def RF(opts):
FOLDER = 'clean_vpn12_rf'
param_grid = {
'critire': ['gini', 'gain'],
'n_estimators': [200, 700],
'max_features': ['auto', 'sqrt', 'log2'],
'min_samples_split': np.arange(2, 30, 2),
'max_depth':np.arange(2, 31)
}
classifier = RandomForestClassifier(n_jobs=-1, oob_score=True)
rf = ML_Model("Random Forest", classifier, param_grid)
X_train, y_train = data_process(opts)
X_train = normalize(X_train, norm = 'l2', axis=0, copy = True, return_norm = False)
X_train, X_test, y_train, y_test = train_test_split(X_train, y_train, test_size=0.33, random_state=42)
X_train, X_val, y_train, y_val = train_test_split(X_train, y_train, test_size=0.1, random_state=42)
dim = np.shape(X_train)[1]
size = np.shape(X_train)[0]
print(size, dim)
rf.model_path = FOLDER
train_ml(rf, X_train, y_train, X_test, y_test, opts.sets, FOLDER, random = True)
return rf
def XGB(opts):
FOLDER = 'clean_vpn12_xgb'
xgb = XGBClassifier(
learning_rate=0.1,
n_estimators=1000,
objective='multi:softmax',
nthread=4,
scale_pos_weight=1,
seed=27,
num_classes = 12)
param_grid = {
'max_depth': range(3, 10, 2),
'min_child_weight': range(1, 6, 2),
'gamma': [0.0, 0.1, 0.2, 0.3, 0.4, 0.5, 1, 1.5, 2, 5],
'subsample': [i / 10.0 for i in range(5, 11)],
'colsample_bytree': [i / 10.0 for i in range(5, 11)],
'reg_alpha': [1e-5, 1e-2, 0.1, 1, 100]
}
xgb = ML_Model('XGBoost', xgb, param_grid)
X_train, y_train = data_process(opts)
X_train = normalize(X_train, norm = 'l2', axis=0, copy = True, return_norm = False)
X_train, X_test, y_train, y_test = train_test_split(X_train, y_train, test_size=0.33, random_state=42)
X_train, X_val, y_train, y_val = train_test_split(X_train, y_train, test_size=0.1, random_state=42)
dim = np.shape(X_train)[1]
size = np.shape(X_train)[0]
print(size, dim)
xgb.model_path = FOLDER
train_ml(xgb, X_train, y_train, X_test, y_test, opts.sets, FOLDER, random = True)
return xgb
def NBMULTI(opts):
FOLDER = 'clean_vpn12_NB-Multi'
classifier = MultinomialNB()
X_train, y_train = data_process(opts)
#y_train = to_categorical(y_train, num_classes = nclass)
X_train = normalize(X_train, norm = 'max', axis=0, copy = True, return_norm = False)
X_train, X_test, y_train, y_test = train_test_split(X_train, y_train, test_size=0.3, random_state=42)
X_train, X_val, y_train, y_val = train_test_split(X_train, y_train, test_size=0.1, random_state=42)
dim = np.shape(X_train)[1]
size = np.shape(X_train)[0]
print(size, dim)
nb = ML_Model("MultinomialNB", classifier, None)
nb.model_path = FOLDER
train_ml(nb, X_train, y_train, X_test, y_test, opts.sets, FOLDER, random = True)
return nb
def LR(opts):
FOLDER = 'clean_vpn12_lr'
classifier = LogisticRegression(multi_class='ovr', penalty='l2')
param_grid = dict(C=[0.00001, 0.0001, 0.001, 0.01, 0.1, 1, 10, 100, 1000])
lr = ML_Model("Log. Regression", classifier, param_grid)
X_train, y_train = data_process(opts)
#y_train = to_categorical(y_train, num_classes = nclass)
X_train = normalize(X_train, norm = 'max', axis=0, copy = True, return_norm = False)
X_train, X_test, y_train, y_test = train_test_split(X_train, y_train, test_size=0.3, random_state=42)
X_train, X_val, y_train, y_val = train_test_split(X_train, y_train, test_size=0.1, random_state=42)
dim = np.shape(X_train)[1]
size = np.shape(X_train)[0]
print(size, dim)
lr.model_path = FOLDER
train_ml(lr, X_train, y_train, X_test, y_test, opts.sets, FOLDER, random = True)
return lr
def LINSVC(opts):
FOLDER = 'clean_vpnn_linearsvc'
classifier = svm.LinearSVC()
C_range = range(1, 200, 50)
param_grid = dict(C = C_range)
svmsvc = ML_Model("SVM-Linear", classifier, param_grid)
X_train, y_train = data_process(opts)
X_train = normalize(X_train, norm = 'l2', axis=0, copy = True, return_norm = False)
X_train, X_test, y_train, y_test = train_test_split(X_train, y_train, test_size=0.33, random_state=42)
X_train, X_val, y_train, y_val = train_test_split(X_train, y_train, test_size=0.1, random_state=42)
dim = np.shape(X_train)[1]
size = np.shape(X_train)[0]
print(size, dim)
svmsvc.model_path = FOLDER
train_ml(svmsvc, X_train, y_train, X_test, y_test, opts.sets, FOLDER, random = True)
