def package_data_assembly(proto_data_assembly,
assembly_identifier,
stimulus_set_identifier,
assembly_class="NeuronRecordingAssembly",
bucket_name="brainio-contrib"):
"""
Package a set of data along with its metadata for the BrainIO system.
:param proto_data_assembly: An xarray DataArray containing experimental measurements and all related metadata.
* The dimensions of a neural DataArray must be
* presentation
* neuroid
* time_bin
A behavioral DataArray should also have a presentation dimension, but can be flexible about its other dimensions.
* The presentation dimension must have an image_id coordinate and should have coordinates for presentation-level metadata such as repetition and image_id.
The presentation dimension should not have coordinates for image-specific metadata, these will be drawn from the StimulusSet based on image_id.
* The neuroid dimension must have a neuroid_id coordinate and should have coordinates for as much neural metadata as possible (e.g. region, subregion, animal, row in array, column in array, etc.)
* The time_bin dimension should have coordinates time_bin_start and time_bin_end.
:param assembly_identifier: A dot-separated string starting with a lab identifier.
* For published: <lab identifier>.<first author e.g. 'Rajalingham' or 'MajajHong' for shared first-author><YYYY year of publication>
* For requests: <lab identifier>.<b for behavioral|n for neuroidal>.<m for monkey|h for human>.<proposer e.g. 'Margalit'>.<pull request number>
:param stimulus_set_identifier: The unique name of an existing StimulusSet in the BrainIO system.
:param assembly_class: The name of a DataAssembly subclass.
:param bucket_name: 'brainio-dicarlo' for DiCarlo Lab assemblies, 'brainio-contrib' for external assemblies.
"""
_logger.debug(f"Packaging {assembly_identifier}")
# verify
verify_assembly(proto_data_assembly, assembly_class=assembly_class)
assert hasattr(brainio_base.assemblies, assembly_class)
assert stimulus_set_identifier in list_stimulus_sets(), \
f"StimulusSet {stimulus_set_identifier} not found in packaged stimulus sets"
# identifiers
assembly_store_identifier = "assy_" + assembly_identifier.replace(".", "_")
netcdf_file_name = assembly_store_identifier + ".nc"
target_netcdf_path = Path(__file__).parent / netcdf_file_name
s3_key = netcdf_file_name
# execute
netcdf_kf_sha1 = write_netcdf(proto_data_assembly, target_netcdf_path)
upload_to_s3(target_netcdf_path, bucket_name, s3_key)
lookup.append(object_identifier=assembly_identifier,
stimulus_set_identifier=stimulus_set_identifier,
lookup_type=TYPE_ASSEMBLY,
bucket_name=bucket_name,
sha1=netcdf_kf_sha1,
s3_key=s3_key,
cls=assembly_class)
_logger.debug(f"assembly {assembly_identifier} packaged")
def main():
data_dir = Path(
__file__).parents[6] / 'data2' / 'active' / 'users' / 'sachis'
assert os.path.isdir(data_dir)
import brainio_collection
print(brainio_collection.list_stimulus_sets())
print(brainio_collection.list_assemblies())
stimuli = brainio_collection.get_stimulus_set(
'dicarlo.objectome.public').sort_values(by='image_id')
print(stimuli)
# print(stimuli.columns)
stimuli = collect_stimuli(data_dir)
# stimuli.name = 'dicarlo.Rust2012'
# assembly = load_responses(data_dir, stimuli)
# assembly.name = 'dicarlo.SanghaviKar2020'
# print('Packaging stimuli')
# package_stimulus_set(stimuli, stimulus_set_name=stimuli.name, bucket_name='brainio-dicarlo')
# print('Packaging assembly')
# package_data_assembly(assembly, data_assembly_name=assembly.name, stimulus_set_name=stimuli.name,
# bucket_name='brainio-dicarlo')
return
def test_list_stimulus_set(stimulus_set):
l = brainio_collection.list_stimulus_sets()
assert stimulus_set in l
