PERF: avoid is_dtype_equal (pandas-dev#52424)

* PERF: avoid is_dtype_equal

* PERF: avoid is_dtype_equal

* post-merge fixup

Author: jbrockmendel

pandas/core/arrays/_mixins.py

@@ -36,10 +36,7 @@
     validate_insert_loc,
 )
 
-from pandas.core.dtypes.common import (
-    is_dtype_equal,
-    pandas_dtype,
-)
+from pandas.core.dtypes.common import pandas_dtype
 from pandas.core.dtypes.dtypes import (
     DatetimeTZDtype,
     ExtensionDtype,
@@ -172,7 +169,7 @@ def take(
     def equals(self, other) -> bool:
         if type(self) is not type(other):
             return False
-        if not is_dtype_equal(self.dtype, other.dtype):
+        if self.dtype != other.dtype:
             return False
         return bool(array_equivalent(self._ndarray, other._ndarray, dtype_equal=True))
 

pandas/core/arrays/base.py

@@ -40,7 +40,6 @@
 
 from pandas.core.dtypes.cast import maybe_cast_to_extension_array
 from pandas.core.dtypes.common import (
-    is_dtype_equal,
     is_list_like,
     is_scalar,
     pandas_dtype,
@@ -570,7 +569,7 @@ def astype(self, dtype: AstypeArg, copy: bool = True) -> ArrayLike:
         """
 
         dtype = pandas_dtype(dtype)
-        if is_dtype_equal(dtype, self.dtype):
+        if dtype == self.dtype:
             if not copy:
                 return self
             else:
@@ -958,7 +957,7 @@ def equals(self, other: object) -> bool:
         if type(self) != type(other):
             return False
         other = cast(ExtensionArray, other)
-        if not is_dtype_equal(self.dtype, other.dtype):
+        if self.dtype != other.dtype:
             return False
         elif len(self) != len(other):
             return False

pandas/core/arrays/categorical.py

@@ -39,7 +39,6 @@
     is_any_real_numeric_dtype,
     is_bool_dtype,
     is_dict_like,
-    is_dtype_equal,
     is_hashable,
     is_integer_dtype,
     is_list_like,
@@ -1394,7 +1393,7 @@ def __array__(self, dtype: NpDtype | None = None) -> np.ndarray:
             categorical.categories.dtype.
         """
         ret = take_nd(self.categories._values, self._codes)
-        if dtype and not is_dtype_equal(dtype, self.categories.dtype):
+        if dtype and np.dtype(dtype) != self.categories.dtype:
             return np.asarray(ret, dtype)
         # When we're a Categorical[ExtensionArray], like Interval,
         # we need to ensure __array__ gets all the way to an
@@ -2018,7 +2017,7 @@ def _validate_listlike(self, value):
 
         # require identical categories set
         if isinstance(value, Categorical):
-            if not is_dtype_equal(self.dtype, value.dtype):
+            if self.dtype != value.dtype:
                 raise TypeError(
                     "Cannot set a Categorical with another, "
                     "without identical categories"

pandas/core/arrays/datetimelike.py

@@ -83,7 +83,6 @@
 
 from pandas.core.dtypes.common import (
     is_all_strings,
-    is_dtype_equal,
     is_integer_dtype,
     is_list_like,
     is_object_dtype,
@@ -664,7 +663,7 @@ def _validate_listlike(self, value, allow_object: bool = False):
 
         if isinstance(value.dtype, CategoricalDtype):
             # e.g. we have a Categorical holding self.dtype
-            if is_dtype_equal(value.categories.dtype, self.dtype):
+            if value.categories.dtype == self.dtype:
                 # TODO: do we need equal dtype or just comparable?
                 value = value._internal_get_values()
                 value = extract_array(value, extract_numpy=True)
@@ -1859,7 +1858,7 @@ def __init__(
 
             if dtype is not None:
                 dtype = pandas_dtype(dtype)
-                if not is_dtype_equal(dtype, values.dtype):
+                if dtype != values.dtype:
                     # TODO: we only have tests for this for DTA, not TDA (2022-07-01)
                     raise TypeError(
                         f"dtype={dtype} does not match data dtype {values.dtype}"

pandas/core/arrays/datetimes.py

@@ -50,7 +50,6 @@
     DT64NS_DTYPE,
     INT64_DTYPE,
     is_bool_dtype,
-    is_dtype_equal,
     is_float_dtype,
     is_string_dtype,
     pandas_dtype,
@@ -642,7 +641,7 @@ def astype(self, dtype, copy: bool = True):
         # DatetimeLikeArrayMixin Super handles the rest.
         dtype = pandas_dtype(dtype)
 
