Merge remote-tracking branch 'upstream/master' into BUG-32967

Author: Sumanau Sareen

Diff for: ci/code_checks.sh

@@ -283,14 +283,8 @@ if [[ -z "$CHECK" || "$CHECK" == "doctests" ]]; then
     pytest -q --doctest-modules pandas/core/tools/datetimes.py
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
-    MSG='Doctests top-level reshaping functions' ; echo $MSG
-    pytest -q --doctest-modules \
-        pandas/core/reshape/concat.py \
-        pandas/core/reshape/pivot.py \
-        pandas/core/reshape/reshape.py \
-        pandas/core/reshape/tile.py \
-        pandas/core/reshape/melt.py \
-        -k"-crosstab -pivot_table -cut"
+    MSG='Doctests reshaping functions' ; echo $MSG
+    pytest -q --doctest-modules pandas/core/reshape/
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
     MSG='Doctests interval classes' ; echo $MSG
@@ -325,6 +319,10 @@ if [[ -z "$CHECK" || "$CHECK" == "doctests" ]]; then
     MSG='Doctests generic.py' ; echo $MSG
     pytest -q --doctest-modules pandas/core/generic.py
     RET=$(($RET + $?)) ; echo $MSG "DONE"
+
+    MSG='Doctests tseries' ; echo $MSG
+    pytest -q --doctest-modules pandas/tseries/
+    RET=$(($RET + $?)) ; echo $MSG "DONE"
 fi
 
 ### DOCSTRINGS ###

Diff for: doc/source/whatsnew/v1.1.0.rst

@@ -341,6 +341,7 @@ Indexing
 - Fix to preserve the ability to index with the "nearest" method with xarray's CFTimeIndex, an :class:`Index` subclass (`pydata/xarray#3751 <https://github.com/pydata/xarray/issues/3751>`_, :issue:`32905`).
 - Bug in :class:`Index` constructor where an unhelpful error message was raised for ``numpy`` scalars (:issue:`33017`)
 - Bug in :meth:`DataFrame.lookup` incorrectly raising an ``AttributeError`` when ``frame.index`` or ``frame.columns`` is not unique; this will now raise a ``ValueError`` with a helpful error message (:issue:`33041`)
+- Bug in :meth:`DataFrame.iloc.__setitem__` creating a new array instead of overwriting ``Categorical`` values in-place (:issue:`32831`)
 
 Missing
 ^^^^^^^

Diff for: pandas/core/frame.py

@@ -2300,7 +2300,7 @@ def to_html(
         )
 
     # ----------------------------------------------------------------------
-    @Appender(info.__doc__)
+    @doc(info)
     def info(
         self, verbose=None, buf=None, max_cols=None, memory_usage=None, null_counts=None
     ) -> None:

Diff for: pandas/core/generic.py

@@ -1723,7 +1723,7 @@ def items(self):
         for h in self._info_axis:
             yield h, self[h]
 
-    @Appender(items.__doc__)
+    @doc(items)
     def iteritems(self):
         return self.items()
 
@@ -10222,7 +10222,7 @@ def _add_series_or_dataframe_operations(cls):
         """
         from pandas.core.window import EWM, Expanding, Rolling, Window
 
-        @Appender(Rolling.__doc__)
+        @doc(Rolling)
         def rolling(
             self,
             window,
@@ -10260,14 +10260,14 @@ def rolling(
 
         cls.rolling = rolling
 
-        @Appender(Expanding.__doc__)
+        @doc(Expanding)
         def expanding(self, min_periods=1, center=False, axis=0):
             axis = self._get_axis_number(axis)
             return Expanding(self, min_periods=min_periods, center=center, axis=axis)
 
         cls.expanding = expanding
 
-        @Appender(EWM.__doc__)
+        @doc(EWM)
         def ewm(
             self,
             com=None,