return svmsvc
def SVMSVC(opts):
FOLDER = 'clean_vpn12_svc'
classifier = svm.SVC()
C_range = np.logspace(-2, 10, 13)
gamma_range = np.logspace(-9, 3, 13)
param_grid = dict(gamma=gamma_range, C=C_range)
X_train, y_train = data_process(opts)
X_train = normalize(X_train, norm = 'l2', axis=0, copy = True, return_norm = False)
X_train, X_test, y_train, y_test = train_test_split(X_train, y_train, test_size=0.33, random_state=42)
X_train, X_val, y_train, y_val = train_test_split(X_train, y_train, test_size=0.1, random_state=42)
dim = np.shape(X_train)[1]
size = np.shape(X_train)[0]
print(size, dim)
svmsvc = ML_Model('SVM-SVC', classifier, param_grid)
svmsvc.model_path = FOLDER
train_ml(svmsvc, X_train, y_train, X_test, y_test, opts.sets, FOLDER, random = True)
return svmsvc
def DTree(opts):
FOLDER = 'clean_vpn12_dtr'
classifier = DecisionTreeClassifier()
entropy_thresholds = np.linspace(0, 1, 50)
gini_thresholds = np.linspace(0, 0.5, 50)
param_grid = [{'criterion': ['entropy'], 'min_impurity_decrease': entropy_thresholds},
{'criterion': ['gini'], 'min_impurity_decrease': gini_thresholds},
{'max_depth': np.arange(2, 31)},
{'min_samples_split': np.arange(2, 30, 2)}]
dtree = ML_Model('Decision Tree', classifier, param_grid)
X_train, y_train = data_process(opts)
X_train = normalize(X_train, norm = 'l2', axis=0, copy = True, return_norm = False)
X_train, X_test, y_train, y_test = train_test_split(X_train, y_train, test_size=0.33, random_state=42)
X_train, X_val, y_train, y_val = train_test_split(X_train, y_train, test_size=0.1, random_state=42)
dim = np.shape(X_train)[1]
size = np.shape(X_train)[0]
print(size, dim)
dtree.model_path = FOLDER
train_ml(dtree, X_train, y_train, X_test, y_test, opts.sets, FOLDER, random = True)
return dtree
def ALLModels(opts):
models = []
#models.append(XGB(opts))
#models.append(DTree(opts))
#models.append(LR(opts))
#models.append(SVMSVC(opts))
#models.append(LINSVC(opts))
#models.append(NBMULTI(opts))
#models.append(NBBonuli(opts))
X_train, y_train = data_process(opts)
#y_train = to_categorical(y_train, num_classes = nclass)
X_train = normalize(X_train, norm = 'max', axis=0, copy = True, return_norm = False)
X_train, X_test, y_train, y_test = train_test_split(X_train, y_train, test_size=0.3, random_state=42)
X_train, X_val, y_train, y_val = train_test_split(X_train, y_train, test_size=0.1, random_state=42)
FOLDER = 'clean_vpn12_rf'
param_grid = {
'critire': ['gini', 'gain'],
'n_estimators': [200, 700],
'max_features': ['auto', 'sqrt', 'log2'],
'min_samples_split': np.arange(2, 30, 2),
'max_depth':np.arange(2, 31)
}
classifier = RandomForestClassifier(n_jobs=-1, oob_score=True)
rf = ML_Model("Random Forest", classifier, param_grid)
rf.model_path = FOLDER
models.append(rf)
FOLDER = 'clean_vpn12_lr'
classifier = LogisticRegression(multi_class='ovr', penalty='l2')
param_grid = dict(C=[0.00001, 0.0001, 0.001, 0.01, 0.1, 1, 10, 100, 1000])
lr = ML_Model("Log. Regression", classifier, param_grid)
lr.model_path = FOLDER
models.append(lr)
classifier = BernoulliNB()
FOLDER = 'clean_vpn12_NB-Bonulina'
nb = ML_Model("NB-Bernoulli", classifier, None)
nb.model_path = FOLDER
models.append(nb)
FOLDER = 'clean_vpn12_xgb'
xgb = XGBClassifier(
learning_rate=0.1,
n_estimators=1000,
objective='multi:softmax',
nthread=4,
scale_pos_weight=1,
seed=27,
num_classes = 12)
param_grid = {
'max_depth': range(3, 10, 2),
'min_child_weight': range(1, 6, 2),
'gamma': [0.0, 0.1, 0.2, 0.3, 0.4, 0.5, 1, 1.5, 2, 5],
'subsample': [i / 10.0 for i in range(5, 11)],
'colsample_bytree': [i / 10.0 for i in range(5, 11)],
'reg_alpha': [1e-5, 1e-2, 0.1, 1, 100]
}
xgb = ML_Model('XGBoost', xgb, param_grid)
xgb.model_path = FOLDER
models.append(xgb)
FOLDER = 'clean_vpn12_svc'
classifier = svm.SVC()
C_range = np.logspace(-2, 10, 13)
gamma_range = np.logspace(-9, 3, 13)
param_grid = dict(gamma=gamma_range, C=C_range)
svmsvc = ML_Model('SVM-SVC', classifier, param_grid)
svmsvc.model_path = FOLDER
models.append(svmsvc)
final_train(models, X_train, y_train, X_test, y_test, opts.sets)
ML_Model.models_metric_summary(models)