def get_result_dataset(att_trees, data, type_alg, k=DEFAULT_K, num_test=10):
"""
fix k and QI, while changing size of dataset
num_test is the test nubmber.
"""
data_back = copy.deepcopy(data)
length = len(data_back)
print "K=%d" % k
joint = 5000
datasets = []
check_time = length / joint
if length % joint == 0:
check_time -= 1
for i in range(check_time):
datasets.append(joint * (i + 1))
datasets.append(length)
all_ncp = []
all_rtime = []
for pos in datasets:
ncp = rtime = 0
print '#' * 30
print "size of dataset %d" % pos
for j in range(num_test):
temp = random.sample(data, pos)
_, eval_result = clustering_based_k_anon(att_trees, temp, type_alg, k)
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 get_result_one(att_trees, data, type_alg, k=DEFAULT_K):
"run clustering_based_k_anon for one time, with k=10"
print "K=%d" % k
data_back = copy.deepcopy(data)
_, eval_result = clustering_based_k_anon(att_trees, data, type_alg, k)
print "NCP %0.2f" % eval_result[0] + "%"
print "Running time %0.2f" % eval_result[1] + "seconds"
def get_result_one(att_trees, data, type_alg, k=DEFAULT_K):
"run clustering_based_k_anon for one time, with k=10"
print "K=%d" % k
data_back = copy.deepcopy(data)
result, eval_result = clustering_based_k_anon(att_trees, data, type_alg, k)
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, type_alg, k=10):
"run clustering_based_k_anon for one time, with k=10"
print("K=%d" % k)
data_back = copy.deepcopy(data)
result, eval_result = clustering_based_k_anon(att_trees, data, type_alg, k)
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_k(att_trees, data, type_alg):
"""
change k, whle fixing QD and size of dataset
"""
data_back = copy.deepcopy(data)
for k in range(5, 55, 5):
print '#' * 30
print "K=%d" % k
result, eval_result = clustering_based_k_anon(att_trees, data, type_alg, k)
data = copy.deepcopy(data_back)
print "NCP %0.2f" % eval_result[0] + "%"
print "Running time %0.2f" % eval_result[1] + " seconds"
def test1_oka(self):
init()
data = [['6', '1', 'haha'], ['6', '1', 'test'], ['8', '2', 'haha'],
['8', '2', 'test'], ['4', '1', 'hha'], ['4', '1', 'hha'],
['4', '3', 'hha'], ['4', '3', 'hha']]
result, eval_r = clustering_based_k_anon(ATT_TREE, data, 'oka', 2)
try:
self.assertTrue(abs(eval_r[0] - 0) < 0.05)
except AssertionError:
print data
print result
print eval_r
self.assertEqual(0, 1)
def test2_k_nn(self):
init()
data = [['6', '1', 'haha'], ['6', '1', 'test'], ['8', '2', 'haha'],
['8', '2', 'test'], ['4', '1', 'hha'], ['4', '2', 'hha'],
['4', '3', 'hha'], ['4', '4', 'hha']]
result, eval_r = clustering_based_k_anon(ATT_TREE, data, 'knn', 2)
try:
self.assertTrue(abs(eval_r[0] - 2.77) < 0.05)
except AssertionError:
print(data)
print(result)
print(eval_r)
self.assertEqual(0, 1)
def get_result_dataset(att_trees, data, type_alg, k=DEFAULT_K, n=10):
"""
fix k and QI, while changing size of dataset
n is the proportion nubmber.
