def repair_main(schema,
sigma_k=1.0,
outliers=None,
epsilon=None,
filenames=None,
neighbor_k=3,
data_size=None,
used_attrs=None,
comma=None):
if filenames is None:
filenames = {
'error': '../dataset/restaurant/data_error',
'origin': '../dataset/restaurant/data_origin',
}
DORCRepair.sigma_k = sigma_k
instance = Instance(schema,
filenames['error'],
data_size=data_size,
used_attrs=used_attrs)
repair = DORCRepair(instance, neighbor_k, epsilon)
print 'epsilon: %f' % repair.epsilon
print outliers
solutions = repair.repair()
for record_id, solution_id in solutions:
class_id = None
try:
class_id = instance.get(record_id).get('class')
except:
pass
instance.data[record_id] = instance.get(solution_id).clone()
if class_id is not None:
instance.data[record_id].set('class', class_id)
return instance
def repair_main_for_avg_attr(schema,
sigma_k=1.0,
outliers=None,
epsilon=None,
filenames=None,
neighbor_k=3,
data_size=None,
used_attrs=None):
if filenames is None:
filenames = {
'error': '../dataset/restaurant/data_error',
'origin': '../dataset/restaurant/data_origin',
}
if used_attrs is not None:
schema = used_attrs + ['class']
DORCRepair.sigma_k = sigma_k
instance = Instance(schema,
filenames['error'],
data_size=data_size,
used_attrs=used_attrs)
repair = DORCRepair(instance, neighbor_k, epsilon)
repair.calculate_epsilon()
outliers = repair.filter()
print 'epsilon: %f' % repair.epsilon
print outliers
# repair.repair(outliers)
solutions = repair.repair()
for record_id, solution_id in solutions:
# print '---------------'
# print instance.get(record_id)
# print solution
# print '---------------'
instance.data[record_id] = instance.get(solution_id)
return instance, len(outliers)