class TestOCSVM(unittest.TestCase):
def setUp(self):
self.n_train = 200
self.n_test = 100
self.contamination = 0.1
self.roc_floor = 0.8
self.X_train, self.y_train, self.X_test, self.y_test = generate_data(
n_train=self.n_train,
n_test=self.n_test,
contamination=self.contamination,
random_state=42)
self.clf = OCSVM()
self.clf.fit(self.X_train)
def test_parameters(self):
assert (hasattr(self.clf, 'decision_scores_')
and self.clf.decision_scores_ is not None)
assert (hasattr(self.clf, 'labels_') and self.clf.labels_ is not None)
assert (hasattr(self.clf, 'threshold_')
and self.clf.threshold_ is not None)
assert (hasattr(self.clf, '_mu') and self.clf._mu is not None)
assert (hasattr(self.clf, '_sigma') and self.clf._sigma is not None)
assert (hasattr(self.clf, 'support_')
and self.clf.support_ is not None)
assert (hasattr(self.clf, 'support_vectors_')
and self.clf.support_vectors_ is not None)
assert (hasattr(self.clf, 'dual_coef_')
and self.clf.dual_coef_ is not None)
assert (hasattr(self.clf, 'intercept_')
and self.clf.intercept_ is not None)
# only available for linear kernel
# if not hasattr(self.clf, 'coef_') or self.clf.coef_ is None:
# self.assertRaises(AttributeError, 'coef_ is not set')
def test_train_scores(self):
assert_equal(len(self.clf.decision_scores_), self.X_train.shape[0])
def test_prediction_scores(self):
pred_scores = self.clf.decision_function(self.X_test)
# check score shapes
assert_equal(pred_scores.shape[0], self.X_test.shape[0])
# check performance
assert_greater(roc_auc_score(self.y_test, pred_scores), self.roc_floor)
def test_prediction_labels(self):
pred_labels = self.clf.predict(self.X_test)
assert_equal(pred_labels.shape, self.y_test.shape)
def test_prediction_proba_linear(self):
pred_proba = self.clf.predict_proba(self.X_test, method='linear')
assert_greater_equal(pred_proba.min(), 0)
assert_less_equal(pred_proba.max(), 1)
def test_prediction_proba_unify(self):
pred_proba = self.clf.predict_proba(self.X_test, method='unify')
assert_greater_equal(pred_proba.min(), 0)
assert_less_equal(pred_proba.max(), 1)
def test_prediction_proba_parameter(self):
with assert_raises(ValueError):
self.clf.predict_proba(self.X_test, method='something')
def test_fit_predict(self):
pred_labels = self.clf.fit_predict(self.X_train)
assert_equal(pred_labels.shape, self.y_train.shape)
def test_fit_predict_score(self):
self.clf.fit_predict_score(self.X_test, self.y_test)
self.clf.fit_predict_score(self.X_test,
self.y_test,
scoring='roc_auc_score')
self.clf.fit_predict_score(self.X_test,
self.y_test,
scoring='prc_n_score')
with assert_raises(NotImplementedError):
self.clf.fit_predict_score(self.X_test,
self.y_test,
scoring='something')
def test_predict_rank(self):
pred_socres = self.clf.decision_function(self.X_test)
pred_ranks = self.clf._predict_rank(self.X_test)
# assert the order is reserved
assert_allclose(rankdata(pred_ranks), rankdata(pred_socres), atol=3.5)
assert_array_less(pred_ranks, self.X_train.shape[0] + 1)
assert_array_less(-0.1, pred_ranks)
def test_predict_rank_normalized(self):
pred_socres = self.clf.decision_function(self.X_test)
pred_ranks = self.clf._predict_rank(self.X_test, normalized=True)
# assert the order is reserved
assert_allclose(rankdata(pred_ranks), rankdata(pred_socres), atol=3.5)
