'submitter_id': case_submitter_id
},
'submitter_id': submitter_id,
'project_id': DEFAULT_PROJECT_ID,
'data_type': row['c_file.mime'],
'md5sum': row['c_file.ETag'],
'file_size': row['c_file.size'],
'file_name': row['c_file.path'],
}
file_emitter.write(file)
file_emitter.close()
if __name__ == "__main__":
item_paths = [DEFAULT_INPUT_FILE]
args = default_parser(DEFAULT_OUTPUT_DIR, DEFAULT_EXPERIMENT_CODE,
DEFAULT_PROJECT_ID).parse_args()
transform(item_paths,
output_dir=args.output_dir,
experiment_code=args.experiment_code)
p = os.path.join(args.output_dir, 'submitted_file.json')
assert os.path.isfile(p), 'should have an output file {}'.format(p)
print(p)
if args.schema:
def my_callback(schema):
# adds the source property
schema['category'] = 'hop extention'
schema['properties']['cases'] = {
# diagnosis['*last_known_disease_status'] = disease_status.get(line['Cancer Status'], 'Unknown tumor status')
# diagnosis['*morphology'] = 'tumor_size={}'.format(line['Tumor Size']) # "None is not of type 'string'")
# diagnosis['*primary_diagnosis'] = line['Case_ICD::Transformation']
# diagnosis['*progression_or_recurrence'] = 'unknown' # ['yes', 'no', 'unknown', 'not reported', 'Not Allowed To Collect']
# diagnosis['*site_of_resection_or_biopsy'] = 'unknown'
# diagnosis['*tissue_or_organ_of_origin'] = 'pancrease'
# diagnosis['*tumor_grade'] = 'unknown' # "None is not of type 'string'")
# diagnosis['*tumor_stage'] = 'unknown' # "None is not of type 'string'")
# diagnosis['*vital_status'] = 'unknown'
#
# diagnosis_emitter.write(diagnosis)
cases_emitter.close()
demographics_emitter.close()
if __name__ == "__main__":
item_paths = [
'source/ccle/Individual.Vertex.json.gz',
'source/ccle/maf.Individual.Vertex.json.gz'
]
args = default_parser().parse_args()
transform(item_paths=item_paths, output_dir=args.output_dir)
# glob.glob("output/bcc/*.json")
if args.schema:
schema_path = generate(item_paths,
'case',
output_dir=DEFAULT_OUTPUT_DIR)
print(schema_path)