PERF: avoid is_datetime64_any_dtype

doc/source/whatsnew/v2.1.0.rst

@@ -238,6 +238,7 @@ Deprecations
 - Deprecated parameter ``convert_type`` in :meth:`Series.apply` (:issue:`52140`)
 - Deprecated passing a dictionary to :meth:`.SeriesGroupBy.agg`; pass a list of aggregations instead (:issue:`50684`)
 - Deprecated the "fastpath" keyword in :class:`Categorical` constructor, use :meth:`Categorical.from_codes` instead (:issue:`20110`)
+- Deprecated the behavior of :func:`is_bool_dtype` returning ``True`` for object-dtype :class:`Index` of bool objects (:issue:`52680`)
 - Deprecated the methods :meth:`Series.bool` and :meth:`DataFrame.bool` (:issue:`51749`)
 - Deprecated unused "closed" and "normalize" keywords in the :class:`DatetimeIndex` constructor (:issue:`52628`)
 - Deprecated unused "closed" keyword in the :class:`TimedeltaIndex` constructor (:issue:`52628`)

pandas/core/arrays/datetimelike.py

@@ -83,7 +83,6 @@
 
 from pandas.core.dtypes.common import (
     is_all_strings,
-    is_datetime64_any_dtype,
     is_dtype_equal,
     is_integer_dtype,
     is_list_like,
@@ -1390,8 +1389,11 @@ def __sub__(self, other):
 
     def __rsub__(self, other):
         other_dtype = getattr(other, "dtype", None)
+        other_is_dt64 = lib.is_np_dtype(other_dtype, "M") or isinstance(
+            other_dtype, DatetimeTZDtype
+        )
 
-        if is_datetime64_any_dtype(other_dtype) and lib.is_np_dtype(self.dtype, "m"):
+        if other_is_dt64 and lib.is_np_dtype(self.dtype, "m"):
             # ndarray[datetime64] cannot be subtracted from self, so
             # we need to wrap in DatetimeArray/Index and flip the operation
             if lib.is_scalar(other):
@@ -1403,11 +1405,7 @@ def __rsub__(self, other):
 
                 other = DatetimeArray(other)
             return other - self
-        elif (
-            is_datetime64_any_dtype(self.dtype)
-            and hasattr(other, "dtype")
-            and not is_datetime64_any_dtype(other.dtype)
-        ):
+        elif self.dtype.kind == "M" and hasattr(other, "dtype") and not other_is_dt64:
             # GH#19959 datetime - datetime is well-defined as timedelta,
             # but any other type - datetime is not well-defined.
             raise TypeError(

pandas/core/arrays/datetimes.py

@@ -50,7 +50,6 @@
     DT64NS_DTYPE,
     INT64_DTYPE,
     is_bool_dtype,
-    is_datetime64_any_dtype,
     is_dtype_equal,
     is_float_dtype,
     is_object_dtype,
@@ -192,7 +191,9 @@ class DatetimeArray(dtl.TimelikeOps, dtl.DatelikeOps):  # type: ignore[misc]
     _typ = "datetimearray"
     _internal_fill_value = np.datetime64("NaT", "ns")
     _recognized_scalars = (datetime, np.datetime64)
-    _is_recognized_dtype = is_datetime64_any_dtype
+    _is_recognized_dtype = lambda x: lib.is_np_dtype(x, "M") or isinstance(
+        x, DatetimeTZDtype
+    )
     _infer_matches = ("datetime", "datetime64", "date")
 
     @property

pandas/core/arrays/period.py

@@ -55,12 +55,14 @@
 
 from pandas.core.dtypes.common import (
     ensure_object,
-    is_datetime64_any_dtype,
     is_dtype_equal,
     is_period_dtype,
     pandas_dtype,
 )
-from pandas.core.dtypes.dtypes import PeriodDtype
+from pandas.core.dtypes.dtypes import (
+    DatetimeTZDtype,
+    PeriodDtype,
+)
 from pandas.core.dtypes.generic import (
     ABCIndex,
     ABCPeriodIndex,
@@ -655,7 +657,7 @@ def astype(self, dtype, copy: bool = True):
         if isinstance(dtype, PeriodDtype):
             return self.asfreq(dtype.freq)
 
