String dtype: fix isin() values handling for python storage

Author: jorisvandenbossche

pandas/conftest.py

@@ -1310,7 +1310,13 @@ def string_storage(request):
         pytest.param(("pyarrow", pd.NA), marks=td.skip_if_no("pyarrow")),
         pytest.param(("pyarrow", np.nan), marks=td.skip_if_no("pyarrow")),
         ("python", np.nan),
-    ]
+    ],
+    ids=[
+        "string=string[python]",
+        "string=string[pyarrow]",
+        "string=str[pyarrow]",
+        "string=str[python]",
+    ],
 )
 def string_dtype_arguments(request):
     """
@@ -1341,6 +1347,7 @@ def dtype_backend(request):
 
 # Alias so we can test with cartesian product of string_storage
 string_storage2 = string_storage
+string_dtype_arguments2 = string_dtype_arguments
 
 
 @pytest.fixture(params=tm.BYTES_DTYPES)

pandas/core/arrays/string_.py

@@ -46,6 +46,7 @@
     nanops,
     ops,
 )
+from pandas.core.algorithms import isin
 from pandas.core.array_algos import masked_reductions
 from pandas.core.arrays.base import ExtensionArray
 from pandas.core.arrays.floating import (
@@ -65,6 +66,7 @@
     import pyarrow
 
     from pandas._typing import (
+        ArrayLike,
         AxisInt,
         Dtype,
         DtypeObj,
@@ -731,6 +733,22 @@ def _putmask(self, mask: npt.NDArray[np.bool_], value) -> None:
         # base class implementation that uses __setitem__
         ExtensionArray._putmask(self, mask, value)
 
+    def isin(self, values: ArrayLike) -> npt.NDArray[np.bool_]:
+        if not isinstance(values, BaseStringArray):
+            if not lib.is_string_array(np.asarray(values), skipna=True):
+                values = np.array(
+                    [val for val in values if isinstance(val, str) or isna(val)],
+                    dtype=object,
+                )
+                if not len(values):
+                    return np.zeros(self.shape, dtype=bool)
+
+            values = self._from_sequence(values, dtype=self.dtype)
+        else:
+            values = values.astype(self.dtype, copy=False)
+
+        return isin(np.asarray(self), np.asarray(values))
+
     def astype(self, dtype, copy: bool = True):
         dtype = pandas_dtype(dtype)
 

pandas/tests/arrays/string_/test_string.py

@@ -30,6 +30,12 @@ def dtype(string_dtype_arguments):
     return pd.StringDtype(storage=storage, na_value=na_value)
 
 
+@pytest.fixture
+def dtype2(string_dtype_arguments2):
+    storage, na_value = string_dtype_arguments2
+    return pd.StringDtype(storage=storage, na_value=na_value)
+
+
 @pytest.fixture
 def cls(dtype):
     """Fixture giving array type from parametrized 'dtype'"""
@@ -665,11 +671,7 @@ def test_isin(dtype, fixed_now_ts):
     tm.assert_series_equal(result, expected)
 
     result = s.isin(["a", pd.NA])
-    if dtype.storage == "python" and dtype.na_value is np.nan:
-        # TODO(infer_string) we should make this consistent
-        expected = pd.Series([True, False, False])
-    else:
-        expected = pd.Series([True, False, True])
+    expected = pd.Series([True, False, True])
     tm.assert_series_equal(result, expected)
 
     result = s.isin([])
@@ -681,6 +683,18 @@ def test_isin(dtype, fixed_now_ts):
     tm.assert_series_equal(result, expected)
 
 
+def test_isin_string_array(dtype, dtype2):
+    s = pd.Series(["a", "b", None], dtype=dtype)
+
+    result = s.isin(pd.array(["a", "c"], dtype=dtype2))
+    expected = pd.Series([True, False, False])
+    tm.assert_series_equal(result, expected)
+
+    result = s.isin(pd.array(["a", None], dtype=dtype2))
+    expected = pd.Series([True, False, True])
+    tm.assert_series_equal(result, expected)
+
+
 def test_setitem_scalar_with_mask_validation(dtype):
     # https://github.com/pandas-dev/pandas/issues/47628
     # setting None with a boolean mask (through _putmaks) should still result