def main(dirs):
for this_dir in dirs:
print this_dir
for filename in glob.glob(os.path.join(this_dir, '*.json.gz')):
parser = PcbaJsonParser(filename)
tree = parser.tree
aid = parser.get_aid()
try:
del tree['PC_AssaySubmit']['data']
except KeyError as e:
print 'JSON is not properly formatted. Please follow NCBI FTP format.'
raise e
with gzip.open(
os.path.join(this_dir, '{}-desc.json.gz'.format(aid)),
'wb') as f:
json.dump(tree, f, indent=2)
def main(dirs, output_filename):
targets = []
aids = []
for this_dir in dirs:
print this_dir
for filename in glob.glob(os.path.join(this_dir, '*.json.gz')):
parser = PcbaJsonParser(filename)
aid = parser.get_aid()
target = parser.get_target()
if target is None or len(target) > 1:
continue
try:
mol_id = target[0]['mol_id']
except KeyError:
print '\tAID {} target has no mol_id'.format(aid)
continue
print '\tAID {} => {}'.format(aid, mol_id)
targets.append(mol_id)
aids.append(aid)
print 'Found {} targets'.format(len(aids))
with open(output_filename, 'wb') as f:
for aid, target in zip(aids, targets):
f.write('{}\t{}\n'.format(aid, target))
def setUp(self):
"""
Set up tests.
"""
self.data_dir = os.path.split(os.path.realpath(__file__))[0]
self.parser = PcbaJsonParser(
os.path.join(self.data_dir, 'data/aid490.json'))
self.no_target = PcbaJsonParser(
os.path.join(self.data_dir, 'data/aid1.json'))
self.confirmatory = self.no_target
self.multiple_target = PcbaJsonParser(
os.path.join(self.data_dir, 'data/aid429.json'))
self.gzip_parser = PcbaJsonParser(
os.path.join(self.data_dir, 'data/aid490.json.gz'))
self.rest_parser = PcbaJsonParser(
os.path.join(self.data_dir, 'data/aid1-rest.json'))
self.data_parser = PcbaJsonParser(
os.path.join(self.data_dir, 'data/999.json.gz'))
self.target_keys = ['name', 'mol_id', 'molecule_type', 'organism']
def setUp(self):
self.handler = PcbaPandasHandler()
self.data_dir = os.path.split(os.path.realpath(__file__))[0]
self.parser = PcbaJsonParser(
os.path.join(self.data_dir, 'data/aid1.json'))
