def unbox_dataframe(typ, val, c):
"""unbox dataframe to an empty DataFrame struct
columns will be extracted later if necessary.
"""
n_cols = len(typ.columns)
column_strs = [
numba.unicode.make_string_from_constant(c.context, c.builder,
string_type, a)
for a in typ.columns
]
# create dataframe struct and store values
dataframe = cgutils.create_struct_proxy(typ)(c.context, c.builder)
column_tup = c.context.make_tuple(c.builder,
types.UniTuple(string_type, n_cols),
column_strs)
# this unboxes all DF columns so that no column unboxing occurs later
for col_ind in range(n_cols):
series_obj = c.pyapi.object_getattr_string(val, typ.columns[col_ind])
arr_obj = c.pyapi.object_getattr_string(series_obj, "values")
ty_series = typ.data[col_ind]
if isinstance(ty_series, types.Array):
native_val = unbox_array(typ.data[col_ind], arr_obj, c)
elif ty_series == string_array_type:
native_val = unbox_str_series(string_array_type, series_obj, c)
dataframe.data = c.builder.insert_value(dataframe.data,
native_val.value, col_ind)
# TODO: support unboxing index
if typ.index == types.none:
dataframe.index = c.context.get_constant(types.none, None)
if typ.index == string_array_type:
index_obj = c.pyapi.object_getattr_string(val, "index")
dataframe.index = unbox_str_series(string_array_type, index_obj,
c).value
if isinstance(typ.index, types.Array):
index_obj = c.pyapi.object_getattr_string(val, "index")
index_data = c.pyapi.object_getattr_string(index_obj, "_data")
dataframe.index = unbox_array(typ.index, index_data, c).value
dataframe.columns = column_tup
dataframe.parent = val
# increase refcount of stored values
if c.context.enable_nrt:
# TODO: other objects?
for var in column_strs:
c.context.nrt.incref(c.builder, string_type, var)
return NativeValue(dataframe._getvalue())
def _unbox_index_data(index_typ, index_obj, c):
""" Unboxes Pandas index object basing on the native type inferred previously.
Params:
index_typ: native Numba type the object is to be unboxed into
index_obj: Python object to be unboxed
c: LLVM context object
Returns: LLVM instructions to generate native value
"""
if isinstance(index_typ, RangeIndexType):
return unbox_range_index(index_typ, index_obj, c)
if isinstance(index_typ, Int64IndexType):
return unbox_int64_index(index_typ, index_obj, c)
if index_typ == string_array_type:
return unbox_str_series(index_typ, index_obj, c)
# this is still here only because of Float64Index represented as array
# TO-DO: remove when it's added
if isinstance(index_typ, types.Array):
index_data = c.pyapi.object_getattr_string(index_obj, "_data")
res = unbox_array(index_typ, index_data, c)
c.pyapi.decref(index_data)
return res
if isinstance(index_typ, types.NoneType):
return unbox_none(index_typ, index_obj, c)
assert False, f"_unbox_index_data: unexpected index type({index_typ}) while unboxing"
def _unbox_series_data(dtype, data_typ, arr_obj, c):
if data_typ == string_array_type:
return unbox_str_series(string_array_type, arr_obj, c)
elif data_typ == list_string_array_type:
return _unbox_array_list_str(arr_obj, c)
elif isinstance(dtype, CategoricalDtypeType):
return unbox_Categorical(data_typ, arr_obj, c)
# TODO: error handling like Numba callwrappers.py
return unbox_array(data_typ, arr_obj, c)
def _unbox_series_data(dtype, data_typ, arr_obj, c):
if data_typ == string_array_type:
return unbox_str_series(string_array_type, arr_obj, c)
elif dtype == datetime_date_type:
return unbox_datetime_date_array(data_typ, arr_obj, c)
elif data_typ == list_string_array_type:
return _unbox_array_list_str(arr_obj, c)
elif data_typ == string_array_split_view_type:
# XXX dummy unboxing to avoid errors in _get_dataframe_data()
out_view = c.context.make_helper(c.builder,
string_array_split_view_type)
return NativeValue(out_view._getvalue())
elif isinstance(dtype, PDCategoricalDtype):
return unbox_categorical_array(data_typ, arr_obj, c)
# TODO: error handling like Numba callwrappers.py
return unbox_array(data_typ, arr_obj, c)
def unbox_dataframe(typ, val, c):
"""unbox dataframe to an empty DataFrame struct
columns will be extracted later if necessary.
"""
n_cols = len(typ.columns)
column_strs = [
numba.unicode.make_string_from_constant(c.context, c.builder,
string_type, a)
for a in typ.columns
]
# create dataframe struct and store values
dataframe = cgutils.create_struct_proxy(typ)(c.context, c.builder)
column_tup = c.context.make_tuple(c.builder,
types.UniTuple(string_type, n_cols),
column_strs)
zero = c.context.get_constant(types.int8, 0)
unboxed_tup = c.context.make_tuple(c.builder,
types.UniTuple(types.int8, n_cols + 1),
[zero] * (n_cols + 1))
# TODO: support unboxing index
if typ.index == types.none:
dataframe.index = c.context.get_constant(types.none, None)
if typ.index == string_array_type:
index_obj = c.pyapi.object_getattr_string(val, "index")
dataframe.index = unbox_str_series(string_array_type, index_obj,
c).value
if isinstance(typ.index, types.Array):
index_obj = c.pyapi.object_getattr_string(val, "index")
index_data = c.pyapi.object_getattr_string(index_obj, "_data")
dataframe.index = unbox_array(typ.index, index_data, c).value
dataframe.columns = column_tup
dataframe.unboxed = unboxed_tup
dataframe.parent = val
# increase refcount of stored values
if c.context.enable_nrt:
# TODO: other objects?
for var in column_strs:
c.context.nrt.incref(c.builder, string_type, var)
return NativeValue(dataframe._getvalue())
def unbox_series(typ, val, c):
arr_obj = c.pyapi.object_getattr_string(val, "values")
series = cgutils.create_struct_proxy(typ)(c.context, c.builder)
series.data = _unbox_series_data(typ.dtype, typ.data, arr_obj, c).value
# TODO: other indices
if typ.index == string_array_type:
index_obj = c.pyapi.object_getattr_string(val, "index")
series.index = unbox_str_series(string_array_type, index_obj, c).value
if isinstance(typ.index, types.Array):
index_obj = c.pyapi.object_getattr_string(val, "index")
index_data = c.pyapi.object_getattr_string(index_obj, "_data")
series.index = unbox_array(typ.index, index_data, c).value
if typ.is_named:
name_obj = c.pyapi.object_getattr_string(val, "name")
series.name = numba.unicode.unbox_unicode_str(string_type, name_obj,
c).value
# TODO: handle index and name
c.pyapi.decref(arr_obj)
return NativeValue(series._getvalue())
def unbox_dataframe(typ, val, c):
"""unbox dataframe to an empty DataFrame struct
columns will be extracted later if necessary.
"""
n_cols = len(typ.columns)
column_strs = [
numba.cpython.unicode.make_string_from_constant(
c.context, c.builder, string_type, a) for a in typ.columns
]
# create dataframe struct and store values
dataframe = cgutils.create_struct_proxy(typ)(c.context, c.builder)
errorptr = cgutils.alloca_once_value(c.builder, cgutils.false_bit)
col_list_type = types.List(string_type)
ok, inst = listobj.ListInstance.allocate_ex(c.context, c.builder,
col_list_type, n_cols)
with c.builder.if_else(ok, likely=True) as (if_ok, if_not_ok):
with if_ok:
inst.size = c.context.get_constant(types.intp, n_cols)
for i, column_str in enumerate(column_strs):
inst.setitem(c.context.get_constant(types.intp, i),
column_str,
incref=False)
dataframe.columns = inst.value
with if_not_ok:
c.builder.store(cgutils.true_bit, errorptr)
# If an error occurred, drop the whole native list
with c.builder.if_then(c.builder.load(errorptr)):
c.context.nrt.decref(c.builder, col_list_type, inst.value)
_, data_typs_map, types_order = get_structure_maps(typ.data, typ.columns)
for col_typ in types_order:
type_id, col_indices = data_typs_map[col_typ]
n_type_cols = len(col_indices)
list_type = types.List(col_typ)
ok, inst = listobj.ListInstance.allocate_ex(c.context, c.builder,
list_type, n_type_cols)
with c.builder.if_else(ok, likely=True) as (if_ok, if_not_ok):
with if_ok:
inst.size = c.context.get_constant(types.intp, n_type_cols)
for i, col_idx in enumerate(col_indices):
series_obj = c.pyapi.object_getattr_string(
val, typ.columns[col_idx])
arr_obj = c.pyapi.object_getattr_string(
series_obj, "values")
ty_series = typ.data[col_idx]
if isinstance(ty_series, types.Array):
native_val = unbox_array(typ.data[col_idx], arr_obj, c)
elif ty_series == string_array_type:
native_val = unbox_str_series(string_array_type,
series_obj, c)
inst.setitem(c.context.get_constant(types.intp, i),
native_val.value,
incref=False)
dataframe.data = c.builder.insert_value(
dataframe.data, inst.value, type_id)
with if_not_ok:
c.builder.store(cgutils.true_bit, errorptr)
# If an error occurred, drop the whole native list
with c.builder.if_then(c.builder.load(errorptr)):
c.context.nrt.decref(c.builder, list_type, inst.value)
index_obj = c.pyapi.object_getattr_string(val, "index")
dataframe.index = _unbox_index_data(typ.index, index_obj, c).value
c.pyapi.decref(index_obj)
dataframe.parent = val
# increase refcount of stored values
if c.context.enable_nrt:
# TODO: other objects?
for var in column_strs:
c.context.nrt.incref(c.builder, string_type, var)
return NativeValue(dataframe._getvalue(),
is_error=c.builder.load(errorptr))
