def get_result_dataset(att_trees, data, l=5, num_test=10):
"""
fix l and QI, while changing size of dataset
num_test is the test nubmber.
"""
data_back = copy.deepcopy(data)
length = len(data_back)
joint = 5000
dataset_num = length / joint
print "L=%d" % l
if length % joint == 0:
dataset_num += 1
for i in range(1, dataset_num + 1):
pos = i * joint
ncp = rtime = 0
if pos > length:
continue
print "#" * 30
print "size of dataset %d" % pos
for j in range(num_test):
temp = random.sample(data, pos)
_, eval_result = mondrian_l_diversity(att_trees, temp, l)
ncp += eval_result[0]
rtime += eval_result[1]
data = copy.deepcopy(data_back)
ncp /= num_test
rtime /= num_test
print "Average NCP %0.2f" % ncp + "%"
print "Running time %0.2f" % rtime + " seconds"
print "#" * 30
def test_mondrian_l_diversity(self):
init_tree()
att_trees = [ATT_TREE]
data = [['a1', 'a1'], ['b2', 'a1'], ['b1', 'b1'], ['b2', 'b1'],
['b1', 'b2'], ['b2', 'b2'], ['a1', 'a2']]
result, eval_result = mondrian_l_diversity(att_trees, data, 2)
self.assertTrue(abs(eval_result[0] - 0) <= 0.001)
def Separation_Gen(att_trees, data, k=10, l=5):
"""Using partition_for_transaction to anonymize SA (transaction) partition,
while applying anatomy to separate QID and SA
return (result, eval_result)
result is 2-dimensional list
eval_result is a tuple (rncp, tncp, rtime)
"""
global ATT_TREES, DATA
ATT_TREES = att_trees
DATA = data
start_time = time.time()
if _DEBUG:
print "size of dataset %d" % len(data)
result = []
# copy transaction part of data to trans
trans = [t[-1] for t in data]
# anonymize transaction part with partition algorithm
trans_set, sa_ncp = partition(att_trees[-1], trans, k)
partition_data = []
for ttemp in trans_set:
(index_list, tran_value) = ttemp
for t in index_list:
DATA[t][-1] = tran_value[:]
partition_data.append(DATA[t][:])
if _DEBUG:
print "Begin Mondrian"
# anonymize qid and sa part with mondrian_l_diversity
result, qid_ncp = mondrian_l_diversity(ATT_TREES, partition_data, l)
rtime = float(time.time() - start_time)
if _DEBUG:
print "Total running time = %.2f seconds" % rtime
# transform data format (QID1,.., QIDn, SA set, GroupID, 1/|group size|, Group SA domain)
# 1/|group size|, Group SA domain will be used in evaluation
return (result, (qid_ncp, sa_ncp, rtime))
def m_generalization(att_trees, data, k=10, l=5):
"""Using partition_for_transaction to anonymize SA (transaction) partition,
while applying anatomy to separate QID and SA
return (result, eval_result)
result is 2-dimensional list
eval_result is a tuple (rncp, tncp, rtime)
"""
global ATT_TREES, DATA
ATT_TREES = att_trees
DATA = data
start_time = time.time()
if _DEBUG:
print "size of dataset %d" % len(data)
result = []
trans = [t[-1] for t in data]
trans_set, tncp = partition(att_trees[-1], trans, k)
partition_data = []
for ttemp in trans_set:
(index_list, tran_value) = ttemp
for t in index_list:
DATA[t][-1] = tran_value[:]
partition_data.append(DATA[t][:])
if _DEBUG:
print "Begin Mondrian"
result, rncp = mondrian_l_diversity(ATT_TREES, partition_data, l)
rtime = float(time.time() - start_time)
if _DEBUG:
print "Total running time = %.2f seconds" % rtime
# transform data format (QID1,.., QIDn, SA set, GroupID, 1/|group size|, Group SA domain)
# 1/|group size|, Group SA domain will be used in evaluation
return (result, (rncp, tncp, rtime))
def get_result_dataset(att_trees, data, l=5, num_test=10):
"""
fix l and QI, while changing size of dataset
num_test is the test nubmber.
