def pivot_items_to_frame(
*,
blocks: TypeBlocks,
group_fields_iloc: tp.Iterable[tp.Hashable],
group_depth: int,
data_field_iloc: tp.Hashable,
func_single: tp.Optional[UFunc],
frame_cls: tp.Type['Frame'],
name: NameType,
dtype: np.dtype,
index_constructor: IndexConstructor,
columns_constructor: IndexConstructor,
kind: str,
) -> 'Frame':
'''
Specialized generator of pairs for when we have only one data_field and one function.
This version returns a Frame.
'''
from static_frame.core.series import Series
group_key = group_fields_iloc if group_depth > 1 else group_fields_iloc[
0] #type: ignore
if func_single:
labels = []
values = []
for label, _, v in blocks.group_extract(
axis=0,
key=group_key,
extract=data_field_iloc,
kind=kind,
):
labels.append(label)
values.append(func_single(v))
if dtype is None:
array, _ = iterable_to_array_1d(values, count=len(values))
else:
array = np.array(values, dtype=dtype)
array.flags.writeable = False
index = index_constructor(labels)
return frame_cls.from_elements(
array,
index=index,
own_index=True,
columns=(name, ),
columns_constructor=columns_constructor,
)
# func_no scenario
if group_depth == 1:
index = index_constructor(blocks._extract_array_column(group_key))
else:
index = index_constructor(
tuple(label)
for label in blocks._extract_array(column_key=group_key))
array = blocks._extract_array_column(data_field_iloc)
return frame_cls.from_elements(
array,
index=index,
own_index=True,
columns=(name, ),
columns_constructor=columns_constructor,
)
def pivot_items_to_block(
*,
blocks: TypeBlocks,
group_fields_iloc: tp.Iterable[tp.Hashable],
group_depth: int,
data_field_iloc: tp.Hashable,
func_single: tp.Optional[UFunc],
dtype: tp.Optional[np.dtype],
fill_value: tp.Any,
fill_value_dtype: np.dtype,
index_outer: 'IndexBase',
kind: str,
) -> np.ndarray:
'''
Specialized generator of pairs for when we have only one data_field and one function.
'''
from static_frame.core.series import Series
group_key = group_fields_iloc if group_depth > 1 else group_fields_iloc[
0] #type: ignore
if func_single and dtype is not None:
array = np.full(
len(index_outer),
fill_value,
dtype=resolve_dtype(dtype, fill_value_dtype),
)
for label, _, values in blocks.group_extract(
axis=0,
key=group_key,
extract=data_field_iloc,
kind=kind,
):
array[index_outer._loc_to_iloc(label)] = func_single(values)
array.flags.writeable = False
return array
if func_single and dtype is None:
def gen() -> tp.Iterator[tp.Tuple[int, tp.Any]]:
for label, _, values in blocks.group_extract(
axis=0,
key=group_key,
extract=data_field_iloc,
kind=kind,
):
yield index_outer._loc_to_iloc(label), func_single(values)
post = Series.from_items(gen())
if len(post) == len(index_outer):
array = np.empty(len(index_outer), dtype=post.dtype)
else:
array = np.full(
len(index_outer),
fill_value,
dtype=resolve_dtype(post.dtype, fill_value_dtype),
)
array[post.index.values] = post.values
array.flags.writeable = False
return array
# func_no scenario as no mapping here
if group_depth == 1:
labels = [
index_outer._loc_to_iloc(label)
for label in blocks._extract_array_column(group_key)
]
else:
# NOTE: might replace _extract_array_column with an iterator of tuples
labels = [
index_outer._loc_to_iloc(tuple(label))
for label in blocks._extract_array(column_key=group_key)
]
values = blocks._extract_array_column(data_field_iloc)
if len(values) == len(index_outer):
array = np.empty(len(index_outer), dtype=dtype)
else:
array = np.full(
len(index_outer),
fill_value,
dtype=resolve_dtype(values.dtype, fill_value_dtype),
)
array[labels] = values
array.flags.writeable = False
return array