Diff for: pandas/core/indexes/multi.py

@@ -21,7 +21,7 @@
 from pandas._typing import AnyArrayLike, Scalar
 from pandas.compat.numpy import function as nv
 from pandas.errors import PerformanceWarning, UnsortedIndexError
-from pandas.util._decorators import Appender, cache_readonly
+from pandas.util._decorators import Appender, cache_readonly, doc
 
 from pandas.core.dtypes.cast import coerce_indexer_dtype
 from pandas.core.dtypes.common import (
@@ -986,7 +986,7 @@ def _engine(self):
     def _constructor(self):
         return MultiIndex.from_tuples
 
-    @Appender(Index._shallow_copy.__doc__)
+    @doc(Index._shallow_copy)
     def _shallow_copy(
         self,
         values=None,
@@ -1098,7 +1098,7 @@ def view(self, cls=None):
         result._id = self._id
         return result
 
-    @Appender(Index.__contains__.__doc__)
+    @doc(Index.__contains__)
     def __contains__(self, key: Any) -> bool:
         hash(key)
         try:
@@ -1119,7 +1119,7 @@ def f(l):
 
         return any(f(l) for l in self._inferred_type_levels)
 
-    @Appender(Index.memory_usage.__doc__)
+    @doc(Index.memory_usage)
     def memory_usage(self, deep: bool = False) -> int:
         # we are overwriting our base class to avoid
         # computing .values here which could materialize
@@ -1351,7 +1351,7 @@ def _set_names(self, names, level=None, validate=True):
 
     # --------------------------------------------------------------------
 
-    @Appender(Index._get_grouper_for_level.__doc__)
+    @doc(Index._get_grouper_for_level)
     def _get_grouper_for_level(self, mapper, level):
         indexer = self.codes[level]
         level_index = self.levels[level]
@@ -1462,7 +1462,7 @@ def _inferred_type_levels(self):
         """ return a list of the inferred types, one for each level """
         return [i.inferred_type for i in self.levels]
 
-    @Appender(Index.duplicated.__doc__)
+    @doc(Index.duplicated)
     def duplicated(self, keep="first"):
         shape = map(len, self.levels)
         ids = get_group_index(self.codes, shape, sort=False, xnull=False)
@@ -1475,7 +1475,7 @@ def fillna(self, value=None, downcast=None):
         """
         raise NotImplementedError("isna is not defined for MultiIndex")
 
-    @Appender(Index.dropna.__doc__)
+    @doc(Index.dropna)
     def dropna(self, how="any"):
         nans = [level_codes == -1 for level_codes in self.codes]
         if how == "any":
@@ -1548,7 +1548,7 @@ def get_level_values(self, level):
         values = self._get_level_values(level)
         return values
 
-    @Appender(Index.unique.__doc__)
+    @doc(Index.unique)
     def unique(self, level=None):
 
         if level is None:
@@ -3423,7 +3423,7 @@ def _convert_can_do_setop(self, other):
 
     # --------------------------------------------------------------------
 
-    @Appender(Index.astype.__doc__)
+    @doc(Index.astype)
     def astype(self, dtype, copy=True):
         dtype = pandas_dtype(dtype)
         if is_categorical_dtype(dtype):
@@ -3498,7 +3498,7 @@ def _wrap_joined_index(self, joined, other):
         names = self.names if self.names == other.names else None
         return MultiIndex.from_tuples(joined, names=names)
 
-    @Appender(Index.isin.__doc__)
+    @doc(Index.isin)
     def isin(self, values, level=None):
         if level is None:
             values = MultiIndex.from_tuples(values, names=self.names)._values

Diff for: pandas/core/indexes/numeric.py

@@ -4,7 +4,7 @@
 
 from pandas._libs import index as libindex, lib
 from pandas._typing import Dtype, Label
-from pandas.util._decorators import Appender, cache_readonly
+from pandas.util._decorators import cache_readonly, doc
 
 from pandas.core.dtypes.cast import astype_nansafe
 from pandas.core.dtypes.common import (
@@ -95,14 +95,14 @@ def _validate_dtype(cls, dtype: Dtype) -> None:
                 f"Incorrect `dtype` passed: expected {expected}, received {dtype}"
             )
 
-    @Appender(Index._maybe_cast_slice_bound.__doc__)
+    @doc(Index._maybe_cast_slice_bound)
     def _maybe_cast_slice_bound(self, label, side, kind):
         assert kind in ["loc", "getitem", None]
 
