def write_series(self, group: zarr.Group, name: str, array: np.ndarray,
data_type: str) -> None:
if data_type == 'data_frame':
if not is_categorical_dtype(
array) and name != '_index' and is_string_dtype(array):
keywords = set(array)
if len(keywords
) <= array.size / 10.0: # at least 10x reduction
array = pd.Categorical(array,
categories=natsorted(keywords))
if is_categorical_dtype(array):
# write category keys
categories = group.require_group('_categories')
values = array.categories.values
if isinstance(values[0], bytes):
values = np.array([x.decode() for x in values],
dtype=object)
dtype = str if values.dtype.kind == 'O' else values.dtype
categories.create_dataset(name,
data=values,
shape=values.shape,
chunks=calc_chunk(values.shape),
dtype=dtype,
compressor=COMPRESSOR,
overwrite=True)
# write codes
codes_arr = group.create_dataset(name,
data=array.codes,
shape=array.codes.shape,
chunks=calc_chunk(
array.codes.shape),
dtype=array.codes.dtype,
compressor=COMPRESSOR,
overwrite=True)
codes_arr.attrs['ordered'] = array.ordered
return None
dtype = str if array.dtype.kind == 'O' else array.dtype
group.create_dataset(name,
data=array,
shape=array.shape,
chunks=calc_chunk(array.shape),
dtype=dtype,
compressor=COMPRESSOR,
overwrite=True)
def write_unimodal_data(self, group: zarr.Group, name: str, data: UnimodalData, overwrite: bool = True) -> None:
""" Write UnimodalData
"""
sub_group = group.require_group(name, overwrite = overwrite)
attrs_dict = {'data_type': 'UnimodalData', '_cur_matrix': data.current_matrix()}
sub_group.attrs.update(**attrs_dict)
self.write_dataframe(sub_group, 'barcode_metadata', data.barcode_metadata)
self.write_dataframe(sub_group, 'feature_metadata', data.feature_metadata)
if overwrite or data.matrices.is_dirty():
self.write_mapping(sub_group, 'matrices', data.matrices, overwrite = overwrite)
if overwrite or data.metadata.is_dirty():
self.write_mapping(sub_group, 'metadata', data.metadata, overwrite = overwrite)
if overwrite or data.barcode_multiarrays.is_dirty():
self.write_mapping(sub_group, 'barcode_multiarrays', data.barcode_multiarrays, overwrite = overwrite)
if overwrite or data.feature_multiarrays.is_dirty():
self.write_mapping(sub_group, 'feature_multiarrays', data.feature_multiarrays, overwrite = overwrite)
def write_mapping(self,
group: zarr.Group,
name: str,
mapping: dict,
overwrite=True) -> None:
sub_group = group.require_group(name, overwrite=overwrite)
scalar_dict = sub_group.attrs.pop(
'scalar', {}) # if overwrite == True, there should be no 'scalar'
def _write_one_pair(key, value):
if is_scalar(value):
scalar_dict[key] = value
elif isinstance(value, np.ndarray):
self.write_array(sub_group, key, value)
elif isinstance(value, pd.DataFrame):
self.write_dataframe(sub_group, key, value)
elif is_dict_like(value):
self.write_mapping(sub_group, key, value)
elif issparse(value):
assert isinstance(value, csr_matrix)
self.write_csr(sub_group, key, value)
else:
# assume value is either list or tuple, converting it to np.ndarray
self.write_array(
sub_group, key,
value.astype(str)
if is_categorical_dtype(value) else np.array(value))
if overwrite:
for key, value in mapping.items():
_write_one_pair(key, value)
else:
for key in mapping.deleted:
if key in scalar_dict:
del scalar_dict[key]
else:
del sub_group[key]
for key in mapping.modified:
_write_one_pair(key, mapping[key])
attrs_dict = {'data_type': 'dict'}
if len(scalar_dict) > 0:
attrs_dict['scalar'] = scalar_dict
sub_group.attrs.update(**attrs_dict)
