def _get_series_array_type(dtype):
"""get underlying default array type of series based on its dtype
"""
# list(list(str))
if dtype == types.List(string_type):
# default data layout is list but split view is used if possible
return list_string_array_type
# string array
elif dtype == string_type:
return string_array_type
# categorical
if isinstance(dtype, PDCategoricalDtype):
return CategoricalArray(dtype)
# use recarray data layout for series of tuples
if isinstance(dtype, types.BaseTuple):
if any(not isinstance(t, types.Number) for t in dtype.types):
# TODO: support more types. what types can be in recarrays?
raise ValueError(
"series tuple dtype {} includes non-numerics".format(dtype))
np_dtype = np.dtype(','.join(str(t) for t in dtype.types), align=True)
dtype = numba.numpy_support.from_dtype(np_dtype)
# TODO: other types?
# regular numpy array
return types.Array(dtype, 1, 'C')
def _get_dtype_str(t):
dtype = t.dtype
if isinstance(dtype, PDCategoricalDtype):
cat_arr = CategoricalArray(dtype)
# HACK: add cat type to numba.types
# FIXME: fix after Numba #3372 is resolved
cat_arr_name = 'CategoricalArray' + str(ir_utils.next_label())
setattr(types, cat_arr_name, cat_arr)
return cat_arr_name
if dtype == types.NPDatetime('ns'):
dtype = 'NPDatetime("ns")'
if t == string_array_type:
# HACK: add string_array_type to numba.types
# FIXME: fix after Numba #3372 is resolved
types.string_array_type = string_array_type
return 'string_array_type'
return '{}[::1]'.format(dtype)