assert_array_less(pred_ranks, 1.01)
assert_array_less(-0.1, pred_ranks)
def tearDown(self):
pass
class SolverVAECIFAR():
def __init__(self,
data_name,
hidden_dim=256,
seed=0,
learning_rate=3e-4,
normal_class=0,
anomaly_ratio=0.1,
batch_size=128,
concentrated=0,
training_ratio=0.8,
SN=1,
Trim=1,
L=1.5,
max_epochs=100):
np.random.seed(seed)
torch.manual_seed(seed)
torch.cuda.manual_seed(seed)
use_cuda = torch.cuda.is_available()
self.device = torch.device("cuda" if use_cuda else "cpu")
self.L = L
if concentrated == 1.0:
full_data_name = 'CIFAR10_Concentrated'
elif concentrated == 0.0:
full_data_name = 'CIFAR10'
self.result_path = "./results/{}_{}/0.0/OCSVM/{}/".format(
full_data_name, normal_class, seed)
data_path = "./data/" + data_name + ".npy"
self.learning_rate = learning_rate
self.SN = SN
self.Trim = Trim
# self.dataset = RealGraphDataset(data_path, missing_ratio=0, radius=2)
self.dataset = CIFARVGGDataset(data_path,
normal_class=normal_class,
anomaly_ratio=anomaly_ratio,
concentrated=concentrated)
self.seed = seed
self.hidden_dim = hidden_dim
self.max_epochs = max_epochs
self.data_path = data_path
self.data_anomaly_ratio = self.dataset.__anomalyratio__()
self.batch_size = batch_size
self.input_dim = self.dataset.__dim__()
self.data_normaly_ratio = 1 - self.data_anomaly_ratio
n_sample = self.dataset.__len__()
self.n_train = int(n_sample * training_ratio)
self.n_test = n_sample - self.n_train
print('|data dimension: {}|data noise ratio:{}'.format(
self.dataset.__dim__(), self.data_anomaly_ratio))
self.training_data, self.testing_data = data.random_split(
dataset=self.dataset, lengths=[self.n_train, self.n_test])
self.ae = None
self.discriminator = None
self.model = None
def train(self):
self.model = OCSVM()
self.model.fit(self.training_data.dataset.x)
def test(self):
y_test_scores = self.model.decision_function(
self.testing_data.dataset.x)
auc = roc_auc_score(self.testing_data.dataset.y, y_test_scores)
from sklearn.metrics import precision_recall_fscore_support as prf, accuracy_score
print("AUC:{:0.4f}".format(auc))
os.makedirs(self.result_path, exist_ok=True)
np.save(
self.result_path + "result.npy",
{
"accuracy": auc,
"precision": auc,
"recall": auc,
"f1": auc,
"auc": auc,
},
) # for consistency
print("result save to {}".format(self.result_path))
n_features=2,
contamination=contamination,
random_state=42)
# train one_class_svm detector
clf_name = 'OneClassSVM'
clf = OCSVM()
clf.fit(X_train)
# get the prediction labels and outlier scores of the training data
y_train_pred = clf.labels_ # binary labels (0: inliers, 1: outliers)
y_train_scores = clf.decision_scores_ # raw outlier scores
# get the prediction on the test data
y_test_pred = clf.predict(X_test) # outlier labels (0 or 1)
y_test_scores = clf.decision_function(X_test) # outlier scores
# evaluate and print the results
print("\nOn Training Data:")
evaluate_print(clf_name, y_train, y_train_scores)
print("\nOn Test Data:")
evaluate_print(clf_name, y_test, y_test_scores)
# visualize the results
visualize(clf_name,
X_train,
y_train,
X_test,
y_test,
y_train_pred,
y_test_pred,
class TestOCSVM(unittest.TestCase):
def setUp(self):
self.n_train = 100
self.n_test = 50
self.contamination = 0.1
self.roc_floor = 0.6