"""
data_back = copy.deepcopy(data)
length = len(data_back)
print "K=%d" % k
joint = 5000
datasets = []
check_time = length / joint
if length % joint == 0:
check_time -= 1
for i in range(check_time):
datasets.append(joint * (i + 1))
datasets.append(length)
all_ncp = []
all_rtime = []
for pos in datasets:
ncp = rtime = 0
print '#' * 30
print "size of dataset %d" % pos
for j in range(n):
temp = random.sample(data, pos)
result, eval_result = clustering_based_k_anon(
att_trees, temp, type_alg, k)
ncp += eval_result[0]
rtime += eval_result[1]
data = copy.deepcopy(data_back)
result_file = FILE_NAME + "_resultfile_" + str(TYPE_ALG) + ".csv"
with open(result_file, "w") as rf:
for r in result:
outstring = ""
sepBy = ","
for val in r:
outstring += val
outstring += sepBy
rf.write(outstring)
rf.write("\n")
ncp /= n
rtime /= n
print "Average NCP %0.2f" % ncp + "%"
all_ncp.append(round(ncp, 2))
print "Running time %0.2f" % rtime + "seconds"
all_rtime.append(round(rtime, 2))
print '#' * 30
print "All NCP", all_ncp
print "All Running time", all_rtime
def get_result_qi(att_trees, data, type_alg, k=DEFAULT_K):
"""
change nubmber of QI, whle fixing k and size of dataset
"""
data_back = copy.deepcopy(data)
num_data = len(data[0])
print "L=%d" % k
for i in reversed(range(1, num_data)):
print '#' * 30
print "Number of QI=%d" % i
_, eval_result = clustering_based_k_anon(att_trees, data, type_alg, k, 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_n(att_trees, data, type_alg, k=10, n=10):
"""
run clustering_based_k_anon for n time, with k=10
"""
print("K=%d" % k)
data_back = copy.deepcopy(data)
n_ncp = 0.0
n_time = 0.0
for i in range(n):
_, eval_result = clustering_based_k_anon(att_trees, data, type_alg, k)
data = copy.deepcopy(data_back)
n_ncp += eval_result[0]
n_time += eval_result[1]
n_ncp = n_ncp / n
n_time = n_ncp / n
print("Run %d times" % n)
print("NCP %0.2f" % n_ncp + "%")
print("Running time %0.2f" % n_time + " seconds")
def test2_k_nn(self):
init()
data = [['6', '1', 'haha'],
['6', '1', 'test'],
['8', '2', 'haha'],
['8', '2', 'test'],
['4', '1', 'hha'],
['4', '2', 'hha'],
['4', '3', 'hha'],
['4', '4', 'hha']]
result, eval_r = clustering_based_k_anon(ATT_TREE, data, 'knn', 2)
try:
self.assertTrue(abs(eval_r[0] - 2.77) < 0.05)
except AssertionError:
print data
print result
print eval_r
self.assertEqual(0, 1)
def get_result_n(att_trees, data, type_alg, k=DEFAULT_K, n=10):
"""
run clustering_based_k_anon for n time, with k=10
"""
print "K=%d" % k
data_back = copy.deepcopy(data)
n_ncp = 0.0
n_time = 0.0
for i in range(n):
_, eval_result = clustering_based_k_anon(att_trees, data, type_alg, k)
data = copy.deepcopy(data_back)
n_ncp += eval_result[0]
n_time += eval_result[1]
n_ncp = n_ncp / n
n_time = n_ncp / n
print "Run %d times" % n
print "NCP %0.2f" % n_ncp + "%"
print "Running time %0.2f" % n_time + " seconds"
def get_result_k(att_trees, data, type_alg):
"""
change k, whle fixing QD and size of dataset
"""
data_back = copy.deepcopy(data)
all_ncp = []
all_rtime = []
# for k in range(5, 105, 5):
for k in [2, 5, 10, 25, 50, 100]:
print '#' * 30
print "K=%d" % k
_, eval_result = clustering_based_k_anon(att_trees, data, type_alg, k)
data = copy.deepcopy(data_back)
print "NCP %0.2f" % eval_result[0] + "%"
all_ncp.append(round(eval_result[0], 2))
print "Running time %0.2f" % eval_result[1] + "seconds"
all_rtime.append(round(eval_result[1], 2))
print "All NCP", all_ncp
print "All Running time", all_rtime
