This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# recombine training and validation data | |
X_tv = torch.cat((X_train.cpu(), X_val.cpu())) | |
y_tv = torch.cat((y_train.cpu(), y_val.cpu())) | |
np.random.seed(101) | |
sample_weights = compute_sample_weight(class_weight='balanced',y=y_tv) | |
model = XGBClassifier() | |
model.fit(X_tv, y_tv, sample_weight=sample_weights) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
np.random.seed(42) | |
df = pd.read_csv("data/RT_IOT2022.csv") | |
s = ['DOS_SYN_Hping', 'Thing_Speak', 'ARP_poisioning', 'MQTT_Publish'] | |
s_dict = {'DOS_SYN_Hping':0, 'Thing_Speak':1, 'ARP_poisioning':2, 'MQTT_Publish':3} | |
df = df[df.Attack_type.isin(s)] | |
df.drop("Unnamed: 0", axis=1, inplace=True) | |
df.drop("service", axis=1, inplace=True) | |
df.drop("proto", axis=1, inplace=True) | |
# df = pd.get_dummies(df, columns=['service', 'proto'])*1 | |
df["label"] = df.Attack_type.apply(lambda x: s_dict[x]) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
torch.manual_seed(101) | |
# Make predictions | |
model.eval() | |
with torch.inference_mode(): | |
y_logits = model(X_test).to(device) | |
y_preds = torch.softmax(y_logits, dim=1).argmax(dim=1) | |
accuracy = Accuracy(task="multiclass", num_classes=model.output_features).to(device) | |
confusion = ConfusionMatrix(task="multiclass", num_classes=model.output_features).to(device) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
plt.plot(train_losses, label='train') | |
plt.plot(val_losses, label='validation') | |
plt.title("Train/Validation Loss") | |
plt.legend() | |
plt.tight_layout() | |
plt.show() | |
plt.plot(train_accs, label='train') | |
plt.plot(val_accs, label='validation') | |
plt.title("Train/Validation Accuracy") |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
torch.manual_seed(101) | |
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') | |
# input_features = 91 | |
input_features = 81 | |
output_features = 4 | |
hidden_units = 128 #128 | |
dropout = 0.0 | |
lr = 0.001 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
sample_weights = compute_sample_weight(class_weight='balanced',y=df.label) | |
label_weights = { k:v for k, v in sorted(list(zip(df.label, sample_weights)))} | |
label_weights = torch.tensor(list(label_weights.values()), dtype=torch.float32) | |
label_weights |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
df = pd.read_csv("data/RT_IOT2022.csv") | |
print(df.shape) | |
print("===========================================") | |
print(df.head()) | |
print(df[['service', 'proto', 'Attack_type']]) | |
labels = dict(Counter(df.Attack_type).most_common()) | |
print(labels) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
def training_loop(model, X_train, X_val, y_train, y_val, epochs = 1000, weight_decay = 0.0, lr=0.001, device='cuda'): | |
# Put all data on target device | |
X_train, y_train = X_train.to(device), y_train.to(device) #y_train.unsqueeze(dim=1).to(device) | |
X_val, y_val = X_val.to(device), y_val.to(device) #y_test.unsqueeze(dim=1).to(device) | |
# Define the accuracy function and initialize train/validation accuracy and loss lists | |
accuracy = Accuracy(task="multiclass", num_classes=model.output_features).to(device) | |
train_losses, train_accs, val_losses, val_accs = [], [], [], [] | |
loss_fn = nn.CrossEntropyLoss(weight=label_weights.to(device)) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Build model | |
class IoTMultiClassModel(nn.Module): | |
def __init__(self, input_features=91, output_features=4, hidden_units=128, dropout=0.0): | |
super().__init__() | |
self.input_features = input_features | |
self.output_features = output_features | |
self.hidden_units = hidden_units | |
self.linear_layer_stack = nn.Sequential( |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# setting device on GPU if available, else CPU | |
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') | |
print('Using device:', device) | |
print() | |
#Additional Info when using cuda | |
dev = 0 | |
if device.type == 'cuda': | |
print(torch.cuda.get_device_name(dev)) | |
print('Memory Usage:') |
NewerOlder