def test_assess_memorization(self):
n = 1000
m = 3
missing_value = -999999
pri = Privacy()
header = []
for i in range(m):
header = np.append(header, 'col' + str(i))
x_real = np.random.random(size=(n, m))
x_synth = np.random.random(size=(n, m))
res = pri.assess_memorization(mat_f_r=x_real,
mat_f_s=x_synth,
missing_value=missing_value,
header=header,
metric='euclidean',
debug=False)
assert np.mean(res['real']) < np.mean(res['rand'])
s['x'] = s['x'][idx, :]
if args.sample_privacy < len(r_trn['x']):
idx = np.random.choice(range(len(r_trn['x'])),
args.sample_privacy,
replace=False)
r_trn['x'] = r_trn['x'][idx, :]
if args.sample_privacy < len(r_tst['x']):
idx = np.random.choice(range(len(r_tst['x'])),
args.sample_privacy,
replace=False)
r_tst['x'] = r_tst['x'][idx, :]
# analysis
if args.analysis_privacy == 'nearest_neighbors':
res = pri.assess_memorization(mat_f_r=r_trn['x'],
mat_f_s=s['x'],
missing_value=args.missing_value_privacy,
header=r_trn['header'])
elif args.analysis_privacy == 'membership_inference':
res = pri.membership_inference(
mat_f_r_trn=r_trn['x'],
mat_f_r_tst=r_tst['x'],
mat_f_s=s['x'],
header=r_trn['header'],
missing_value=args.missing_value_privacy)
else:
print('Error: do not recognize analysis_privacy option ' +
args.analysis_privacy)
sys.exit(0)
# output
if args.output_privacy == 'file':