self.X_train, self.y_train, self.X_test, self.y_test = generate_data(
n_train=self.n_train, n_test=self.n_test,
contamination=self.contamination, random_state=42)
self.clf = OCSVM()
self.clf.fit(self.X_train)
def test_sklearn_estimator(self):
check_estimator(self.clf)
def test_parameters(self):
assert_true(hasattr(self.clf, 'decision_scores_') and
self.clf.decision_scores_ is not None)
assert_true(hasattr(self.clf, 'labels_') and
self.clf.labels_ is not None)
assert_true(hasattr(self.clf, 'threshold_') and
self.clf.threshold_ is not None)
assert_true(hasattr(self.clf, '_mu') and
self.clf._mu is not None)
assert_true(hasattr(self.clf, '_sigma') and
self.clf._sigma is not None)
assert_true(hasattr(self.clf, 'support_') and
self.clf.support_ is not None)
assert_true(hasattr(self.clf, 'support_vectors_') and
self.clf.support_vectors_ is not None)
assert_true(hasattr(self.clf, 'dual_coef_') and
self.clf.dual_coef_ is not None)
assert_true(hasattr(self.clf, 'intercept_') and
self.clf.intercept_ is not None)
# only available for linear kernel
# if not hasattr(self.clf, 'coef_') or self.clf.coef_ is None:
# self.assertRaises(AttributeError, 'coef_ is not set')
def test_train_scores(self):
assert_equal(len(self.clf.decision_scores_), self.X_train.shape[0])
def test_prediction_scores(self):
pred_scores = self.clf.decision_function(self.X_test)
# check score shapes
assert_equal(pred_scores.shape[0], self.X_test.shape[0])
# check performance
assert_greater(roc_auc_score(self.y_test, pred_scores), self.roc_floor)
def test_prediction_labels(self):
pred_labels = self.clf.predict(self.X_test)
assert_equal(pred_labels.shape, self.y_test.shape)
def test_prediction_proba_linear(self):
pred_proba = self.clf.predict_proba(self.X_test, method='linear')
assert_greater_equal(pred_proba.min(), 0)
assert_less_equal(pred_proba.max(), 1)
def test_prediction_proba_unify(self):
pred_proba = self.clf.predict_proba(self.X_test, method='unify')
assert_greater_equal(pred_proba.min(), 0)
assert_less_equal(pred_proba.max(), 1)
def test_prediction_proba_parameter(self):
with assert_raises(ValueError):
self.clf.predict_proba(self.X_test, method='something')
def test_fit_predict(self):
pred_labels = self.clf.fit_predict(self.X_train)
assert_equal(pred_labels.shape, self.y_train.shape)
def test_fit_predict_score(self):
self.clf.fit_predict_score(self.X_test, self.y_test)
self.clf.fit_predict_score(self.X_test, self.y_test,
scoring='roc_auc_score')
self.clf.fit_predict_score(self.X_test, self.y_test,
scoring='prc_n_score')
with assert_raises(NotImplementedError):
self.clf.fit_predict_score(self.X_test, self.y_test,
scoring='something')
def test_predict_rank(self):
pred_socres = self.clf.decision_function(self.X_test)
pred_ranks = self.clf._predict_rank(self.X_test)
# assert the order is reserved
assert_allclose(rankdata(pred_ranks), rankdata(pred_socres), atol=2)
assert_array_less(pred_ranks, self.X_train.shape[0] + 1)
assert_array_less(-0.1, pred_ranks)
def test_predict_rank_normalized(self):
pred_socres = self.clf.decision_function(self.X_test)
pred_ranks = self.clf._predict_rank(self.X_test, normalized=True)
# assert the order is reserved
assert_allclose(rankdata(pred_ranks), rankdata(pred_socres), atol=2)
assert_array_less(pred_ranks, 1.01)
assert_array_less(-0.1, pred_ranks)
