Load and pre-process NSL KDD data set

Question

since I am a newbie in python programming and I want to load the data according to the table of the article but I don’t know how to can do categorical training and testing the NSL_KDD dataset into(‘normal’, ‘dos’, ‘r2l’, ‘probe’, ‘u2r’).

I’ve reviewed a lot of code in GateHub to pre-process the NSL_KDD data set to categorize into five groups(‘normal’, ‘dos’, ‘r2l’, ‘probe’, ‘u2r’), but I still haven’t been able to find the code to do it right.
Can anyone help me? I really need help.

Comments

Hi, @Areezo,

 I would suggest you use Google Colab, try to run it. Install spark on ubuntu: