From d6fe9792a4ac08e3ddf6ceaa4c65c980b76d5d57 Mon Sep 17 00:00:00 2001
From: Brock <jbrockmendel@gmail.com>
Date: Wed, 14 Aug 2024 09:32:29 -0700
Subject: [PATCH 1/2] REF (string): remove _str_na_value

---
 pandas/core/arrays/numpy_.py        |  4 ----
 pandas/core/arrays/string_.py       | 10 ----------
 pandas/core/arrays/string_arrow.py  |  4 ----
 pandas/core/strings/object_array.py | 10 ++++------
 4 files changed, 4 insertions(+), 24 deletions(-)

diff --git a/pandas/core/arrays/numpy_.py b/pandas/core/arrays/numpy_.py
index 07eb91e0cb13b..03712f75db0c7 100644
--- a/pandas/core/arrays/numpy_.py
+++ b/pandas/core/arrays/numpy_.py
@@ -557,7 +557,3 @@ def _wrap_ndarray_result(self, result: np.ndarray):
 
             return TimedeltaArray._simple_new(result, dtype=result.dtype)
         return type(self)(result)
-
-    # ------------------------------------------------------------------------
-    # String methods interface
-    _str_na_value = np.nan
diff --git a/pandas/core/arrays/string_.py b/pandas/core/arrays/string_.py
index bdced4c496d14..11924003ba4d5 100644
--- a/pandas/core/arrays/string_.py
+++ b/pandas/core/arrays/string_.py
@@ -827,12 +827,6 @@ def _cmp_method(self, other, op):
 
     _arith_method = _cmp_method
 
-    # ------------------------------------------------------------------------
-    # String methods interface
-    # error: Incompatible types in assignment (expression has type "NAType",
-    # base class "NumpyExtensionArray" defined the type as "float")
-    _str_na_value = libmissing.NA  # type: ignore[assignment]
-
 
 class StringArrayNumpySemantics(StringArray):
     _storage = "python"
@@ -894,7 +888,3 @@ def value_counts(self, dropna: bool = True) -> Series:
         result = value_counts(self._ndarray, sort=False, dropna=dropna)
         result.index = result.index.astype(self.dtype)
         return result
-
-    # ------------------------------------------------------------------------
-    # String methods interface
-    _str_na_value = np.nan
diff --git a/pandas/core/arrays/string_arrow.py b/pandas/core/arrays/string_arrow.py
index 8e33179de0512..e7baf802c3194 100644
--- a/pandas/core/arrays/string_arrow.py
+++ b/pandas/core/arrays/string_arrow.py
@@ -275,10 +275,6 @@ def astype(self, dtype, copy: bool = True):
     # ------------------------------------------------------------------------
     # String methods interface
 
-    # error: Incompatible types in assignment (expression has type "NAType",
-    # base class "ObjectStringArrayMixin" defined the type as "float")
-    _str_na_value = libmissing.NA  # type: ignore[assignment]
-
     _str_map = BaseStringArray._str_map
 
     def _str_contains(
diff --git a/pandas/core/strings/object_array.py b/pandas/core/strings/object_array.py
index 290a28ab60ae1..148a3830840a6 100644
--- a/pandas/core/strings/object_array.py
+++ b/pandas/core/strings/object_array.py
@@ -37,8 +37,6 @@ class ObjectStringArrayMixin(BaseStringArrayMethods):
     String Methods operating on object-dtype ndarrays.
     """
 
-    _str_na_value = np.nan
-
     def __len__(self) -> int:
         # For typing, _str_map relies on the object being sized.
         raise NotImplementedError
@@ -56,7 +54,7 @@ def _str_map(
         na_value : Scalar, optional
             The value to set for NA values. Might also be used for the
             fill value if the callable `f` raises an exception.
-            This defaults to ``self._str_na_value`` which is ``np.nan``
+            This defaults to ``self.dtype.na_value`` which is ``np.nan``
             for object-dtype and Categorical and ``pd.NA`` for StringArray.
         dtype : Dtype, optional
             The dtype of the result array.
@@ -66,7 +64,7 @@ def _str_map(
         if dtype is None:
             dtype = np.dtype("object")
         if na_value is None:
-            na_value = self._str_na_value
+            na_value = self.dtype.na_value
 
         if not len(self):
             return np.array([], dtype=dtype)
@@ -272,7 +270,7 @@ def f(x):
                 return x.get(i)
             elif len(x) > i >= -len(x):
                 return x[i]
-            return self._str_na_value
+            return self.dtype.na_value
 
         return self._str_map(f)
 
@@ -466,7 +464,7 @@ def _str_removesuffix(self, suffix: str):
 
     def _str_extract(self, pat: str, flags: int = 0, expand: bool = True):
         regex = re.compile(pat, flags=flags)
-        na_value = self._str_na_value
+        na_value = self.dtype.na_value
 
         if not expand:
 

From 188275b1d53c7814ba419c32bd99ab88e329f7ec Mon Sep 17 00:00:00 2001
From: Brock <jbrockmendel@gmail.com>
Date: Wed, 14 Aug 2024 10:59:54 -0700
Subject: [PATCH 2/2] mypy fixup

---
 pandas/core/strings/object_array.py | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/pandas/core/strings/object_array.py b/pandas/core/strings/object_array.py
index 148a3830840a6..100afa956bd24 100644
--- a/pandas/core/strings/object_array.py
+++ b/pandas/core/strings/object_array.py
@@ -64,7 +64,7 @@ def _str_map(
         if dtype is None:
             dtype = np.dtype("object")
         if na_value is None:
-            na_value = self.dtype.na_value
+            na_value = self.dtype.na_value  # type: ignore[attr-defined]
 
         if not len(self):
             return np.array([], dtype=dtype)
@@ -270,7 +270,7 @@ def f(x):
                 return x.get(i)
             elif len(x) > i >= -len(x):
                 return x[i]
-            return self.dtype.na_value
+            return self.dtype.na_value  # type: ignore[attr-defined]
 
         return self._str_map(f)
 
@@ -464,7 +464,7 @@ def _str_removesuffix(self, suffix: str):
 
     def _str_extract(self, pat: str, flags: int = 0, expand: bool = True):
         regex = re.compile(pat, flags=flags)
-        na_value = self.dtype.na_value
+        na_value = self.dtype.na_value  # type: ignore[attr-defined]
 
         if not expand: