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_categorical_array(typ, val, c):
arr_obj = c.pyapi.object_getattr_string(val, "codes")
# c.pyapi.print_object(arr_obj)
dtype = get_categories_int_type(typ.dtype)
native_val = unbox_array(types.Array(dtype, 1, 'C'), arr_obj, c)
c.pyapi.decref(arr_obj)
return native_val
def lower_unbox_df_column(context, builder, sig, args):
# FIXME: last arg should be types.DType?
pyapi = context.get_python_api(builder)
c = numba.pythonapi._UnboxContext(context, builder, pyapi)
# TODO: refcounts?
col_ind = sig.args[1].value
col_name = sig.args[0].col_names[col_ind]
series_obj = c.pyapi.object_getattr_string(args[0], col_name)
arr_obj = c.pyapi.object_getattr_string(series_obj, "values")
if isinstance(sig.args[2],
types.Const) and sig.args[2].value == 11: # FIXME: str code
native_val = unbox_str_series(string_array_type, arr_obj, c)
else:
if isinstance(
sig.args[2],
types.Const) and sig.args[2].value == 12: # FIXME: dt64 code
dtype = types.NPDatetime('ns')
else:
dtype = sig.args[2].dtype
# TODO: error handling like Numba callwrappers.py
native_val = unbox_array(types.Array(dtype=dtype, ndim=1, layout='C'),
arr_obj, c)
c.pyapi.decref(series_obj)
c.pyapi.decref(arr_obj)
return native_val.value
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, 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_series(typ, val, c):
arr_obj = c.pyapi.object_getattr_string(val, "values")
if typ.dtype == string_type:
native_val = unbox_str_series(string_array_type, arr_obj, c)
elif typ.dtype == datetime_date_type:
native_val = unbox_datetime_date_array(typ, val, c)
else:
# TODO: error handling like Numba callwrappers.py
native_val = unbox_array(types.Array(dtype=typ.dtype, ndim=1, layout='C'), arr_obj, c)
c.pyapi.decref(arr_obj)
return native_val
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())
