update

Author: TomAugspurger

pandas/_libs/lib.pyx

@@ -49,7 +49,6 @@ cdef extern from "src/parse_helper.h":
     int floatify(object, float64_t *result, int *maybe_int) except -1
 
 cimport pandas._libs.util as util
-from pandas.core.na_scalar import NA
 from pandas._libs.util cimport is_nan, UINT64_MAX, INT64_MAX, INT64_MIN
 
 from pandas._libs.tslib import array_to_datetime
@@ -156,7 +155,6 @@ def is_scalar(val: object) -> bool:
 
     return (cnp.PyArray_IsAnyScalar(val)
             # PyArray_IsAnyScalar is always False for bytearrays on Py3
-            or val is NA
             or PyDate_Check(val)
             or PyDelta_Check(val)
             or PyTime_Check(val)
@@ -1502,7 +1500,7 @@ cdef class Validator:
                                   f'must define is_value_typed')
 
     cdef bint is_valid_null(self, object value) except -1:
-        return value is None or value is NA or util.is_nan(value)
+        return value is None or value is C_NA or util.is_nan(value)
 
     cdef bint is_array_typed(self) except -1:
         return False

pandas/_libs/testing.pyx

@@ -180,13 +180,15 @@ cpdef assert_almost_equal(a, b,
         # classes can't be the same, to raise error
         assert_class_equal(a, b, obj=obj)
 
-    if a == b:
-        # object comparison
-        return True
     if isna(a) and isna(b):
         # TODO: Should require same-dtype NA?
         # nan / None comparison
         return True
+
+    if a == b:
+        # object comparison
+        return True
+
     if is_comparable_as_number(a) and is_comparable_as_number(b):
         if array_equivalent(a, b, strict_nan=True):
             # inf comparison

pandas/_libs/tslibs/nattype.pyx

@@ -12,7 +12,6 @@ cimport numpy as cnp
 from numpy cimport int64_t
 cnp.import_array()
 
-from pandas.core.na_scalar import NA
 from pandas._libs.tslibs.np_datetime cimport (
     get_datetime64_value, get_timedelta64_value)
 cimport pandas._libs.tslibs.util as util
@@ -800,8 +799,6 @@ cpdef bint is_null_datetimelike(object val, bint inat_is_null=True):
     """
     if val is None:
         return True
-    elif val is NA:
-        return True
     elif val is c_NaT:
         return True
     elif util.is_float_object(val) or util.is_complex_object(val):

pandas/core/arrays/string_.py

@@ -3,7 +3,7 @@
 
 import numpy as np
 
-from pandas._libs import lib
+from pandas._libs import lib, missing as libmissing
 
 from pandas.core.dtypes.base import ExtensionDtype
 from pandas.core.dtypes.common import is_float_dtype, pandas_dtype
@@ -16,7 +16,6 @@
 from pandas.core.arrays import PandasArray
 from pandas.core.construction import extract_array
 from pandas.core.missing import isna
-from pandas.core.na_scalar import NA
 
 
 @register_extension_dtype
@@ -49,7 +48,7 @@ class StringDtype(ExtensionDtype):
     """
 
     #: StringDtype.na_value uses pandas.NA
-    na_value = NA
+    na_value = libmissing.NA
 
     @property
     def type(self) -> Type:
@@ -202,13 +201,16 @@ def __setitem__(self, key, value):
         # validate new items
         if scalar_value:
             if (
-                value is NA
+                value is libmissing.NA
                 or value is None
-                or is_float_dtype(value)
-                and np.isnan(value)
+                or (
+                    is_float_dtype(value)
+                    and not isinstance(value, str)
+                    and np.isnan(value)
+                )
             ):
                 value = StringDtype.na_value
-            elif not (isinstance(value, str) or (value is NA)):
+            elif not (isinstance(value, str) or (value is libmissing.NA)):
                 raise ValueError(
                     "Cannot set non-string value '{}' into a StringArray.".format(value)
                 )

pandas/core/dtypes/missing.py

@@ -9,7 +9,6 @@
 import pandas._libs.missing as libmissing
 from pandas._libs.tslibs import NaT, iNaT
 
-from ..na_scalar import NA
 from .common import (
     _NS_DTYPE,
     _TD_DTYPE,
@@ -441,7 +440,7 @@ def array_equivalent(left, right, strict_nan=False):
             if left_value is NaT and right_value is not NaT:
                 return False
 
-            elif left_value is NA and right_value is not NA:
+            elif left_value is libmissing.NA and right_value is not libmissing.NA:
                 return False
 
             elif isinstance(left_value, float) and np.isnan(left_value):
@@ -455,6 +454,8 @@ def array_equivalent(left, right, strict_nan=False):
                     if "Cannot compare tz-naive" in str(err):
                         # tzawareness compat failure, see GH#28507
                         return False
+                    elif "boolean value of NA is ambiguous" in str(err):
+                        return False
                     raise
         return True
 

pandas/tests/arrays/string_/test_string.py

@@ -24,6 +24,15 @@ def test_setitem_validates():
         a[:] = np.array([1, 2])
 
 
+def test_setitem_with_scalar_string():
+    # is_float_dtype considers some strings, like 'd', to be floats
+    # which can cause issues.
+    arr = pd.array(["a", "c"], dtype="string")
+    arr[0] = "d"
+    expected = pd.array(["d", "c"], dtype="string")
+    tm.assert_extension_array_equal(arr, expected)
+
+
 @pytest.mark.parametrize(
     "input, method",
     [