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()
def setUp(self):
self.name_map = NameMap('test_data/test_maps/test_map_0.pkl')