def get_result_k(att_trees, data, type_alg):
"""
change k, whle fixing QD and size of dataset
"""
data_back = copy.deepcopy(data)
all_ncp = []
all_rtime = []
# for k in range(5, 105, 5):
for k in [2, 5, 10, 25, 50, 100]:
print '#' * 30
print "K=%d" % k
_, eval_result = clustering_based_k_anon(att_trees, data, type_alg, k)
data = copy.deepcopy(data_back)
print "NCP %0.2f" % eval_result[0] + "%"
all_ncp.append(round(eval_result[0], 2))
print "Running time %0.2f" % eval_result[1] + "seconds"
all_rtime.append(round(eval_result[1], 2))
print "All NCP", all_ncp
print "All Running time", all_rtime
def get_result_k(att_trees, data, type_alg):
"""
change k, whle fixing QD and size of dataset
"""
data_back = copy.deepcopy(data)
all_ncp = []
all_rtime = []
# for k in range(50,100,50):
for k in [50, 100, 150, 200, 250, 300, 350, 400, 450, 500]:
print('#' * 30)
print("K=%d" % k)
_, eval_result = clustering_based_k_anon(att_trees, data, type_alg, k)
data = copy.deepcopy(data_back)
print("NCP %0.2f" % eval_result[0] + "%")
all_ncp.append(round(eval_result[0], 2))
print("Running time %0.2f" % eval_result[1] + "seconds")
all_rtime.append(round(eval_result[1], 2))
print("All NCP", all_ncp)
print("All Running time", all_rtime)
def get_result_qi(att_trees, data, type_alg, k=DEFAULT_K):
"""
change nubmber of QI, whle fixing k and size of dataset
"""
data_back = copy.deepcopy(data)
ls = len(data[0])
all_ncp = []
all_rtime = []
for i in range(1, ls):
print '#' * 30
print "Number of QI=%d" % i
_, eval_result = clustering_based_k_anon(att_trees, data, type_alg, k,
i)
data = copy.deepcopy(data_back)
print "NCP %0.2f" % eval_result[0] + "%"
all_ncp.append(round(eval_result[0], 2))
print "Running time %0.2f" % eval_result[1] + "seconds"
all_rtime.append(round(eval_result[1], 2))
print "All NCP", all_ncp
print "All Running time", all_rtime
def get_result_qi(att_trees, data, type_alg, k=DEFAULT_K):
"""
change nubmber of QI, whle fixing k and size of dataset
"""
data_back = copy.deepcopy(data)
ls = len(data[0])
all_ncp = []
all_rtime = []
for i in range(1, ls):
print '#' * 30
print "Number of QI=%d" % i
_, eval_result = clustering_based_k_anon(att_trees,
data, type_alg, k, i)
data = copy.deepcopy(data_back)
print "NCP %0.2f" % eval_result[0] + "%"
all_ncp.append(round(eval_result[0], 2))
print "Running time %0.2f" % eval_result[1] + "seconds"
all_rtime.append(round(eval_result[1], 2))
print "All NCP", all_ncp
print "All Running time", all_rtime
def get_result_dataset(att_trees, data, type_alg, k=DEFAULT_K, n=10):
"""
fix k and QI, while changing size of dataset
n is the proportion nubmber.
"""
data_back = copy.deepcopy(data)
length = len(data_back)
print "K=%d" % k
joint = 5000
datasets = []
check_time = length / joint
if length % joint == 0:
check_time -= 1
for i in range(check_time):
datasets.append(joint * (i + 1))
datasets.append(length)
all_ncp = []
all_rtime = []
for pos in datasets:
ncp = rtime = 0
print '#' * 30
print "size of dataset %d" % pos
for j in range(n):
temp = random.sample(data, pos)
result, eval_result = clustering_based_k_anon(
att_trees, temp, type_alg, k)
ncp += eval_result[0]
rtime += eval_result[1]
data = copy.deepcopy(data_back)
# save_to_file((att_trees, temp, result, k, L))
ncp /= n
rtime /= n
print "Average NCP %0.2f" % ncp + "%"
all_ncp.append(round(ncp, 2))
print "Running time %0.2f" % rtime + "seconds"
all_rtime.append(round(rtime, 2))
print '#' * 30
print "All NCP", all_ncp
print "All Running time", all_rtime