-        if is_dtype_equal(dtype, self.dtype):
+        if dtype == self.dtype:
             if copy:
                 return self.copy()
             return self
@@ -2316,7 +2315,7 @@ def _validate_dt64_dtype(dtype):
     """
     if dtype is not None:
         dtype = pandas_dtype(dtype)
-        if is_dtype_equal(dtype, np.dtype("M8")):
+        if dtype == np.dtype("M8"):
             # no precision, disallowed GH#24806
             msg = (
                 "Passing in 'datetime64' dtype with no precision is not allowed. "

pandas/core/arrays/interval.py

@@ -50,7 +50,6 @@
     maybe_upcast_numeric_to_64bit,
 )
 from pandas.core.dtypes.common import (
-    is_dtype_equal,
     is_float_dtype,
     is_integer_dtype,
     is_list_like,
@@ -1684,7 +1683,7 @@ def isin(self, values) -> npt.NDArray[np.bool_]:
                 # not comparable -> no overlap
                 return np.zeros(self.shape, dtype=bool)
 
-            if is_dtype_equal(self.dtype, values.dtype):
+            if self.dtype == values.dtype:
                 # GH#38353 instead of casting to object, operating on a
                 #  complex128 ndarray is much more performant.
                 left = self._combined.view("complex128")

pandas/core/arrays/masked.py

@@ -41,7 +41,6 @@
 from pandas.core.dtypes.base import ExtensionDtype
 from pandas.core.dtypes.common import (
     is_bool,
-    is_dtype_equal,
     is_integer_dtype,
     is_list_like,
     is_scalar,
@@ -459,7 +458,7 @@ def astype(self, dtype: AstypeArg, copy: bool = ...) -> ArrayLike:
     def astype(self, dtype: AstypeArg, copy: bool = True) -> ArrayLike:
         dtype = pandas_dtype(dtype)
 
-        if is_dtype_equal(dtype, self.dtype):
+        if dtype == self.dtype:
             if copy:
                 return self.copy()
             return self

pandas/core/arrays/numpy_.py

@@ -13,10 +13,7 @@
 
 from pandas.core.dtypes.astype import astype_array
 from pandas.core.dtypes.cast import construct_1d_object_array_from_listlike
-from pandas.core.dtypes.common import (
-    is_dtype_equal,
-    pandas_dtype,
-)
+from pandas.core.dtypes.common import pandas_dtype
 from pandas.core.dtypes.dtypes import PandasDtype
 from pandas.core.dtypes.missing import isna
 
@@ -199,7 +196,7 @@ def __array_ufunc__(self, ufunc: np.ufunc, method: str, *inputs, **kwargs):
     def astype(self, dtype, copy: bool = True):
         dtype = pandas_dtype(dtype)
 
-        if is_dtype_equal(dtype, self.dtype):
+        if dtype == self.dtype:
             if copy:
                 return self.copy()
             return self

pandas/core/arrays/period.py

@@ -55,7 +55,6 @@
 
 from pandas.core.dtypes.common import (
     ensure_object,
-    is_dtype_equal,
     pandas_dtype,
 )
 from pandas.core.dtypes.dtypes import (
@@ -650,7 +649,7 @@ def astype(self, dtype, copy: bool = True):
         # We handle Period[T] -> Period[U]
         # Our parent handles everything else.
         dtype = pandas_dtype(dtype)
-        if is_dtype_equal(dtype, self._dtype):
+        if dtype == self._dtype:
             if not copy:
                 return self
             else:

pandas/core/arrays/sparse/array.py

@@ -44,7 +44,6 @@
 from pandas.core.dtypes.common import (
     is_array_like,
     is_bool_dtype,
-    is_dtype_equal,
     is_integer,
     is_list_like,
     is_object_dtype,
@@ -180,7 +179,7 @@ def _sparse_array_op(
     ltype = left.dtype.subtype
     rtype = right.dtype.subtype
 
-    if not is_dtype_equal(ltype, rtype):
+    if ltype != rtype:
         subtype = find_common_type([ltype, rtype])
         ltype = SparseDtype(subtype, left.fill_value)
         rtype = SparseDtype(subtype, right.fill_value)
@@ -1240,7 +1239,7 @@ def astype(self, dtype: AstypeArg | None = None, copy: bool = True):
         IntIndex
         Indices: array([2, 3], dtype=int32)
         """
-        if is_dtype_equal(dtype, self._dtype):
+        if dtype == self._dtype:
             if not copy:
                 return self
             else:

pandas/core/arrays/string_.py

@@ -26,7 +26,6 @@
 from pandas.core.dtypes.common import (
     is_array_like,
     is_bool_dtype,
-    is_dtype_equal,
     is_integer_dtype,
     is_object_dtype,
     is_string_dtype,
@@ -444,7 +443,7 @@ def _putmask(self, mask: npt.NDArray[np.bool_], value) -> None:
     def astype(self, dtype, copy: bool = True):
         dtype = pandas_dtype(dtype)
 
-        if is_dtype_equal(dtype, self.dtype):
+        if dtype == self.dtype:
             if copy:
                 return self.copy()
             return self

pandas/core/arrays/string_arrow.py

@@ -19,7 +19,6 @@
 
 from pandas.core.dtypes.common import (
     is_bool_dtype,
-    is_dtype_equal,
     is_integer_dtype,
     is_object_dtype,
     is_scalar,
@@ -210,7 +209,7 @@ def isin(self, values) -> npt.NDArray[np.bool_]:
     def astype(self, dtype, copy: bool = True):
         dtype = pandas_dtype(dtype)
 