         # we will try to coerce to integers
         return self._maybe_cast_indexer(label)
 
-    @Appender(Index._shallow_copy.__doc__)
+    @doc(Index._shallow_copy)
     def _shallow_copy(self, values=None, name: Label = lib.no_default):
         if values is not None and not self._can_hold_na and values.dtype.kind == "f":
             name = self.name if name is lib.no_default else name
@@ -158,7 +158,7 @@ def is_all_dates(self) -> bool:
         """
         return False
 
-    @Appender(Index.insert.__doc__)
+    @doc(Index.insert)
     def insert(self, loc: int, item):
         # treat NA values as nans:
         if is_scalar(item) and isna(item):
@@ -295,7 +295,7 @@ class UInt64Index(IntegerIndex):
     _engine_type = libindex.UInt64Engine
     _default_dtype = np.dtype(np.uint64)
 
-    @Appender(Index._convert_arr_indexer.__doc__)
+    @doc(Index._convert_arr_indexer)
     def _convert_arr_indexer(self, keyarr):
         # Cast the indexer to uint64 if possible so that the values returned
         # from indexing are also uint64.
@@ -307,7 +307,7 @@ def _convert_arr_indexer(self, keyarr):
 
         return com.asarray_tuplesafe(keyarr, dtype=dtype)
 
-    @Appender(Index._convert_index_indexer.__doc__)
+    @doc(Index._convert_index_indexer)
     def _convert_index_indexer(self, keyarr):
         # Cast the indexer to uint64 if possible so
         # that the values returned from indexing are
@@ -357,7 +357,7 @@ def inferred_type(self) -> str:
         """
         return "floating"
 
-    @Appender(Index.astype.__doc__)
+    @doc(Index.astype)
     def astype(self, dtype, copy=True):
         dtype = pandas_dtype(dtype)
         if needs_i8_conversion(dtype):
@@ -375,11 +375,11 @@ def astype(self, dtype, copy=True):
     # ----------------------------------------------------------------
     # Indexing Methods
 
-    @Appender(Index._should_fallback_to_positional.__doc__)
+    @doc(Index._should_fallback_to_positional)
     def _should_fallback_to_positional(self):
         return False
 
-    @Appender(Index._convert_slice_indexer.__doc__)
+    @doc(Index._convert_slice_indexer)
     def _convert_slice_indexer(self, key: slice, kind: str):
         assert kind in ["loc", "getitem"]
 
@@ -433,7 +433,7 @@ def __contains__(self, other: Any) -> bool:
 
         return is_float(other) and np.isnan(other) and self.hasnans
 
-    @Appender(Index.get_loc.__doc__)
+    @doc(Index.get_loc)
     def get_loc(self, key, method=None, tolerance=None):
         if is_bool(key):
             # Catch this to avoid accidentally casting to 1.0
@@ -453,7 +453,7 @@ def get_loc(self, key, method=None, tolerance=None):
     def is_unique(self) -> bool:
         return super().is_unique and self._nan_idxs.size < 2
 
-    @Appender(Index.isin.__doc__)
+    @doc(Index.isin)
     def isin(self, values, level=None):
         if level is not None:
             self._validate_index_level(level)

Diff for: pandas/core/indexes/period.py

@@ -10,7 +10,7 @@
 from pandas._libs.tslibs.parsing import parse_time_string
 from pandas._libs.tslibs.period import Period
 from pandas._typing import DtypeObj, Label
-from pandas.util._decorators import Appender, cache_readonly
+from pandas.util._decorators import Appender, cache_readonly, doc
 
 from pandas.core.dtypes.common import (
     ensure_platform_int,
@@ -327,7 +327,7 @@ def _engine(self):
         period = weakref.ref(self)
         return self._engine_type(period, len(self))
 
-    @Appender(Index.__contains__.__doc__)
+    @doc(Index.__contains__)
     def __contains__(self, key: Any) -> bool:
         if isinstance(key, Period):
             if key.freq != self.freq:
@@ -405,7 +405,7 @@ def asof_locs(self, where, mask: np.ndarray) -> np.ndarray:
 
         return result
 
-    @Appender(Index.astype.__doc__)
+    @doc(Index.astype)
     def astype(self, dtype, copy=True, how="start"):
         dtype = pandas_dtype(dtype)
 

