Data preprocessing

Data preprocessing is an essential step for a DL pipeline. The CPU utilization dataset is ready to be used in the training, but the KDD cup 1999 IDS dataset needs multilevel preprocessing that includes the following three steps:

1. Splitting the data into three different protocol sets (application, transport, and network)
2. Duplicate data removal, categorical data conversion, and normalization
3. Feature selection (optional)

Using the following lines of code is a potential way of splitting the dataset into three datasets, namely Final_App_Layer, Final_Transport_Layer, and Final_Network_Layer:

#Importing all the required Libraries
import pandas as pd
IDSdata = pd.read_csv("kddcup.data_10_percent.csv",header = None,engine = 'python',sep=",")

# Add column header
IDSdata.columns = ["duration","protocol_type","service...