Use ensure_string_array in also in construct_1d_ndarray_preserving_na

Author: topper-123

pandas/_libs/lib.pyx

@@ -1698,18 +1698,46 @@ cpdef bint is_string_array(ndarray values, bint skipna=False):
     return validator.validate(values)
 
 
-cpdef ndarray ensure_string_array(ndarray values, object na_value):
+cpdef ndarray ensure_string_array(
+        values, object na_value=np.nan, bint convert_na_value=True, bint copy=True):
+    """Returns a new numpy array with object dtype and only strings and na values.
+    
+    Parameters
+    ---------
+    values : array-like
+        The values to be converted to str, if needed
+    na_value : Any
+        The value to use for na. For example, np.nan or pd.NAN
+    convert_na_value : bool, default True
+        If False, existing na values will be used unchanged in the new array
+    copy : bool, default True
+        Whether to wnsure that a new array is returned
+
+    Returns
+    -------
+    ndarray    
+    """
     cdef:
         Py_ssize_t i = 0, n = len(values)
 
-    for i in range(n):
-        val = values[i]
-        if not checknull(val):
-            values[i] = str(val)
-        else:
-            values[i] = na_value
+    result = np.asarray(values, dtype="object")
+    if copy and result is values:
+        result = result.copy()
 
-    return values
+    if convert_na_value:
+        for i in range(n):
+            val = result[i]
+            if not checknull(val):
+                result[i] = str(val)
+            else:
+                result[i] = na_value
+    else:
+        for i in range(n):
+            val = result[i]
+            if not checknull(val):
+                result[i] = str(val)
+
+    return result
 
 
 cdef class BytesValidator(Validator):

pandas/core/arrays/string_.py

@@ -199,11 +199,10 @@ def _from_sequence(cls, scalars, dtype=None, copy=True):
             assert dtype == "string"
 
         result = np.asarray(scalars, dtype="object")
-        if copy and result is scalars:
-            result = result.copy()
 
         # convert non-na-likes to str, and nan-likes to StringDtype.na_value
-        result = lib.ensure_string_array(result, StringDtype.na_value)
+        result = lib.ensure_string_array(
+            result, na_value=StringDtype.na_value, copy=copy)
 
         return cls(result)
 

pandas/core/dtypes/cast.py

@@ -1608,19 +1608,11 @@ def construct_1d_ndarray_preserving_na(
     >>> construct_1d_ndarray_preserving_na([1.0, 2.0, None], dtype=np.dtype('str'))
     array(['1.0', '2.0', None], dtype=object)
     """
-    subarr = np.array(values, dtype=dtype, copy=copy)
 
     if dtype is not None and dtype.kind == "U":
-        # GH-21083
-        # We can't just return np.array(subarr, dtype='str') since
-        # NumPy will convert the non-string objects into strings
-        # Including NA values. Se we have to go
-        # string -> object -> update NA, which requires an
-        # additional pass over the data.
-        na_values = isna(values)
-        subarr2 = subarr.astype(object)
-        subarr2[na_values] = np.asarray(values, dtype=object)[na_values]
-        subarr = subarr2
+        subarr = lib.ensure_string_array(values, convert_na_value=False, copy=copy)
+    else:
+        subarr = np.array(values, dtype=dtype, copy=copy)
 
     return subarr