def test_DA_partition_case2(self):
init_tree()
trans = [['a1'], ['a1', 'a2'], ['b1', 'b2'], ['b1', 'b2'],
['a1', 'a2', 'b2'], ['a1', 'a2', 'b2'],
['a1', 'a2', 'b1', 'b2']]
_, result = apriori_based_anon(ATT_TREE, trans, 'DA', 2, 4)
# not {'a1': 'A', 'a2': 'A', 'b1': 'B', 'b2': 'B'}
self.assertEqual(result[2], {'b1': 'B', 'b2': 'B'})
_, result = apriori_based_anon(ATT_TREE, trans, 'AA', 2, 2)
self.assertEqual(result[2], {'b1': 'B', 'b2': 'B'})
def test_AA_with_AA_case(self):
init_tree()
trans = [['a1', 'b1', 'b2'],
['a2', 'b1'],
['a2', 'b1', 'b2'],
['a1', 'a2', 'b2']]
_, result = apriori_based_anon(ATT_TREE, trans, 'AA', 2, 2)
self.assertEqual(result[2], {'a1': 'A', 'a2': 'A'})
_, result = apriori_based_anon(ATT_TREE, trans, 'DA', 2, 2)
self.assertEqual(result[2], {'a1': 'A', 'a2': 'A'})
def test_DA_partition_case2(self):
init_tree()
trans = [['a1'],
['a1', 'a2'],
['b1', 'b2'],
['b1', 'b2'],
['a1', 'a2', 'b2'],
['a1', 'a2', 'b2'],
['a1', 'a2', 'b1', 'b2']]
_, result = apriori_based_anon(ATT_TREE, trans, 'DA', 2, 4)
# not {'a1': 'A', 'a2': 'A', 'b1': 'B', 'b2': 'B'}
self.assertEqual(result[2], {'b1': 'B', 'b2': 'B'})
_, result = apriori_based_anon(ATT_TREE, trans, 'DA', 2, 2)
self.assertEqual(result[2], {'b1': 'B', 'b2': 'B'})
def get_result_dataset(att_tree,
data,
type_alg='AA',
k=DEFALUT_K,
num_test=10):
"""
fix k, while changing size of dataset
num_test is the test nubmber.
"""
print "K=%d" % k
print "m=%d" % DEFALUT_M
data_back = copy.deepcopy(data)
length = len(data_back)
joint = 5000
dataset_num = length / joint
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 = apriori_based_anon(att_tree, 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_dataset(att_tree, data, type_alg='AA', k=DEFALUT_K, num_test=10):
"""
fix k, while changing size of dataset
num_test is the test nubmber.
"""
print "K=%d" % k
print "m=%d" % DEFALUT_M
data_back = copy.deepcopy(data)
length = len(data_back)
joint = 5000
dataset_num = length / joint
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 = apriori_based_anon(att_tree, 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_tree, data, type_alg, k=DEFALUT_K):
"""
run apriori_based_anon for one time, with k=10
"""
print "K=%d" % k
print "Size of Data", len(data)
print "m=%d" % DEFALUT_M
_, eval_result = apriori_based_anon(att_tree, 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_tree, data, type_alg, k=DEFALUT_K):
"""
run apriori_based_anon for one time, with k=10
"""
print "K=%d" % k
print "Size of Data", len(data)
print "m=%d" % DEFALUT_M
_, eval_result = apriori_based_anon(att_tree, data, type_alg, k)
print "NCP %0.2f" % eval_result[0] + "%"
print "Running time %0.2f" % eval_result[1] + " seconds"
def get_result_k(att_tree, data, type_alg):
"""
change k, whle fixing size of dataset
"""
data_back = copy.deepcopy(data)
# for k in range(5, 105, 5):
print "m=%d" % DEFALUT_M
print "Size of Data", len(data)
for k in [2, 5, 10, 25, 50]:
print '#' * 30
print "K=%d" % k
result, eval_result = apriori_based_anon(att_tree, 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 get_result_m(att_tree, data, type_alg, k=DEFALUT_K):
"""
change k, whle fixing size of dataset
"""
print "K=%d" % k
print "Size of Data", len(data)
data_back = copy.deepcopy(data)
# for m in range(1, 100, 5):
for m in [1, 2, 3, 4, 5, M_MAX]:
print '#' * 30
print "m=%d" % m
result, eval_result = apriori_based_anon(att_tree, data, type_alg, k, m)
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_tree, data, type_alg):
"""
change k, whle fixing size of dataset
"""
data_back = copy.deepcopy(data)
# for k in range(5, 105, 5):
print "m=%d" % DEFALUT_M
print "Size of Data", len(data)
for k in [2, 5, 10, 25, 50]:
print '#' * 30
print "K=%d" % k
result, eval_result = apriori_based_anon(att_tree, 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 get_result_m(att_tree, data, type_alg, k=DEFALUT_K):
"""
change k, whle fixing size of dataset
"""
print "K=%d" % k
print "Size of Data", len(data)
data_back = copy.deepcopy(data)
# for m in range(1, 100, 5):
for m in [1, 2, 3, 4, 5, M_MAX]:
print '#' * 30
print "m=%d" % m
result, eval_result = apriori_based_anon(att_tree, data, type_alg, k,
m)
data = copy.deepcopy(data_back)
print "NCP %0.2f" % eval_result[0] + "%"
print "Running time %0.2f" % eval_result[1] + " seconds"
def T_Gen(trans, k=25, m=2):
"""transaction generalization based on AA
"""
# using AA to generalization transaction part
result, eval_result = apriori_based_anon(ATT_TREES[-1], trans, 'AA', k, m)
return result, eval_result
def T_Gen(trans, k=25, m=2):
"""transaction generalization based on AA
"""
# using AA to generalization transaction part
result, eval_result = apriori_based_anon(ATT_TREES[-1], trans, 'AA', k, m)
return result, eval_result
def test_DA(self):
init_tree()
trans = [['a1', 'b1', 'b2'], ['a2', 'b1'], ['a2', 'b1', 'b2'],
['a1', 'a2', 'b2']]
_, result = apriori_based_anon(ATT_TREE, trans, 'DA', 2, 2)
self.assertEqual(result[2], {'a1': 'A', 'a2': 'A'})
