class TestNameUtils(unittest.TestCase):
def setUp(self):
self.name_map = NameMap('test_data/test_maps/test_map_0.pkl')
def test_add_mappings1(self):
self.name_map.add_mappings('test_data/test_map_csv/test_map_0.csv')
print self.name_map
self.assertEqual(self.name_map['alanine'][standard_name], 'Alanine')
self.assertEqual(self.name_map['anthranilate'][standard_name], '2-Aminobenzoic acid')
def test_add_mappings2(self):
self.name_map.add_mappings('test_data/test_map_csv/test_map_1.csv')
print self.name_map
self.assertEqual(self.name_map['cystathionine'],
{standard_name: 'L-Cystathionine', hmdb: 'HMDB00099', pubchem: '439258', kegg: 'C02291'})
self.assertEqual(self.name_map['proline'],
{standard_name: 'L-Proline', hmdb: 'HMDB00162', pubchem: '145742', kegg: 'C00148'})
self.assertEqual(self.name_map['alanine'],
{standard_name: 'Alanine', hmdb: 'METPA0179', kegg: 'C01401'})
def test_remove_mappings(self):
pass
def standardized_compound_names(original_names,
map_pkl_path=default_map_pkl_path,
id_type=standard_name):
"""
:param original_names: A list of original field names to be standardized
:param map_pkl_path: Path to a pkl file containing mappings used to standardize the names
:return: A list of standardized field names
"""
print 'Standardizing names to: {0}'.format(id_type)
name_map = NameMap(map_pkl_path)
standardized = original_names
for i in range(len(standardized)):
name = _strip_suffix(standardized[i])
if name in name_map:
new_id = name_map[name][id_type] if id_type in name_map[
name] else name
print '{0} --> {1}'.format(standardized[i], new_id)
standardized[i] = new_id
else:
standardized[i] = name
return standardized
print "Incorporating all name map files in {0}.".format(
args.find_in_dir)
name_map_files = [
join(args.find_in_dir, f) for f in listdir(args.find_in_dir)
if f.endswith('.csv')
]
# Find "manual" csv files and move them to the end so that their contents take priority.
index_of_manual = filter(
lambda j: 'manual' in basename(name_map_files[j]),
range(len(name_map_files)))
index_of_manual.sort(reverse=True)
for i in index_of_manual:
name_map_files.append(name_map_files.pop(i))
current_map = NameMap()
if args.clear_first:
current_map.clear()
for f in name_map_files:
print f
if args.a:
current_map.add_mappings(f)
elif args.d:
current_map.remove_mappings(f)
elif args.prune_csv:
name_map_utils.prune(f)
else:
print('There are currently {0} values in the name map.'.format(
len(current_map)))
def setUp(self):
self.name_map = NameMap('test_data/test_maps/test_map.pkl')
self.name_map.clear()
self.name_map['existing entry 1'] = {standard_name: 'foo'}
self.name_map['existing entry 2'] = {standard_name: 'bar'}
self.name_map._commit()
class SimpleTestNameMapUtils(unittest.TestCase):
def setUp(self):
self.name_map = NameMap('test_data/test_maps/test_map.pkl')
self.name_map.clear()
self.name_map['existing entry 1'] = {standard_name: 'foo'}
self.name_map['existing entry 2'] = {standard_name: 'bar'}
self.name_map._commit()
def tearDown(self):
pass
def test_get_map_from_csv(self):
result_map = self.name_map.get_map_from_csv('./test_data/test_map_csv/test_map_tiny.csv')
self.assertTrue(contains_only(result_map, {'speshul': {standard_name: 'special'},
'tomahto': {standard_name: 'tomato'},
'weird': {standard_name: 'unicorn'},
'existing entry 1': {standard_name: 'not foo'}}))
def test_add_mappings(self):
self.name_map.add_mappings('./test_data/test_map_csv/test_map_small.csv')
self.assertEqual(self.name_map['speshul'][standard_name], 'special')
self.assertEqual(self.name_map['speshol'][standard_name], 'special')
self.assertEqual(self.name_map['irregardless of'][standard_name], 'regardless of')
self.assertEqual(self.name_map['tomahto'][standard_name], 'tomato')
self.assertEqual(self.name_map['existing entry 1'][standard_name], 'foo')
self.assertEqual(self.name_map['existing entry 2'][standard_name], 'bar')
with open(self.name_map.map_pkl_path) as map_pkl:
loaded_map = pickle.load(map_pkl)
def test_remove_mappings(self):
self.name_map.add_mappings('test_data/test_map_csv/test_map_small.csv')
self.name_map.remove_mappings('test_data/test_map_csv/test_map_tiny.csv')
self.assertEqual(self.name_map['speshol'][standard_name], 'special')
self.assertFalse('speshul' in self.name_map)
with open(self.name_map.map_pkl_path) as map_pkl:
loaded_map = pickle.load(map_pkl)
self.assertTrue(contains_only(loaded_map, {
'speshol': {standard_name: 'special'},
'irregardless of': {standard_name: 'regardless of'},
'existing entry 1': {standard_name: 'foo'},
'existing entry 2': {standard_name: 'bar'}
}))
def test_clear(self):
self.name_map.clear()
self.assertEqual(len(self.name_map), 0)
with open(self.name_map.map_pkl_path) as map_pkl:
loaded_map = pickle.load(map_pkl)
self.assertEqual(len(loaded_map), 0)
def setUp(self):
self.name_map = NameMap('test_data/test_maps/test_map_0.pkl')
if args.use_file:
use_file = join(args.find_in_dir, args.use_file)
print "Incorporating file {0}".format(use_file)
name_map_files = [use_file]
elif args.find_in_dir:
print "Incorporating all name map files in {0}.".format(args.find_in_dir)
name_map_files = [join(args.find_in_dir, f) for f in listdir(args.find_in_dir) if f.endswith('.csv')]
# Find "manual" csv files and move them to the end so that their contents take priority.
index_of_manual = filter(lambda j: 'manual' in basename(name_map_files[j]), range(len(name_map_files)))
index_of_manual.sort(reverse=True)
for i in index_of_manual:
name_map_files.append(name_map_files.pop(i))
current_map = NameMap()
if args.clear_first:
current_map.clear()
for f in name_map_files:
print f
if args.a:
current_map.add_mappings(f)
elif args.d:
current_map.remove_mappings(f)
elif args.prune_csv:
name_map_utils.prune(f)
else:
print('There are currently {0} values in the name map.'.format(len(current_map)))