-        if is_dtype_equal(dtype, self.dtype):
+        if dtype == self.dtype:
             if copy:
                 return self.copy()
             return self

pandas/core/arrays/timedeltas.py

@@ -46,7 +46,6 @@
 
 from pandas.core.dtypes.common import (
     TD64NS_DTYPE,
-    is_dtype_equal,
     is_float_dtype,
     is_integer_dtype,
     is_object_dtype,
@@ -1048,7 +1047,7 @@ def _objects_to_td64ns(data, unit=None, errors: DateTimeErrorChoices = "raise"):
 
 def _validate_td64_dtype(dtype) -> DtypeObj:
     dtype = pandas_dtype(dtype)
-    if is_dtype_equal(dtype, np.dtype("timedelta64")):
+    if dtype == np.dtype("m8"):
         # no precision disallowed GH#24806
         msg = (
             "Passing in 'timedelta' dtype with no precision is not allowed. "

pandas/core/construction.py

@@ -43,7 +43,6 @@
     maybe_promote,
 )
 from pandas.core.dtypes.common import (
-    is_dtype_equal,
     is_list_like,
     is_object_dtype,
     pandas_dtype,
@@ -312,9 +311,7 @@ def array(
     if dtype is not None:
         dtype = pandas_dtype(dtype)
 
-    if isinstance(data, ExtensionArray) and (
-        dtype is None or is_dtype_equal(dtype, data.dtype)
-    ):
+    if isinstance(data, ExtensionArray) and (dtype is None or data.dtype == dtype):
         # e.g. TimedeltaArray[s], avoid casting to PandasArray
         if copy:
             return data.copy()

pandas/core/dtypes/astype.py

@@ -18,7 +18,6 @@
 from pandas.errors import IntCastingNaNError
 
 from pandas.core.dtypes.common import (
-    is_dtype_equal,
     is_object_dtype,
     is_string_dtype,
     pandas_dtype,
@@ -171,7 +170,7 @@ def astype_array(values: ArrayLike, dtype: DtypeObj, copy: bool = False) -> Arra
     -------
     ndarray or ExtensionArray
     """
-    if is_dtype_equal(values.dtype, dtype):
+    if values.dtype == dtype:
         if copy:
             return values.copy()
         return values

pandas/core/dtypes/concat.py

@@ -18,7 +18,6 @@
     common_dtype_categorical_compat,
     find_common_type,
 )
-from pandas.core.dtypes.common import is_dtype_equal
 from pandas.core.dtypes.dtypes import (
     CategoricalDtype,
     DatetimeTZDtype,
@@ -276,10 +275,7 @@ def _maybe_unwrap(x):
     to_union = [_maybe_unwrap(x) for x in to_union]
     first = to_union[0]
 
-    if not all(
-        is_dtype_equal(other.categories.dtype, first.categories.dtype)
-        for other in to_union[1:]
-    ):
+    if not lib.dtypes_all_equal([obj.categories.dtype for obj in to_union]):
         raise TypeError("dtype of categories must be the same")
 
     ordered = False

pandas/core/dtypes/dtypes.py

@@ -1248,9 +1248,7 @@ def __eq__(self, other: Any) -> bool:
         elif self.closed != other.closed:
             return False
         else:
-            from pandas.core.dtypes.common import is_dtype_equal
-
-            return is_dtype_equal(self.subtype, other.subtype)
+            return self.subtype == other.subtype
 
     def __setstate__(self, state) -> None:
         # for pickle compat. __get_state__ is defined in the

pandas/core/dtypes/missing.py

@@ -25,7 +25,6 @@
     DT64NS_DTYPE,
     TD64NS_DTYPE,
     ensure_object,
-    is_dtype_equal,
     is_scalar,
     is_string_or_object_np_dtype,
 )
@@ -592,7 +591,7 @@ def array_equals(left: ArrayLike, right: ArrayLike) -> bool:
     """
     ExtensionArray-compatible implementation of array_equivalent.
     """
-    if not is_dtype_equal(left.dtype, right.dtype):
+    if left.dtype != right.dtype:
         return False
     elif isinstance(left, ABCExtensionArray):
         return left.equals(right)

pandas/core/frame.py

@@ -93,7 +93,6 @@
     is_bool_dtype,
     is_dataclass,
     is_dict_like,
-    is_dtype_equal,
     is_float,
     is_float_dtype,
     is_hashable,
@@ -8347,7 +8346,7 @@ def combiner(x, y):
         dtypes = {
             col: find_common_type([self.dtypes[col], other.dtypes[col]])
             for col in self.columns.intersection(other.columns)
-            if not is_dtype_equal(combined.dtypes[col], self.dtypes[col])
+            if combined.dtypes[col] != self.dtypes[col]
         }
 
         if dtypes: