From ecc451d6ff0934ac88ead3875d092d0841ecc0c1 Mon Sep 17 00:00:00 2001
From: jbrockmendel <jbrockmendel@gmail.com>
Date: Fri, 9 Aug 2024 14:13:06 -0700
Subject: [PATCH] REF (string): de-duplicate str_map_nan_semantics (#59464)

REF: de-duplicate str_map_nan_semantics
---
 pandas/core/arrays/string_.py      |  9 ++++---
 pandas/core/arrays/string_arrow.py | 42 ------------------------------
 2 files changed, 5 insertions(+), 46 deletions(-)

diff --git a/pandas/core/arrays/string_.py b/pandas/core/arrays/string_.py
index 94d49c4fdf6e6..2ba7c9fccbfce 100644
--- a/pandas/core/arrays/string_.py
+++ b/pandas/core/arrays/string_.py
@@ -395,7 +395,7 @@ def _str_map(
             return constructor(result, mask)
 
         else:
-            return self._str_map_str_or_object(dtype, na_value, arr, f, mask, convert)
+            return self._str_map_str_or_object(dtype, na_value, arr, f, mask)
 
     def _str_map_str_or_object(
         self,
@@ -404,7 +404,6 @@ def _str_map_str_or_object(
         arr: np.ndarray,
         f,
         mask: npt.NDArray[np.bool_],
-        convert: bool,
     ):
         # _str_map helper for case where dtype is either string dtype or object
         if is_string_dtype(dtype) and not is_object_dtype(dtype):
@@ -438,7 +437,6 @@ def _str_map_nan_semantics(
 
         mask = isna(self)
         arr = np.asarray(self)
-        convert = convert and not np.all(mask)
 
         if is_integer_dtype(dtype) or is_bool_dtype(dtype):
             na_value_is_na = isna(na_value)
@@ -457,6 +455,9 @@ def _str_map_nan_semantics(
                 dtype=np.dtype(cast(type, dtype)),
             )
             if na_value_is_na and mask.any():
+                # TODO: we could alternatively do this check before map_infer_mask
+                #  and adjust the dtype/na_value we pass there. Which is more
+                #  performant?
                 if is_integer_dtype(dtype):
                     result = result.astype("float64")
                 else:
@@ -465,7 +466,7 @@ def _str_map_nan_semantics(
             return result
 
         else:
-            return self._str_map_str_or_object(dtype, na_value, arr, f, mask, convert)
+            return self._str_map_str_or_object(dtype, na_value, arr, f, mask)
 
 
 # error: Definition of "_concat_same_type" in base class "NDArrayBacked" is
diff --git a/pandas/core/arrays/string_arrow.py b/pandas/core/arrays/string_arrow.py
index fdb0259230c7f..cc37995969f0a 100644
--- a/pandas/core/arrays/string_arrow.py
+++ b/pandas/core/arrays/string_arrow.py
@@ -6,7 +6,6 @@
 from typing import (
     TYPE_CHECKING,
     Union,
-    cast,
 )
 
 import numpy as np
@@ -23,8 +22,6 @@
 )
 
 from pandas.core.dtypes.common import (
-    is_bool_dtype,
-    is_integer_dtype,
     is_scalar,
     pandas_dtype,
 )
@@ -281,45 +278,6 @@ def astype(self, dtype, copy: bool = True):
 
     _str_map = BaseStringArray._str_map
 
-    def _str_map_nan_semantics(
-        self, f, na_value=None, dtype: Dtype | None = None, convert: bool = True
-    ):
-        if dtype is None:
-            dtype = self.dtype
-        if na_value is None:
-            na_value = self.dtype.na_value
-
-        mask = isna(self)
-        arr = np.asarray(self)
-
-        if is_integer_dtype(dtype) or is_bool_dtype(dtype):
-            if is_integer_dtype(dtype):
-                na_value = np.nan
-            else:
-                na_value = False
-
-            dtype = np.dtype(cast(type, dtype))
-            if mask.any():
-                # numpy int/bool dtypes cannot hold NaNs so we must convert to
-                # float64 for int (to match maybe_convert_objects) or
-                # object for bool (again to match maybe_convert_objects)
-                if is_integer_dtype(dtype):
-                    dtype = np.dtype("float64")
-                else:
-                    dtype = np.dtype(object)
-            result = lib.map_infer_mask(
-                arr,
-                f,
-                mask.view("uint8"),
-                convert=False,
-                na_value=na_value,
-                dtype=dtype,
-            )
-            return result
-
-        else:
-            return self._str_map_str_or_object(dtype, na_value, arr, f, mask, convert)
-
     def _str_contains(
         self, pat, case: bool = True, flags: int = 0, na=np.nan, regex: bool = True
     ):