-        if is_datetime64_any_dtype(dtype):
+        if lib.is_np_dtype(dtype, "M") or isinstance(dtype, DatetimeTZDtype):
             # GH#45038 match PeriodIndex behavior.
             tz = getattr(dtype, "tz", None)
             return self.to_timestamp().tz_localize(tz)

pandas/core/arrays/sparse/array.py

@@ -44,7 +44,6 @@
 from pandas.core.dtypes.common import (
     is_array_like,
     is_bool_dtype,
-    is_datetime64_any_dtype,
     is_dtype_equal,
     is_integer,
     is_list_like,
@@ -559,7 +558,7 @@ def __array__(self, dtype: NpDtype | None = None) -> np.ndarray:
             # Can NumPy represent this type?
             # If not, `np.result_type` will raise. We catch that
             # and return object.
-            if is_datetime64_any_dtype(self.sp_values.dtype):
+            if self.sp_values.dtype.kind == "M":
                 # However, we *do* special-case the common case of
                 # a datetime64 with pandas NaT.
                 if fill_value is NaT:

pandas/core/dtypes/common.py

@@ -1219,7 +1219,18 @@ def is_bool_dtype(arr_or_dtype) -> bool:
 
     if isinstance(arr_or_dtype, ABCIndex):
         # Allow Index[object] that is all-bools or Index["boolean"]
-        return arr_or_dtype.inferred_type == "boolean"
+        if arr_or_dtype.inferred_type == "boolean":
+            if not is_bool_dtype(arr_or_dtype.dtype):
+                # GH#52680
+                warnings.warn(
+                    "The behavior of is_bool_dtype with an object-dtype Index "
+                    "of bool objects is deprecated. In a future version, "
+                    "this will return False. Cast the Index to a bool dtype instead.",
+                    FutureWarning,
+                    stacklevel=find_stack_level(),
+                )
+            return True
+        return False
     elif isinstance(dtype, ExtensionDtype):
         return getattr(dtype, "_is_boolean", False)
 

pandas/core/generic.py

@@ -110,7 +110,6 @@
     ensure_str,
     is_bool,
     is_bool_dtype,
-    is_datetime64_any_dtype,
     is_dict_like,
     is_dtype_equal,
     is_extension_array_dtype,
@@ -7754,8 +7753,8 @@ def interpolate(
             methods = {"index", "values", "nearest", "time"}
             is_numeric_or_datetime = (
                 is_numeric_dtype(index.dtype)
-                or is_datetime64_any_dtype(index.dtype)
-                or lib.is_np_dtype(index.dtype, "m")
+                or isinstance(index.dtype, DatetimeTZDtype)
+                or lib.is_np_dtype(index.dtype, "mM")
             )
             if method not in methods and not is_numeric_or_datetime:
                 raise ValueError(

pandas/core/methods/describe.py

@@ -31,10 +31,10 @@
 from pandas.core.dtypes.common import (
     is_bool_dtype,
     is_complex_dtype,
-    is_datetime64_any_dtype,
     is_extension_array_dtype,
     is_numeric_dtype,
 )
+from pandas.core.dtypes.dtypes import DatetimeTZDtype
 
 from pandas.core.arrays.arrow.dtype import ArrowDtype
 from pandas.core.arrays.floating import Float64Dtype
@@ -361,7 +361,7 @@ def select_describe_func(
         return describe_categorical_1d
     elif is_numeric_dtype(data):
         return describe_numeric_1d
-    elif is_datetime64_any_dtype(data.dtype):
+    elif lib.is_np_dtype(data.dtype, "M") or isinstance(data.dtype, DatetimeTZDtype):
         return describe_timestamp_1d
     elif lib.is_np_dtype(data.dtype, "m"):
         return describe_numeric_1d

pandas/tests/scalar/test_nat.py

@@ -11,8 +11,6 @@
 from pandas._libs.tslibs import iNaT
 from pandas.compat import is_numpy_dev
 
-from pandas.core.dtypes.common import is_datetime64_any_dtype
-
 from pandas import (
     DatetimeIndex,
     DatetimeTZDtype,
@@ -444,7 +442,7 @@ def test_nat_arithmetic_index(op_name, value):
     exp_name = "x"
     exp_data = [NaT] * 2
 
-    if is_datetime64_any_dtype(value.dtype) and "plus" in op_name:
+    if value.dtype.kind == "M" and "plus" in op_name:
         expected = DatetimeIndex(exp_data, tz=value.tz, name=exp_name)
     else:
         expected = TimedeltaIndex(exp_data, name=exp_name)