"""
data_back = copy.deepcopy(data)
length = len(data_back)
joint = 5000
dataset_num = length / joint
print "L=%d" % l
if length % joint == 0:
dataset_num += 1
for i in range(1, dataset_num + 1):
pos = i * joint
ncp = rtime = 0
if pos > length:
continue
print '#' * 30
print "size of dataset %d" % pos
for j in range(num_test):
temp = random.sample(data, pos)
_, eval_result = mondrian_l_diversity(att_trees, temp, l)
ncp += eval_result[0]
rtime += eval_result[1]
data = copy.deepcopy(data_back)
ncp /= num_test
rtime /= num_test
print "Average NCP %0.2f" % ncp + "%"
print "Running time %0.2f" % rtime + " seconds"
print '#' * 30
def test_group(self):
init_tree()
att_trees = [ATT_TREE]
data = [['a1', ['female', 'diabetes']], ['a1', ['female', 'cold']],
['b1', ['male', 'diabetes']], ['a2', ['male', 'cold']]]
result, eval_result = mondrian_l_diversity(att_trees, data, 2)
print result
self.assertTrue(abs(eval_result[0] - 0))
def get_result_one(att_trees, data, l=5):
"""
run mondrian_l_diversity for one time, with l=5
"""
print "L=%d" % l
data_back = copy.deepcopy(data)
_, eval_result = mondrian_l_diversity(att_trees, data, l)
data = copy.deepcopy(data_back)
print "NCP %0.2f" % eval_result[0] + "%"
print "Running time %0.2f" % eval_result[1] + " seconds"
def test_single(self):
init_tree()
att_trees = [ATT_TREE] * 2
data = [['a1', 'b1', 'cold'], ['a2', 'b1', 'cold'],
['a1', 'b2', 'cold'], ['a1', 'b1', 'cold'],
['a1', 'b2', 'cancer'], ['a1', 'b1', 'cancer']]
result, eval_result = mondrian_l_diversity(att_trees, data, 2)
print result
self.assertTrue(abs(eval_result[0] - 0))
def get_result_one(att_trees, data, l=5):
"""
run mondrian_l_diversity for one time, with l=5
"""
print "L=%d" % l
data_back = copy.deepcopy(data)
result, eval_result = mondrian_l_diversity(att_trees, data, l)
write_to_file(result)
data = copy.deepcopy(data_back)
print "NCP= %0.2f %%" % eval_result[0]
print "Running time %0.2f" % eval_result[1] + " seconds"
def get_result_one(att_trees, data, l=5):
"""
run mondrian_l_diversity for one time, with l=5
"""
print "L=%d" % l
data_back = copy.deepcopy(data)
_, eval_result = mondrian_l_diversity(att_trees, data, l)
data = copy.deepcopy(data_back)
print "NCP %0.2f" % eval_result[0] + "%"
# print _
print "Running time %0.2f" % eval_result[1] + " seconds"
def test_mondrian_l_diversity(self):
init_tree()
att_trees = [ATT_TREE]
data = [['a1', 'a1'],
['b2', 'a1'],
['b1', 'b1'],
['b2', 'b1'],
['b1', 'b2'],
['b2', 'b2'],
['a1', 'a2']]
result, eval_result = mondrian_l_diversity(att_trees, data, 2)
self.assertTrue(abs(eval_result[0] - 0) <= 0.001)
def get_result_l(att_trees, data):
"""
change l, whle fixing QD and size of dataset
"""
data_back = copy.deepcopy(data)
for l in range(2, 21):
print '#' * 30
print "L=%d" % l
result, eval_result = mondrian_l_diversity(att_trees, data, l)
data = copy.deepcopy(data_back)
print "NCP %0.2f" % eval_result[0] + "%"
print "Running time %0.2f" % eval_result[1] + " seconds"
def get_result_l(att_trees, data):
"""
change l, whle fixing QD and size of dataset
"""
data_back = copy.deepcopy(data)
for l in range(2, 21):
print "#" * 30
print "L=%d" % l
result, eval_result = mondrian_l_diversity(att_trees, data, l)
data = copy.deepcopy(data_back)
print "NCP %0.2f" % eval_result[0] + "%"
print "Running time %0.2f" % eval_result[1] + " seconds"
def get_result_one(att_trees, data, l=5):
# run mondrian_l_diversity for one time, with l=5
print "L=%d" % l
data_back = copy.deepcopy(data)
result, eval_result = mondrian_l_diversity(att_trees, data, l)
write_to_file(result)
data = copy.deepcopy(data_back)
print ""
print "Normalized Certainty Penalty (NCP): %0.2f %%" % eval_result[0]
print "Done in %.2f seconds (%.3f minutes (%.2f hours))" % (
eval_result[1], eval_result[1] / 60, eval_result[1] / 60 / 60)
def get_result_qi(att_trees, data, l=5):
"""
change nubmber of QI, whle fixing l and size of dataset
"""
data_back = copy.deepcopy(data)
num_data = len(data[0])
print "L=%d" % l
for i in reversed(range(1, num_data)):
print '#' * 30
print "Number of QI=%d" % i
_, eval_result = mondrian_l_diversity(att_trees, data, l, i)
data = copy.deepcopy(data_back)
print "NCP %0.2f" % eval_result[0] + "%"
print "Running time %0.2f" % eval_result[1] + " seconds"
def get_result_qi(att_trees, data, l=5):
"""
change nubmber of QI, whle fixing l and size of dataset
"""
data_back = copy.deepcopy(data)
num_data = len(data[0])
print "L=%d" % l
for i in reversed(range(1, num_data)):
print "#" * 30
print "Number of QI=%d" % i
_, eval_result = mondrian_l_diversity(att_trees, data, l, i)
data = copy.deepcopy(data_back)
print "NCP %0.2f" % eval_result[0] + "%"
print "Running time %0.2f" % eval_result[1] + " seconds"
def get_result_l(att_trees, data):
# change l, while fixing QD and size of dataset
data_back = copy.deepcopy(data)
for l in range(2, 21):
print '#' * 30
print "L=%d" % l
result, eval_result = mondrian_l_diversity(att_trees, data, l)
data = copy.deepcopy(data_back)
print ""
print "Normalized Certainty Penalty (NCP): %0.2f %%" % eval_result[0]
print "Done in %.2f seconds (%.3f minutes (%.2f hours))" % (
eval_result[1], eval_result[1] / 60, eval_result[1] / 60 / 60)
def get_result_one(att_trees, data, l=config2.l):
"""
run mondrian_l_diversity for one time, with l=5
"""
res = ""
print("L=%d" % l)
data_back = copy.deepcopy(data)
result, eval_result = mondrian_l_diversity(att_trees, data, l)
write_to_file(result)
data = copy.deepcopy(data_back)
print("NCP= %0.2f %%" % eval_result[0])
print('内存使用：',
(psutil.Process(os.getpid()).memory_full_info()).uss / 1024. / 1024.,
'MB')
print("Running time %0.2f" % eval_result[1] + " seconds")
res = res + "k= " + str(l) + ", ncp = " + str(
eval_result[0]) + "%, memory = " + str(
(psutil.Process(os.getpid()).memory_full_info()).uss / 1024. /
1024.) + ", runtime = " + str(eval_result[1])
with open("data/result1.data", "a") as fp:
fp.write(res + '\n')