def tearDown(self):
pass
class TestOCSVM(unittest.TestCase):
def setUp(self):
self.n_train = 100
self.n_test = 50
self.contamination = 0.1
self.roc_floor = 0.6
self.X_train, self.y_train, self.X_test, self.y_test = generate_data(
n_train=self.n_train, n_test=self.n_test,
contamination=self.contamination)
self.clf = OCSVM()
self.clf.fit(self.X_train)
def test_sklearn_estimator(self):
check_estimator(self.clf)
def test_parameters(self):
if not hasattr(self.clf,
'decision_scores_') or self.clf.decision_scores_ is None:
self.assertRaises(AttributeError, 'decision_scores_ is not set')
if not hasattr(self.clf, 'labels_') or self.clf.labels_ is None:
self.assertRaises(AttributeError, 'labels_ is not set')
if not hasattr(self.clf, 'threshold_') or self.clf.threshold_ is None:
self.assertRaises(AttributeError, 'threshold_ is not set')
if not hasattr(self.clf,
'support_') or self.clf.support_ is None:
self.assertRaises(AttributeError, 'support_ is not set')
if not hasattr(self.clf,
'support_vectors_') or self.clf.support_vectors_ is None:
self.assertRaises(AttributeError, 'support_vectors_ is not set')
if not hasattr(self.clf, 'dual_coef_') or self.clf.dual_coef_ is None:
self.assertRaises(AttributeError, 'dual_coef_ is not set')
# only available for linear kernel
# if not hasattr(self.clf, 'coef_') or self.clf.coef_ is None:
# self.assertRaises(AttributeError, 'coef_ is not set')
if not hasattr(self.clf, 'intercept_') or self.clf.intercept_ is None:
self.assertRaises(AttributeError, 'intercept_ is not set')
def test_train_scores(self):
assert_equal(len(self.clf.decision_scores_), self.X_train.shape[0])
def test_prediction_scores(self):
pred_scores = self.clf.decision_function(self.X_test)
# check score shapes
assert_equal(pred_scores.shape[0], self.X_test.shape[0])
# check performance
assert_greater(roc_auc_score(self.y_test, pred_scores), self.roc_floor)
def test_prediction_labels(self):
pred_labels = self.clf.predict(self.X_test)
assert_equal(pred_labels.shape, self.y_test.shape)
def test_prediction_proba_linear(self):
pred_proba = self.clf.predict_proba(self.X_test, method='linear')
assert_greater_equal(pred_proba.min(), 0)
assert_less_equal(pred_proba.max(), 1)
def test_prediction_proba_unify(self):
pred_proba = self.clf.predict_proba(self.X_test, method='unify')
assert_greater_equal(pred_proba.min(), 0)
assert_less_equal(pred_proba.max(), 1)
def test_prediction_proba_parameter(self):
with assert_raises(ValueError):
self.clf.predict_proba(self.X_test, method='something')
def test_fit_predict(self):
pred_labels = self.clf.fit_predict(self.X_train)
assert_equal(pred_labels.shape, self.y_train.shape)
def test_evaluate(self):
self.clf.fit_predict_evaluate(self.X_test, self.y_test)
def tearDown(self):
pass
#划分测试集和训练集
X_train, X_test, y_train, y_test = train_test_split(x, y, test_size=0.33)
#使用pyod中的OCSVM算法拟合数据
clf_name = 'OCSVM'
clf = OCSVM()
clf.fit(X_train)
#预测得到由0和1组成的数组，1表示离群点，0表示飞离群点
y_train_pred = clf.labels_ # binary labels (0: inliers, 1: outliers)
y_train_scores = clf.decision_scores_ # raw outlier scores，The outlier scores of the training data.
#预测样本是不是离群点，返回0和1 的数组
y_test_pred = clf.predict(X_test)
y_test_scores = clf.decision_function(
X_test) # outlier scores，The anomaly score of the input samples.
