fix series.isin slow issue with Dtype IntegerArray

doc/source/reference/extensions.rst

@@ -48,6 +48,7 @@ objects.
       api.extensions.ExtensionArray.equals
       api.extensions.ExtensionArray.factorize
       api.extensions.ExtensionArray.fillna
+      api.extensions.ExtensionArray.isin
       api.extensions.ExtensionArray.isna
       api.extensions.ExtensionArray.ravel
       api.extensions.ExtensionArray.repeat

pandas/core/algorithms.py

@@ -449,10 +449,8 @@ def isin(comps: AnyArrayLike, values: AnyArrayLike) -> np.ndarray:
 
     comps = _ensure_arraylike(comps)
     comps = extract_array(comps, extract_numpy=True)
-    if is_categorical_dtype(comps.dtype):
-        # TODO(extension)
-        # handle categoricals
-        return cast("Categorical", comps).isin(values)
+    if is_extension_array_dtype(comps.dtype):
+        return comps.isin(values)
 
     if needs_i8_conversion(comps.dtype):
         # Dispatch to DatetimeLikeArrayMixin.isin
@@ -464,9 +462,7 @@ def isin(comps: AnyArrayLike, values: AnyArrayLike) -> np.ndarray:
     elif needs_i8_conversion(values.dtype):
         return isin(comps, values.astype(object))
 
-    elif is_extension_array_dtype(comps.dtype) or is_extension_array_dtype(
-        values.dtype
-    ):
+    elif is_extension_array_dtype(values.dtype):
         return isin(np.asarray(comps), np.asarray(values))
 
     # GH16012

pandas/core/arrays/base.py

@@ -45,7 +45,7 @@
 from pandas.core.dtypes.missing import isna
 
 from pandas.core import ops
-from pandas.core.algorithms import factorize_array, unique
+from pandas.core.algorithms import factorize_array, isin, unique
 from pandas.core.missing import get_fill_func
 from pandas.core.sorting import nargminmax, nargsort
 
@@ -78,6 +78,7 @@ class ExtensionArray:
     factorize
     fillna
     equals
+    isin
     isna
     ravel
     repeat
@@ -833,6 +834,22 @@ def equals(self, other: object) -> bool:
             equal_na = self.isna() & other.isna()
             return bool((equal_values | equal_na).all())
 
+    def isin(self, values) -> np.ndarray:
+        """
+        Pointwise comparison for set containment in the given values.
+
+        Roughly equivalent to `np.array([x in values for x in self])`
+
+        Parameters
+        ----------
+        values : Sequence
+
+        Returns
+        -------
+        np.ndarray[bool]
+        """
+        return isin(np.asarray(self), values)
+
     def _values_for_factorize(self) -> Tuple[np.ndarray, Any]:
         """
         Return an array and missing value suitable for factorization.

pandas/core/arrays/masked.py

@@ -18,15 +18,17 @@
 )
 from pandas.core.dtypes.missing import isna, notna
 
+import pandas as pd
 from pandas.core import nanops
-from pandas.core.algorithms import factorize_array, take
+from pandas.core.algorithms import factorize_array, isin, take
 from pandas.core.array_algos import masked_reductions
 from pandas.core.arraylike import OpsMixin
 from pandas.core.arrays import ExtensionArray
 from pandas.core.indexers import check_array_indexer
 
 if TYPE_CHECKING:
     from pandas import Series
+    from pandas.core.arrays import BooleanArray
 
 
 BaseMaskedArrayT = TypeVar("BaseMaskedArrayT", bound="BaseMaskedArray")
@@ -299,6 +301,16 @@ def take(
 
         return type(self)(result, mask, copy=False)
 
+    def isin(self, values) -> "BooleanArray":
+
+        from pandas.core.arrays import BooleanArray
+
+        result = isin(self._data, values) * np.invert(self._mask)
+        if any(x is pd.NA for x in values):
+            result += self._mask
+        mask = np.zeros_like(self, dtype=bool)
+        return BooleanArray(result, mask, copy=False)
+
     def copy(self: BaseMaskedArrayT) -> BaseMaskedArrayT:
         data, mask = self._data, self._mask
         data = data.copy()