class CumlSVMFitter(FitterBase):
def __init__(self,
label='label',
metric='error',
opt: SVMOpt = None,
max_eval=100):
super(CumlSVMFitter, self).__init__(label, metric, max_eval)
if opt is not None:
self.opt = opt
else:
self.opt = SVMOpt()
self.clf = None
def train(self, train_df, eval_df, params=None):
train_df, eval_df = cudf.DataFrame(train_df), cudf.DataFrame(eval_df)
x_train, y_train, x_eval, y_eval = train_df.drop(columns=[self.label]), train_df[self.label], \
eval_df.drop(columns=[self.label]), eval_df[self.label],
if params is None:
use_params = deepcopy(self.opt_params)
else:
use_params = deepcopy(params)
self.clf = SVC(**use_params)
self.clf.fit(X=x_train, y=y_train)
preds = self.clf.predict(X=x_eval)
output = self.get_loss(y_pred=preds, y=y_eval)
return output
def search(self, train_df, eval_df):
self.opt_params = dict()
def train_impl(params):
self.train(train_df, eval_df, params)
if self.metric == 'auc':
y_pred = self.clf.predict(eval_df.drop(columns=[self.label]))
else:
y_pred = self.clf.predict(
eval_df.drop(columns=[self.label])).astype(int)
return self.get_loss(eval_df[self.label], y_pred)
self.opt_params = fmin(train_impl,
asdict(self.opt),
algo=tpe.suggest,
max_evals=self.max_eval)
def search_k_fold(self, k_fold, data):
self.opt_params = dict()
def train_impl_nfold(params):
loss = list()
for train_id, eval_id in k_fold.split(data):
train_df = data.iloc[train_id, :]
eval_df = data.iloc[eval_id, :]
self.train(train_df, eval_df, params)
if self.metric == 'auc':
y_pred = self.clf.predict(
eval_df.drop(columns=[self.label]))
else:
y_pred = self.clf.predict(
eval_df.drop(columns=[self.label])).astype(int)
loss.append(self.get_loss(eval_df[self.label], y_pred))
return np.mean(loss)
self.opt_params = fmin(train_impl_nfold,
asdict(self.opt),
algo=tpe.suggest,
max_evals=self.max_eval)
def train_k_fold(self,
k_fold,
train_data,
test_data,
params=None,
drop_test_y=True):
acc_result = list()
train_pred = cudf.Series(np.empty(train_data.shape[0]))
test_pred = cudf.Series(np.empty(test_data.shape[0]))
if drop_test_y:
dtest = test_data.drop(columns=self.label)
else:
dtest = test_data
for train_id, eval_id in k_fold.split(train_data):
train_df = train_data.iloc[train_id, :]
eval_df = train_data.iloc[eval_id, :]
self.train(train_df, eval_df, params)
train_pred[eval_id] = self.clf.predict_proba(
eval_df.drop(columns=self.label)).iloc[:, 1].values
if self.metric == 'auc':
y_pred = self.clf.predict(eval_df.drop(columns=[self.label]))
else:
y_pred = self.clf.predict(
eval_df.drop(columns=[self.label])).astype(int)
acc_result.append(self.get_loss(eval_df[self.label], y_pred))
test_pred += self.clf.predict_proba(dtest).iloc[:, 1]
test_pred /= k_fold.n_splits
return train_pred, test_pred, acc_result
else:
C = 10
gamma = 0.01
clf = SVC(probability=True, C=C, gamma=gamma)
else:
clf = LogisticRegression() #normal case
clf.fit(X_train, y_train)
#save classifier
filename = './data/detectors/LR_' + attack_method + '_' + detector + '_' + mode + '_' + net + '.sav'
pickle.dump(clf, open(filename, 'wb'))
print('Evaluating classifier...')
prediction = clf.predict(X_test)
prediction_pr = clf.predict_proba(X_test)[:, 1]
benign_rate = 0
benign_guesses = 0
ad_guesses = 0
ad_rate = 0
for i in range(len(prediction)):
if prediction[i] == 0:
benign_guesses += 1
if y_test[i] == 0:
benign_rate += 1
else:
ad_guesses += 1
if y_test[i] == 1:
ad_rate += 1