def process_dataframe(df):
# Replace attack string with an int
for i in range(len(attack_cat_values)):
df['attack_cat'] = df['attack_cat'].replace([attack_cat_values[i]],
i)
# Assign x (inputs) and y (outputs) of the network
y = df['attack_cat']
x = df.drop(columns='attack_cat')
# ***** MULTIPLE ENCODER CHOICE *****
# Encode categorical features as an integer array
if params['encoder'] == 'ordinalencoder':
x = OrdinalEncoder().fit_transform(x)
# Encode labels with value between 0 and n_classes-1.
elif params['encoder'] == 'labelencoder':
x = x.apply(LabelEncoder().fit_transform)
else:
# Replace String features with ints
for i in range(len(proto_values)):
x['proto'] = x['proto'].replace(proto_values[i], i)
for i in range(len(state_values)):
x['state'] = x['state'].replace(state_values[i], i)
for i in range(len(service_values)):
x['service'] = x['service'].replace(service_values[i], i)
# Standardize by removing the mean and scaling to unit variance
if params['encoder'] == "standardscaler":
x = StandardScaler().fit_transform(x)
# Transforms features by scaling each feature to range [0, 1]
elif params['encoder'] == "minmaxscaler01":
x = MinMaxScaler(feature_range=(0, 1)).fit_transform(x)
# Transforms features by scaling each feature to range [-1, 1]
elif params['encoder'] == "minmaxscaler11":
x = MinMaxScaler(feature_range=(-1, 1)).fit_transform(x)
return x, y
def process_dataframe(df):
# Select 4, 8 or 41 features
if params['features_nb'] == 4:
features = four_features
elif params['features_nb'] == 8:
features = eight_features
else:
features = full_features
df = df[features]
# Replace connexion type string with an int (also works with NSL)
df['label'] = df['label'].replace(['normal.', 'normal'], 0)
for i in range(len(entry_type['probe'])):
df['label'] = df['label'].replace(
[entry_type['probe'][i], entry_type['probe'][i][:-1]], 1)
for i in range(len(entry_type['dos'])):
df['label'] = df['label'].replace(
[entry_type['dos'][i], entry_type['dos'][i][:-1]], 2)
for i in range(len(entry_type['u2r'])):
df['label'] = df['label'].replace(
[entry_type['u2r'][i], entry_type['u2r'][i][:-1]], 3)
for i in range(len(entry_type['r2l'])):
df['label'] = df['label'].replace(
[entry_type['r2l'][i], entry_type['r2l'][i][:-1]], 4)
# For NSL KDD
if "difficulty" in df.columns:
df = df.drop(columns='difficulty')
# Assign x (inputs) and y (outputs) of the network
y = df['label']
x = df.drop(columns='label')
# ***** MULTIPLE ENCODER CHOICE *****
# Encode categorical features as an integer array
if params['encoder'] == 'ordinalencoder':
x = OrdinalEncoder().fit_transform(x)
# Encode labels with value between 0 and n_classes-1.
elif params['encoder'] == 'labelencoder':
x = x.apply(LabelEncoder().fit_transform)
else:
# Replace String features with ints
if 'service' in features:
for i in range(len(service_values)):
x['service'] = x['service'].replace(service_values[i], i)
if 'protocol_type' in features:
for i in range(len(protocol_type_values)):
x['protocol_type'] = x['protocol_type'].replace(
protocol_type_values[i], i)
if 'flag' in features:
for i in range(len(flag_values)):
x['flag'] = x['flag'].replace(flag_values[i], i)
# Standardize by removing the mean and scaling to unit variance
if params['encoder'] == "standardscaler":
x = StandardScaler().fit_transform(x)
# Transforms features by scaling each feature to range [0, 1]
elif params['encoder'] == "minmaxscaler01":
x = MinMaxScaler(feature_range=(0, 1)).fit_transform(x)
# Transforms features by scaling each feature to range [-1, 1]
elif params['encoder'] == "minmaxscaler11":
x = MinMaxScaler(feature_range=(-1, 1)).fit_transform(x)
return x, y
