Cython Unicode Method Cleanups (pandas-dev#26138)

Author: WillAyd

pandas/_libs/lib.pyx

@@ -549,41 +549,6 @@ def astype_intsafe(ndarray[object] arr, new_dtype):
     return result
 
 
-@cython.wraparound(False)
-@cython.boundscheck(False)
-def astype_unicode(arr: ndarray, skipna: bool=False) -> ndarray[object]:
-    """
-    Convert all elements in an array to unicode.
-
-    Parameters
-    ----------
-    arr : ndarray
-        The array whose elements we are casting.
-    skipna : bool, default False
-        Whether or not to coerce nulls to their stringified form
-        (e.g. NaN becomes 'nan').
-
-    Returns
-    -------
-    casted_arr : ndarray
-        A new array with the input array's elements casted.
-    """
-    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]
-
-        if not (skipna and checknull(arr_i)):
-            arr_i = unicode(arr_i)
-
-        result[i] = arr_i
-
-    return result
-
-
 @cython.wraparound(False)
 @cython.boundscheck(False)
 def astype_str(arr: ndarray, skipna: bool=False) -> ndarray[object]:
@@ -1321,10 +1286,6 @@ def infer_dtype(value: object, skipna: object=None) -> str:
         if is_string_array(values, skipna=skipna):
             return 'string'
 
-    elif isinstance(val, unicode):
-        if is_unicode_array(values, skipna=skipna):
-            return 'unicode'
-
     elif isinstance(val, bytes):
         if is_bytes_array(values, skipna=skipna):
             return 'bytes'
@@ -1596,22 +1557,6 @@ cpdef bint is_string_array(ndarray values, bint skipna=False):
     return validator.validate(values)
 
 
-cdef class UnicodeValidator(Validator):
-    cdef inline bint is_value_typed(self, object value) except -1:
-        return isinstance(value, unicode)
-
-    cdef inline bint is_array_typed(self) except -1:
-        return issubclass(self.dtype.type, np.unicode_)
-
-
-cdef bint is_unicode_array(ndarray values, bint skipna=False):
-    cdef:
-        UnicodeValidator validator = UnicodeValidator(len(values),
-                                                      values.dtype,
-                                                      skipna=skipna)
-    return validator.validate(values)
-
-
 cdef class BytesValidator(Validator):
     cdef inline bint is_value_typed(self, object value) except -1:
         return isinstance(value, bytes)

pandas/core/dtypes/cast.py

@@ -636,10 +636,6 @@ def astype_nansafe(arr, dtype, copy=True, skipna=False):
         dtype = pandas_dtype(dtype)
 
     if issubclass(dtype.type, str):
-        return lib.astype_unicode(arr.ravel(),
-                                  skipna=skipna).reshape(arr.shape)
-
-    elif issubclass(dtype.type, str):
         return lib.astype_str(arr.ravel(),
                               skipna=skipna).reshape(arr.shape)