def pd_multi_index_from_product_impl(cls,
iterables,
sortorder=None,
names=None):
# TO-DO: support indexes.unique() method and use it here
levels_factorized = sdc_tuple_map(factorize_level, iterables)
levels_names = sdc_tuple_map(sdc_indexes_get_name, iterables)
index_levels = sdc_tuple_map(lambda x: fix_df_index(list(x[0])),
levels_factorized)
temp_cumprod_sizes = [
1,
]
codes_info = sdc_tuple_map(next_codes_info, levels_factorized,
temp_cumprod_sizes)
res_index_size = temp_cumprod_sizes[-1]
index_codes = sdc_tuple_map(next_codes_array, codes_info,
res_index_size)
res = sdc_pandas_multi_index_ctor(index_levels,
index_codes,
name=levels_names)
return res
def pd_multi_index_getitem_idx_bool_array_impl(self, idx):
new_levels = self._levels
new_codes = sdc_tuple_map(
lambda arr_codes, taken_idxs: numpy_like.getitem_by_mask(
arr_codes, taken_idxs), self._codes, idx)
return pd.MultiIndex(new_levels, new_codes)
def pd_multi_index_getitem_idx_slice_impl(self, idx):
new_levels = self._levels
new_codes = sdc_tuple_map(
lambda arr_codes, taken_idxs: arr_codes[taken_idxs],
self._codes, idx)
return pd.MultiIndex(new_levels, new_codes)
def pd_multi_index_ctor_impl(levels,
codes,
sortorder=None,
names=None,
dtype=None,
copy=False,
name=None):
if len(levels) != len(codes):
raise ValueError("Length of levels and codes must be the same.")
if len(levels) == 0:
raise ValueError("Must pass non-zero number of levels/codes")
# if name is None then all level names are reset
if is_name_none == True: # noqa
_names = sdc_tuple_map(
lambda x: None,
levels,
)
else:
_names = name
levels_and_codes_pairs = sdc_tuple_map_elementwise(
_multi_index_create_levels_and_codes, levels, codes, _names)
_levels, _codes = sdc_tuple_unzip(levels_and_codes_pairs)
return init_multi_index(_levels, _codes)
def pd_multi_index_append_impl(self, other):
self_and_other_data = _multi_index_binop_helper(self, other)
tup_append_level_res = sdc_tuple_map(
lambda x: _multi_index_append_level(*x), self_and_other_data)
new_levels, new_codes = sdc_tuple_unzip(tup_append_level_res)
return pd.MultiIndex(levels=new_levels, codes=new_codes)
def pd_multi_index_names_impl(self):
levels_names = sdc_tuple_map(lambda x: x.name, self._levels)
# this exploits undesired side-effect of literal_unroll - type-unification
# of resulting list dtype that will be types.Optional(types.unicode_type)
# as using typed.List of Optional values currently fails to compile
res = []
for i in literal_unroll(levels_names):
res.append(i)
return res
def pd_multi_index_type_from_tuples_impl(cls, iterables):
index_size = len(iterables)
if not index_size:
raise TypeError("Cannot infer number of levels from empty list")
# use first value to infer types and allocate dicts for result multi index levels
example_value = iterables[0]
levels_dicts = sdc_tuple_map(_multi_index_alloc_level_dict,
example_value)
index_codes = sdc_tuple_map(
lambda _, size: np.empty(size, dtype=types.int64), example_value,
index_size)
for i, val in enumerate(iterables):
_multi_index_from_tuples_helper(val, levels_dicts, index_codes, i)
index_levels = sdc_tuple_map(lambda x: list(x.keys()), levels_dicts)
res = pd.MultiIndex(
levels=index_levels,
codes=index_codes,
)
return res
def pd_multi_index_equals_impl(self, other):
if self.nlevels != other.nlevels:
return False
self_and_other_data = _multi_index_binop_helper(self, other)
tup_levels_cmp_res = sdc_tuple_map(
lambda x: cat_array_equal(*x),
self_and_other_data,
)
# np.all is not supported for Tuples and below compiles a bit faster
# than 'np.all(np.array(list(tup_levels_cmp_res)))'
for cmp_res in tup_levels_cmp_res:
if not cmp_res:
return False
return True
def pd_multi_index_take_impl(self, indexes):
new_levels = self._levels
new_codes = sdc_tuple_map(
lambda idx, taken_idxs: sdc_indexes_take(idx, taken_idxs),
self._codes, indexes)
return pd.MultiIndex(new_levels, new_codes)