Diff for: pandas/core/indexes/range.py

@@ -11,7 +11,7 @@
 from pandas._typing import Label
 import pandas.compat as compat
 from pandas.compat.numpy import function as nv
-from pandas.util._decorators import Appender, cache_readonly
+from pandas.util._decorators import Appender, cache_readonly, doc
 
 from pandas.core.dtypes.common import (
     ensure_platform_int,
@@ -342,7 +342,7 @@ def __contains__(self, key: Any) -> bool:
             return False
         return key in self._range
 
-    @Appender(Int64Index.get_loc.__doc__)
+    @doc(Int64Index.get_loc)
     def get_loc(self, key, method=None, tolerance=None):
         if method is None and tolerance is None:
             if is_integer(key) or (is_float(key) and key.is_integer()):
@@ -386,7 +386,7 @@ def get_indexer(self, target, method=None, limit=None, tolerance=None):
     def tolist(self):
         return list(self._range)
 
-    @Appender(Int64Index._shallow_copy.__doc__)
+    @doc(Int64Index._shallow_copy)
     def _shallow_copy(self, values=None, name: Label = no_default):
         name = self.name if name is no_default else name
 
@@ -397,7 +397,7 @@ def _shallow_copy(self, values=None, name: Label = no_default):
         else:
             return Int64Index._simple_new(values, name=name)
 
-    @Appender(Int64Index.copy.__doc__)
+    @doc(Int64Index.copy)
     def copy(self, name=None, deep=False, dtype=None, **kwargs):
         self._validate_dtype(dtype)
         if name is None:
@@ -619,7 +619,7 @@ def _union(self, other, sort):
                     return type(self)(start_r, end_r + step_o, step_o)
         return self._int64index._union(other, sort=sort)
 
-    @Appender(Int64Index.join.__doc__)
+    @doc(Int64Index.join)
     def join(self, other, how="left", level=None, return_indexers=False, sort=False):
         if how == "outer" and self is not other:
             # note: could return RangeIndex in more circumstances

Diff for: pandas/core/indexes/timedeltas.py

@@ -2,7 +2,7 @@
 
 from pandas._libs import NaT, Timedelta, index as libindex
 from pandas._typing import DtypeObj, Label
-from pandas.util._decorators import Appender
+from pandas.util._decorators import doc
 
 from pandas.core.dtypes.common import (
     _TD_DTYPE,
@@ -195,7 +195,7 @@ def _formatter_func(self):
 
     # -------------------------------------------------------------------
 
-    @Appender(Index.astype.__doc__)
+    @doc(Index.astype)
     def astype(self, dtype, copy=True):
         dtype = pandas_dtype(dtype)
         if is_timedelta64_dtype(dtype) and not is_timedelta64_ns_dtype(dtype):

Diff for: pandas/core/resample.py

@@ -11,7 +11,7 @@
 from pandas._libs.tslibs.period import IncompatibleFrequency
 from pandas.compat.numpy import function as nv
 from pandas.errors import AbstractMethodError
-from pandas.util._decorators import Appender, Substitution
+from pandas.util._decorators import Appender, Substitution, doc
 
 from pandas.core.dtypes.generic import ABCDataFrame, ABCSeries
 
@@ -858,7 +858,7 @@ def var(self, ddof=1, *args, **kwargs):
         nv.validate_resampler_func("var", args, kwargs)
         return self._downsample("var", ddof=ddof)
 
-    @Appender(GroupBy.size.__doc__)
+    @doc(GroupBy.size)
     def size(self):
         result = self._downsample("size")
         if not len(self.ax):
@@ -871,7 +871,7 @@ def size(self):
             result = Series([], index=result.index, dtype="int64", name=name)
         return result
 
-    @Appender(GroupBy.count.__doc__)
+    @doc(GroupBy.count)
     def count(self):
         result = self._downsample("count")
         if not len(self.ax):