load_iot_data_fix_labels.py

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])
df.drop("Attack_type", axis=1, inplace=True)
df = df.sample(frac=1)
df.shape