def _box_series_data(dtype, data_typ, val, c):
if isinstance(dtype, types.BaseTuple):
np_dtype = np.dtype(','.join(str(t) for t in dtype.types), align=True)
dtype = numba.numpy_support.from_dtype(np_dtype)
if dtype == string_type:
arr = box_str_arr(string_array_type, val, c)
elif dtype == datetime_date_type:
arr = box_datetime_date_array(data_typ, val, c)
elif isinstance(dtype, PDCategoricalDtype):
arr = box_categorical_array(data_typ, val, c)
elif data_typ == string_array_split_view_type:
arr = box_str_arr_split_view(data_typ, val, c)
elif dtype == types.List(string_type):
arr = box_list(list_string_array_type, val, c)
else:
arr = box_array(data_typ, val, c)
if isinstance(dtype, types.Record):
o_str = c.context.insert_const_string(c.builder.module, "O")
o_str = c.pyapi.string_from_string(o_str)
arr = c.pyapi.call_method(arr, "astype", (o_str, ))
return arr
def box_dataframe(typ, val, c):
context = c.context
builder = c.builder
n_cols = len(typ.columns)
col_names = typ.columns
arr_typs = typ.data
dtypes = [a.dtype for a in arr_typs] # TODO: check Categorical
dataframe = cgutils.create_struct_proxy(typ)(context, builder, value=val)
col_arrs = [
builder.extract_value(dataframe.data, i) for i in range(n_cols)
]
# df unboxed from Python
has_parent = cgutils.is_not_null(builder, dataframe.parent)
pyapi = c.pyapi
# gil_state = pyapi.gil_ensure() # acquire GIL
mod_name = context.insert_const_string(c.builder.module, "pandas")
class_obj = pyapi.import_module_noblock(mod_name)
df_obj = pyapi.call_method(class_obj, "DataFrame", ())
for i, cname, arr, arr_typ, dtype in zip(range(n_cols), col_names,
col_arrs, arr_typs, dtypes):
# df['cname'] = boxed_arr
# TODO: datetime.date, DatetimeIndex?
name_str = context.insert_const_string(c.builder.module, cname)
cname_obj = pyapi.string_from_string(name_str)
if dtype == string_type:
arr_obj = box_str_arr(arr_typ, arr, c)
elif isinstance(dtype, PDCategoricalDtype):
arr_obj = box_categorical_array(arr_typ, arr, c)
# context.nrt.incref(builder, arr_typ, arr)
elif arr_typ == string_array_split_view_type:
arr_obj = box_str_arr_split_view(arr_typ, arr, c)
elif dtype == types.List(string_type):
arr_obj = box_list(list_string_array_type, arr, c)
# context.nrt.incref(builder, arr_typ, arr) # TODO required?
# pyapi.print_object(arr_obj)
else:
arr_obj = box_array(arr_typ, arr, c)
# TODO: is incref required?
# context.nrt.incref(builder, arr_typ, arr)
pyapi.object_setitem(df_obj, cname_obj, arr_obj)
# pyapi.decref(arr_obj)
pyapi.decref(cname_obj)
# set df.index if necessary
if typ.index != types.none:
arr_obj = _box_series_data(typ.index.dtype, typ.index, dataframe.index,
c)
pyapi.object_setattr_string(df_obj, 'index', arr_obj)
pyapi.decref(class_obj)
# pyapi.gil_release(gil_state) # release GIL
return df_obj
def _box_index_data(index_typ, val, c):
""" Boxes native value used to represent Pandas index into appropriate Python object.
Params:
index_typ: Numba type of native value
val: native value
c: LLVM context object
Returns: Python object native value is boxed into
"""
assert isinstance(index_typ, (RangeIndexType, StringArrayType, types.Array, types.NoneType))
if isinstance(index_typ, RangeIndexType):
index = box_range_index(index_typ, val, c)
elif isinstance(index_typ, types.Array):
index = box_array(index_typ, val, c)
elif isinstance(index_typ, StringArrayType):
index = box_str_arr(string_array_type, val, c)
else: # index_typ is types.none
index = c.pyapi.make_none()
return index