def adult_benchmark():
data = Dataset.load('../data/adult.csv', '../data/adult-domain.json')
projections = [('occupation', 'race', 'capital-loss'),
('occupation', 'sex', 'native-country'),
('marital-status', 'relationship', 'income>50K'),
('age', 'education-num', 'sex'),
('workclass', 'education-num', 'occupation'),
('marital-status', 'occupation', 'income>50K'),
('race', 'native-country', 'income>50K'),
('occupation', 'capital-gain', 'income>50K'),
('marital-status', 'hours-per-week', 'income>50K'),
('workclass', 'race', 'capital-gain'),
('marital-status', 'relationship', 'capital-gain'),
('workclass', 'education-num', 'capital-gain'),
('education-num', 'relationship', 'race'),
('fnlwgt', 'hours-per-week', 'income>50K'),
('workclass', 'sex', 'native-country')]
lookup = {}
for attr in data.domain:
n = data.domain.size(attr)
lookup[attr] = workload.Identity(n)
lookup['age'] = workload.Prefix(85)
lookup['fnlwgt'] = workload.Prefix(100)
lookup['capital-gain'] = workload.Prefix(100)
lookup['capital-loss'] = workload.Prefix(100)
lookup['hours-per-week'] = workload.Prefix(99)
workloads = []
for proj in projections:
W = workload.Kronecker([lookup[a] for a in proj])
workloads.append((proj, W))
return data, workloads
def randomKway(name, number, marginal, seed=0):
path = "Datasets/{}.csv".format(name)
domain = "Datasets/{}-domain.json".format(name)
data = Dataset.load(path, domain)
return data, randomKwayData(data, number, marginal, seed)
pb_path+=str(i)
pb_path+=".csv"
print(pb_path)
syn_data_privbayes = Dataset.load(pb_path, domain)
dq_path=dualquerydata
dq_path+=str(i)
dq_path+=".csv"
print(dq_path)
syn_data_dualquery= Dataset.load(dq_path, domain)
'''
gm_path = gmdata
gm_path += str(i + 1)
gm_path += " .csv"
print(gm_path)
syn_data_r = Dataset.load(gm_path, domain)
# err_pb = []
# err_dq = []
err_r = []
print("ss")
for p, W in workload:
true = W.dot(data.project(p).datavector())
# print(data.project(p).datavector())
# pb = W.dot(syn_data_privbayes.project(p).datavector())
# print(syn_data_privbayes.project(p).datavector())
# dq_data=syn_data_dualquery.project(p).datavector()
# dq_data*=total/dq_data.sum()
# dq = W.dot(dq_data)
# print(syn_data_dualquery.project(p).datavector())
r = W.dot(syn_data_r.project(p).datavector())
help='bounded or unbounded privacy definition')
parser.add_argument('--frequency', type=int, help='logging frequency')
parser.add_argument('--seed', type=int, help='random seed')
parser.add_argument('--save', type=str, help='path to save results')
parser.add_argument('--load',
type=str,
help='path to load results from (skips experiment)')
parser.add_argument('--plot', type=str, help='path to save plot')
parser.set_defaults(**default_params())
args = parser.parse_args()
if args.load:
results = pickle.load(open(args.load, 'rb'))
else:
data = Dataset.load('../data/adult.csv', '../data/adult-domain.json')
projections = [['race', 'capital-loss', 'income>50K'],
['marital-status', 'capital-gain', 'income>50K'],
['race', 'native-country', 'income>50K'],
['workclass', 'sex', 'hours-per-week'],
['fnlwgt', 'marital-status', 'relationship'],
['workclass', 'education-num', 'occupation'],
['age', 'relationship', 'sex'],
['occupation', 'sex', 'hours-per-week'],
['occupation', 'relationship', 'income>50K']]
measurements = []
for p in projections:
Q = sparse.eye(data.domain.size(p))
measurements.append((p, Q))