delete libs_.lib.astype_str

Author: topper-123

pandas/_libs/lib.pyx

@@ -618,35 +618,52 @@ def astype_intsafe(ndarray[object] arr, new_dtype):
 
 @cython.wraparound(False)
 @cython.boundscheck(False)
-def astype_str(arr: ndarray, skipna: bool=False) -> ndarray[object]:
-    """
-    Convert all elements in an array to string.
+cpdef ndarray[object] ensure_string_array(
+        ndarray[object] arr,
+        object na_value=np.nan,
+        bint convert_na_value=True,
+        bint copy=True,
+        bint skipna=True,
+):
+    """Returns a new numpy array with object dtype and only strings and na values.
 
     Parameters
     ----------
-    arr : ndarray
-        The array whose elements we are casting.
-    skipna : bool, default False
+    arr : 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.NA.
+    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 ensure that a new array is returned.
+    skipna : bool, default True
         Whether or not to coerce nulls to their stringified form
-        (e.g. NaN becomes 'nan').
+        (e.g. if False, NaN becomes 'nan').
 
     Returns
     -------
     ndarray
-        A new array with the input array's elements casted.
+        An array with the input array's elements casted to str or nan-like.
     """
     cdef:
-        object arr_i
-        Py_ssize_t i, n = arr.size
-        ndarray[object] result = np.empty(n, dtype=object)
-
-    for i in range(n):
-        arr_i = arr[i]
+        Py_ssize_t i = 0, n = len(arr)
 
-        if not (skipna and checknull(arr_i)):
-            arr_i = str(arr_i)
+    result = np.asarray(arr, dtype="object")
+    if copy and result is arr:
+        result = result.copy()
 
-        result[i] = arr_i
+    for i in range(n):
+        val = result[i]
+        if not checknull(val):
+            result[i] = str(val)
+        else:
+            if convert_na_value:
+                val = na_value
+            if skipna:
+                result[i] = val
+            else:
+                result[i] = str(val)
 
     return result
 
@@ -1698,48 +1715,6 @@ cpdef bint is_string_array(ndarray values, bint skipna=False):
     return validator.validate(values)
 
 
-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.NA.
-    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 ensure that a new array is returned.
-
-    Returns
-    -------
-    ndarray
-    """
-    cdef:
-        Py_ssize_t i = 0, n = len(values)
-
-    result = np.asarray(values, dtype="object")
-    if copy and result is values:
-        result = result.copy()
-
-    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):
     cdef inline bint is_value_typed(self, object value) except -1:
         return isinstance(value, bytes)

pandas/core/dtypes/cast.py

@@ -916,7 +916,7 @@ def astype_nansafe(arr, dtype, copy: bool = True, skipna: bool = False):
         dtype = pandas_dtype(dtype)
 
     if issubclass(dtype.type, str):
-        return lib.astype_str(arr.ravel(), skipna=skipna).reshape(arr.shape)
+        return lib.ensure_string_array(arr.ravel(), skipna=skipna).reshape(arr.shape)
 
     elif is_datetime64_dtype(arr):
         if is_object_dtype(dtype):
@@ -1610,6 +1610,7 @@ def construct_1d_ndarray_preserving_na(
     """
 
     if dtype is not None and dtype.kind == "U":
+        values = np.asarray(values, dtype="object")
         subarr = lib.ensure_string_array(values, convert_na_value=False, copy=copy)
     else:
         subarr = np.array(values, dtype=dtype, copy=copy)