def gen_with_smote(target_class, target_num, data_name, discrete_num_map):
smote = MySmote(data_name,
target_class=target_class,
data_map=discrete_num_map)
smote_predict = smote.predict(target_len=target_num,
data_map=discrete_num_map)
return smote_predict
def multi_classify(data_train_total, positive, negatives, pos_len, negs_len, data_map, data_name, expend=False,
using_kdd99=False):
if expend:
print('-' * 16 + 'expending' + '-' * 16)
for negative, neg_len in zip(negatives, negs_len):
neg_len = pos_len - neg_len
vae_predict = gen_with_vae(negative, neg_len, data_name)
if using_kdd99:
smote = MySmote(data_name, target_class=negative, data_map=data_map)
smote_predict = smote.predict(
target_len=neg_len, data_map=data_map)
for l in range(smote_predict.__len__()):
for i in range(len(smote_predict[l].attr_list)):
if smote_predict[l][i] == 'None':
smote_predict[l][i] = vae_predict[l][i]
else:
smote_predict = vae_predict
data_predict = []
for p in smote_predict:
res = fill_with_eucli_distance(data_train_total, p, data_map)
data_predict.append(res)
data_train_total.extend(data_predict)
y = [d.data_class for d in data_train_total]
if using_kdd99:
y = [get_kdd99_big_classification(c) for c in y]
# TODO PRINT
print({big_class: y.count(big_class) for big_class in set(y)})
data_train_total = [d.discrete_to_num(data_map=data_map).attr_list for d in data_train_total]
x = np.array(data_train_total).astype(np.float)
kf = KFold(n_splits=5, shuffle=True)
ones = copy.deepcopy(negatives) + [positive]
if using_kdd99:
ones = list(set([get_kdd99_big_classification(c) for c in ones]))
ones.sort()
for one in ones:
negs = [o for o in ones if o != one]
print('{} vs others'.format(one))
TP, TN, FP, FN = 0, 0, 0, 0
acc = 0
precision = 0
for i_train, i_test in kf.split(X=x, y=y):
train_x = [x[i] for i in i_train]
train_y = [y[i] for i in i_train]
test_x = [x[i] for i in i_test]
test_y = [y[i] for i in i_test]
# clf = svm.SVC()
# if expend:
clf = svm.SVC(kernel='linear')
clf.fit(train_x, train_y)
predict_y = [i for i in clf.predict(test_x)]
TP_k, TN_k, FP_k, FN_k = compute_TP_TN_FP_TN(class_test=test_y, class_predict=predict_y, positive=one,
negative=negs)
TP += TP_k
TN += TN_k
FP += FP_k
FN += FN_k
acc = compute_classification_indicators(TP, TN, FP, FN)[0]
# TODO PRINT
# print('{:>2.3f}'.format(TP / (TP + TN + FP + FN)))
print('acc : {:>2.3f}'.format(acc / 5))
def binary_classify(data_train_total, positive, negative, pos_len, neg_len, expend, data_map, data_name,
using_kdd99=False, vae_only=False):
if expend:
print('expending-------------------------------------------------------')
neg_len = pos_len - neg_len
# vae_predict = gen_with_multi_vae(negative, neg_len, data_name)
vae_predict = gen_with_vae(negative, neg_len, data_name)
if using_kdd99:
smote = MySmote(data_name, target_class=negative, data_map=data_map)
smote_predict = smote.predict(
target_len=neg_len, data_map=data_map)
for l in range(smote_predict.__len__()):
for i in range(len(smote_predict[l].attr_list)):
if smote_predict[l][i] == 'None':
smote_predict[l][i] = vae_predict[l][i]
else:
smote_predict = vae_predict
data_predict = []
for p in smote_predict:
res = fill_with_eucli_distance(data_train_total, p, data_map)
data_predict.append(res)
data_train_total.extend(data_predict)
y = [d.data_class for d in data_train_total]
if using_kdd99:
positive = get_kdd99_big_classification(positive)
negative = get_kdd99_big_classification(negative)
y = [get_kdd99_big_classification(c) for c in y]
if vae_only:
data_train_total = [d.discrete_to_num(data_map=data_map).to_list([DataType.CONTINUOUS]) for d in
data_train_total]
data_train_total = [d.discrete_to_num(data_map=data_map).attr_list for d in data_train_total]
# Todo:
x = np.array(data_train_total).astype(np.float)
print({k: y.count(k) for k in y})
# Todo: kf
kf = KFold(n_splits=5, shuffle=True)
args = []
for i_train, i_test in kf.split(X=x, y=y):
train_x = [x[i] for i in i_train]
train_y = [y[i] for i in i_train]
test_x = [x[i] for i in i_test]
test_y = [y[i] for i in i_test]
clf = svm.SVC(kernel='linear', probability=True,
random_state=np.random.RandomState(0))
# clf = svm.SVC()
# clf = GaussianNB()
# clf = tree.DecisionTreeClassifier()
clf.fit(train_x, train_y)
predict_y = [i for i in clf.predict(test_x)]
temp = compute_classification_indicators(*compute_TP_TN_FP_TN(test_y, predict_y, positive, negative))
if args.__len__() == 0:
args = temp
else:
args = [a + t for a, t in zip(args, temp)]
# print(
# u'acc\u208A: {:>2.3f}, acc\u208B: {:>2.3f}, accuracy: {:>2.3f}, precision: {:>2.3f}, recall: {:>2.3f}, F1: {:>2.3f}, G-mean: {:>2.3f}'
# .format(*[a / 5 for a in args]))
print(
u'acc+: {:>2.3f}, acc-: {:>2.3f}, accuracy: {:>2.3f}, precision: {:>2.3f}, recall: {:>2.3f}, F1: {:>2.3f}, G-mean: {:>2.3f}'
.format(*[a / 5 for a in args]))
print('')