargs):
+    def prod(self, *, skipna=True, min_count=0, **kwargs):
         nv.validate_prod((), kwargs)
         return super()._reduce("prod", skipna=skipna, min_count=min_count)
 
-    def min(self, skipna=True, **kwargs):
+    def min(self, *, skipna=True, **kwargs):
         nv.validate_min((), kwargs)
         return super()._reduce("min", skipna=skipna)
 
-    def max(self, skipna=True, **kwargs):
+    def max(self, *, skipna=True, **kwargs):
         nv.validate_max((), kwargs)
         return super()._reduce("max", skipna=skipna)