PERF: slightly faster dtype.kind checks (#52387)

Author: jbrockmendel

pandas/_libs/lib.pyx

@@ -747,7 +747,7 @@ cpdef ndarray[object] ensure_string_array(
 
     if hasattr(arr, "to_numpy"):
 
-        if hasattr(arr, "dtype") and arr.dtype.kind in ["m", "M"]:
+        if hasattr(arr, "dtype") and arr.dtype.kind in "mM":
             # dtype check to exclude DataFrame
             # GH#41409 TODO: not a great place for this
             out = arr.astype(str).astype(object)
@@ -2641,7 +2641,7 @@ def maybe_convert_objects(ndarray[object] objects,
             dtype = dtype_if_all_nat
             if cnp.PyArray_DescrCheck(dtype):
                 # i.e. isinstance(dtype, np.dtype)
-                if dtype.kind not in ["m", "M"]:
+                if dtype.kind not in "mM":
                     raise ValueError(dtype)
                 else:
                     res = np.empty((<object>objects).shape, dtype=dtype)

pandas/_libs/tslibs/np_datetime.pyx

@@ -419,7 +419,7 @@ def compare_mismatched_resolutions(ndarray left, ndarray right, op):
     array([ True])
     """
 
-    if left.dtype.kind != right.dtype.kind or left.dtype.kind not in ["m", "M"]:
+    if left.dtype.kind != right.dtype.kind or left.dtype.kind not in "mM":
         raise ValueError("left and right must both be timedelta64 or both datetime64")
 
     cdef:

pandas/_libs/tslibs/timedeltas.pyx

@@ -775,7 +775,7 @@ def _binary_op_method_timedeltalike(op, name):
                 item = cnp.PyArray_ToScalar(cnp.PyArray_DATA(other), other)
                 return f(self, item)
 
-            elif other.dtype.kind in ["m", "M"]:
+            elif other.dtype.kind in "mM":
                 return op(self.to_timedelta64(), other)
             elif other.dtype.kind == "O":
                 return np.array([op(self, x) for x in other])
@@ -2028,7 +2028,7 @@ class Timedelta(_Timedelta):
                     result[mask] = np.nan
                 return result
 
-            elif other.dtype.kind in ["i", "u", "f"]:
+            elif other.dtype.kind in "iuf":
                 if other.ndim == 0:
                     return self // other.item()
                 else:

pandas/_libs/tslibs/timestamps.pyx

@@ -464,7 +464,7 @@ cdef class _Timestamp(ABCTimestamp):
             raise integer_op_not_supported(self)
 
         elif is_array(other):
-            if other.dtype.kind in ["i", "u"]:
+            if other.dtype.kind in "iu":
                 raise integer_op_not_supported(self)
             if other.dtype.kind == "m":
                 if self.tz is None:
@@ -496,7 +496,7 @@ cdef class _Timestamp(ABCTimestamp):
             return self + neg_other
 
         elif is_array(other):
-            if other.dtype.kind in ["i", "u"]:
+            if other.dtype.kind in "iu":
                 raise integer_op_not_supported(self)
             if other.dtype.kind == "m":
                 if self.tz is None:

pandas/_testing/asserters.py

@@ -530,7 +530,7 @@ def assert_interval_array_equal(
     _check_isinstance(left, right, IntervalArray)
 
     kwargs = {}
-    if left._left.dtype.kind in ["m", "M"]:
+    if left._left.dtype.kind in "mM":
         # We have a DatetimeArray or TimedeltaArray
         kwargs["check_freq"] = False
 

pandas/core/algorithms.py

@@ -568,7 +568,7 @@ def factorize_array(
     uniques : ndarray
     """
     original = values
-    if values.dtype.kind in ["m", "M"]:
+    if values.dtype.kind in "mM":
         # _get_hashtable_algo will cast dt64/td64 to i8 via _ensure_data, so we
         #  need to do the same to na_value. We are assuming here that the passed
         #  na_value is an appropriately-typed NaT.

pandas/core/array_algos/datetimelike_accumulations.py

@@ -50,7 +50,7 @@ def _cum_func(
     result = func(y)
     result[mask] = iNaT
 
-    if values.dtype.kind in ["m", "M"]:
+    if values.dtype.kind in "mM":
         return result.view(values.dtype.base)
     return result
 

pandas/core/array_algos/putmask.py

@@ -142,7 +142,7 @@ def setitem_datetimelike_compat(values: np.ndarray, num_set: int, other):
     if values.dtype == object:
         dtype, _ = infer_dtype_from(other, pandas_dtype=True)
 
-        if isinstance(dtype, np.dtype) and dtype.kind in ["m", "M"]:
+        if isinstance(dtype, np.dtype) and dtype.kind in "mM":
             # https://github.com/numpy/numpy/issues/12550
             #  timedelta64 will incorrectly cast to int
             if not is_list_like(other):

pandas/core/array_algos/quantile.py

@@ -180,7 +180,7 @@ def _nanpercentile(
     quantiles : scalar or array
     """
 
-    if values.dtype.kind in ["m", "M"]:
+    if values.dtype.kind in "mM":
         # need to cast to integer to avoid rounding errors in numpy
         result = _nanpercentile(
             values.view("i8"),

pandas/core/arrays/datetimelike.py

@@ -740,7 +740,7 @@ def isin(self, values) -> npt.NDArray[np.bool_]:
         if not hasattr(values, "dtype"):
             values = np.asarray(values)
 
-        if values.dtype.kind in ["f", "i", "u", "c"]:
+        if values.dtype.kind in "fiuc":
             # TODO: de-duplicate with equals, validate_comparison_value
             return np.zeros(self.shape, dtype=bool)
 
@@ -769,7 +769,7 @@ def isin(self, values) -> npt.NDArray[np.bool_]:
             except ValueError:
                 return isin(self.astype(object), values)
 
-        if self.dtype.kind in ["m", "M"]:
+        if self.dtype.kind in "mM":
             self = cast("DatetimeArray | TimedeltaArray", self)
             values = values.as_unit(self.unit)
 
@@ -1205,7 +1205,7 @@ def _sub_nat(self):
         # For period dtype, timedelta64 is a close-enough return dtype.
         result = np.empty(self.shape, dtype=np.int64)
         result.fill(iNaT)
-        if self.dtype.kind in ["m", "M"]:
+        if self.dtype.kind in "mM":
             # We can retain unit in dtype
             self = cast("DatetimeArray| TimedeltaArray", self)
             return result.view(f"timedelta64[{self.unit}]")