Do this on Pycharm:

You need to create a AI$-$model to perform the intrusion detection. The source code of decision tree$-$based AI models and the datasets $($training and testing$)$ are provided in the attachments.

$\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_$

Python code:

import numpy as np

import pandas as pd

from sklearn.tree import DecisionTreeClassifier

from sklearn.preprocessing import Normalizer

from sklearn.metrics import accuracy$\_$score

# read the training data set and the test data set.

train$\_$data $=$ pd$.$read$\_$csv$(\text{'}$kddtrain$.$csv$\text{'},$ header$=$None$)$

test$\_$data $=$ pd$.$read$\_$csv$(\text{'}$kddtest$.$csv$\text{'},$ header$=$None$)$

# Normalize the training data set

X $=$ train$\_$data.iloc$[$:$,1$:$42]$

scaler $=$ Normalizer$().$fit$($X$)$

X$\_$train $=$ scaler.transform$($X$)$

X$\_$train $=$ np$.$array$($X$\_$train$)$

y$\_$train $=$ np$.$array$($train$\_$data.iloc$[$:$,0])$

# Normal the test data set

T $=$ test$\_$data.iloc$[$:$,1$:$42]$

scaler $=$ Normalizer$().$fit$($T$)$

X$\_$test $=$ scaler.transform$($T$)$

X$\_$test $=$ np$.$array$($X$\_$test$)$ #X$\_$test

y$\_$test $=$ np$.$array$($test$\_$data.iloc$[$:$,0])$

# Create a decision tree model.

model $=$ DecisionTreeClassifier$()$

# Train the decision tree model

model.fit$($X$\_$train, y$\_$train$)$

# make predictions

y$\_$pred $=$ model.predict$($X$\_$test$)$

# Calculate the prediction accuracy

accuracy $=$ accuracy$\_$score$($y$\_$test, y$\_$pred$)$

# Print out the prediction accuracy

print$("$accuracy: $\%\mathrm{.}3$f$"\%$accuracy$)$

# print out the feature values of the $31$th sample.

print$($X$\_$test$[31,$ :$])$

print$("$The true lable $($Normal:$0$ or Intrusion:$1)$: $",$ y$\_$test$[31])$

print$("$The predicted lable $($Normal:$0$ or Intrusion:$1)$: $",$ y$\_$pred$[31])$