#使用sklearn中的roc_auc_score方法得到auc值，即roc曲线下面的面积
try:
sumAuc_train += sklearn.metrics.roc_auc_score(y_train,
y_train_scores,
average='macro')
sumAuc_test += sklearn.metrics.roc_auc_score(y_test,
y_test_scores,
average='macro')
#s=precision_score(y_train, y_train_scores, average='macro')
i += 1
print(sumAuc_train, sumAuc_test)
except ValueError:
print('1')
pass
def run_all_models(all_array, labels, pca, data_set_name):
picture_name = all_array.get("# img", 1)
all_array = all_array.drop("# img", 1)
# standardizing data for processing
all_array = standardizer(all_array)
y = labels.get("in").to_numpy()
x_train, x_test, y_train, y_test, picture_train, picture_test = train_test_split(all_array, y, picture_name,
test_size=0.4)
if pca:
transformer = IncrementalPCA()
all_array = transformer.fit_transform(all_array)
print("OCSVM")
now = time()
clf = OCSVM()
clf.fit(x_train)
test_scores = clf.decision_function(x_test)
temp = print_score(picture_test, test_scores, y_test)
train_scores = clf.decision_function(x_train)
scores_train = print_score(picture_train, train_scores, y_train)
output_table.append(("OCSVM", all_array.shape, temp, data_set_name, time() - now, scores_train))
print("Auto-encoder")
now = time()
clf = AutoEncoder(epochs=30)
clf.fit(x_train)
test_scores = clf.decision_function(x_test)
temp = print_score(picture_test, test_scores, y_test)
train_scores = clf.decision_function(x_train)
scores_train = print_score(picture_train, train_scores, y_train)
output_table.append(("Auto-encoder", all_array.shape, temp, data_set_name, time() - now, scores_train))
print("HBOS")
now = time()
clf = HBOS()
clf.fit(x_train)
test_scores = clf.decision_function(x_test)
temp = print_score(picture_test, test_scores, y_test)
train_scores = clf.decision_function(x_train)
scores_train = print_score(picture_train, train_scores, y_train)
output_table.append(("HBOS", all_array.shape, temp, data_set_name, time() - now, scores_train))
print("SO_GAAL")
now = time()
clf = SO_GAAL()
clf.fit(x_train)
test_scores = clf.decision_function(x_test)
temp = print_score(picture_test, test_scores, y_test)
train_scores = clf.decision_function(x_train)
scores_train = print_score(picture_train, train_scores, y_train)
output_table.append(("SO_GAAL", all_array.shape, temp, data_set_name, time() - now, scores_train))
print("MO_GAAL")
now = time()
clf = MO_GAAL()
clf.fit(x_train)
test_scores = clf.decision_function(x_test)
temp = print_score(picture_test, test_scores, y_test)
train_scores = clf.decision_function(x_train)
scores_train = print_score(picture_train, train_scores, y_train)
output_table.append(("MO_GAAL", all_array.shape, temp, data_set_name, time() - now, scores_train))
print("MCD")
now = time()
clf = MCD()
clf.fit(x_train)
test_scores = clf.decision_function(x_test)
temp = print_score(picture_test, test_scores, y_test)
train_scores = clf.decision_function(x_train)
scores_train = print_score(picture_train, train_scores, y_train)
output_table.append(("MCD", all_array.shape, temp, data_set_name, time() - now, scores_train))
print("SOS")
now = time()
clf = SOS()
clf.fit(x_train)
test_scores = clf.decision_function(x_test)
temp = print_score(picture_test, test_scores, y_test)
train_scores = clf.decision_function(x_train)
scores_train = print_score(picture_train, train_scores, y_train)
output_table.append(("SOS", all_array.shape, temp, data_set_name, time() - now, scores_train))
print("IForest")
now = time()
clf = IForest()
clf.fit(x_train)
test_scores = clf.decision_function(x_test)
temp = print_score(picture_test, test_scores, y_test)
train_scores = clf.decision_function(x_train)
scores_train = print_score(picture_train, train_scores, y_train)
output_table.append(("IFrorest", all_array.shape, temp, data_set_name, time() - now, scores_train))
print("KNN")
now = time()
clf = KNN()
clf.fit(x_train)
test_scores = clf.decision_function(x_test)
temp = print_score(picture_test, test_scores, y_test)
train_scores = clf.decision_function(x_train)
scores_train = print_score(picture_train, train_scores, y_train)
output_table.append(("KNN", all_array.shape, temp, data_set_name, time() - now, scores_train))
print("PCA")
now = time()
clf = PCA()
clf.fit(x_train)
test_scores = clf.decision_function(x_test)
temp = print_score(picture_test, test_scores, y_test)
train_scores = clf.decision_function(x_train)
scores_train = print_score(picture_train, train_scores, y_train)
output_table.append(("PCA", all_array.shape, temp, data_set_name, time() - now, scores_train))
def main():
parser = argparse.ArgumentParser(description='baseline')
register_data_args(parser)
parser.add_argument("--mode",
type=str,
default='A',
choices=['A', 'AX', 'X'],
help="dropout probability")
parser.add_argument("--seed",
type=int,
default=-1,
help="random seed, -1 means dont fix seed")
parser.add_argument(
"--emb-method",
type=str,
default='DeepWalk',
help="embedding methods: DeepWalk, Node2Vec, LINE, SDNE, Struc2Vec")
parser.add_argument("--ad-method",
type=str,
default='OCSVM',
help="embedding methods: PCA,OCSVM,IF,AE")
args = parser.parse_args()
if args.seed != -1:
np.random.seed(args.seed)
torch.manual_seed(args.seed)
torch.cuda.manual_seed_all(args.seed)
logging.basicConfig(
filename="./log/baseline.log",
filemode="a",
format="%(asctime)s-%(name)s-%(levelname)s-%(message)s",
level=logging.INFO)
logger = logging.getLogger('baseline')
datadict = emb_dataloader(args)
if args.mode == 'X':
data = datadict['features']
#print('X shape',data.shape)
else:
t0 = time.time()
embeddings = embedding(args, datadict)
dur1 = time.time() - t0
if args.mode == 'A':
data = embeddings
#print('A shape',data.shape)
if args.mode == 'AX':
data = np.concatenate((embeddings, datadict['features']), axis=1)
#print('AX shape',data.shape)
logger.debug(f'data shape: {data.shape}')
if args.ad_method == 'OCSVM':
clf = OCSVM(contamination=0.1)
if args.ad_method == 'IF':
clf = IForest(n_estimators=100,
contamination=0.1,
n_jobs=-1,
behaviour="new")
if args.ad_method == 'PCA':
clf = PCA(contamination=0.1)
if args.ad_method == 'AE':
clf = AutoEncoder(contamination=0.1)
t1 = time.time()
clf.fit(data[datadict['train_mask']])
dur2 = time.time() - t1
print('traininig time:', dur1 + dur2)
logger.info('\n')
logger.info('\n')
logger.info(
f'Parameters dataset:{args.dataset} datamode:{args.mode} ad-method:{args.ad_method} emb-method:{args.emb_method}'
)
logger.info('-------------Evaluating Validation Results--------------')
t2 = time.time()
y_pred_val = clf.predict(data[datadict['val_mask']])
y_score_val = clf.decision_function(data[datadict['val_mask']])
auc, ap, f1, acc, precision, recall = baseline_evaluate(datadict,
y_pred_val,
y_score_val,
val=True)
dur3 = time.time() - t2
print('infer time:', dur3)
logger.info(f'AUC:{round(auc,4)},AP:{round(ap,4)}')
logger.info(
f'f1:{round(f1,4)},acc:{round(acc,4)},pre:{round(precision,4)},recall:{round(recall,4)}'
)
logger.info('-------------Evaluating Test Results--------------')
y_pred_test = clf.predict(data[datadict['test_mask']])
y_score_test = clf.decision_function(data[datadict['test_mask']])
auc, ap, f1, acc, precision, recall = baseline_evaluate(datadict,
y_pred_test,
y_score_test,
val=False)
logger.info(f'AUC:{round(auc,4)},AP:{round(ap,4)}')
logger.info(
f'f1:{round(f1,4)},acc:{round(acc,4)},pre:{round(precision,4)},recall:{round(recall,4)}'
)