Machine learning question, use jupyter lab, no AI plz:

Import this:

import sys

from packaging import version

import sklearn

import matplotlib.pyplot as plt

import numpy as np

import tensorflow as tf

from sklearn.preprocessing import add$\_$dummy$\_$feature

from sklearn.datasets import make$\_$blobs

from sklearn import metrics #Import scikit$-$learn metrics module for accuracy calculation

from sklearn.model$\_$selection import train$\_$test$\_$split

from sklearn.metrics import confusion$\_$matrix, ConfusionMatrixDisplay

print$("$Sklearn package",sys$.$version$\_$info$)$

print$("$Sklearn package",sklearn.$\_\_$version$\_\_)$

print$("$TensorFlow version:", tf$.\_\_$version$\_\_)$

assert sys$.$version$\_$info $>=(3,7)$

assert version.parse$($sklearn$.\_\_$version$\_\_)>=$ version.parse$("1\mathrm{.}0\mathrm{.}1")$

plt$.$rc$(\text{'}$font$\text{'},$ size$=12)$

plt$.$rc$(\text{'}$axes$\text{'},$ labelsize$=14,$ titlesize$=14)$

plt$.$rc$(\text{'}$legend$\text{'},$ fontsize$=14)$

plt$.$rc$(\text{'}$xtick$\text{'},$ labelsize$=10)$

plt$.$rc$(\text{'}$ytick$\text{'},$ labelsize$=10)$

$----$

Questions:

$2\mathrm{.}1.$ Load and prepare the MNIST dataset. The pixel values of the images range from $0$ through $255.$ Scale these values to a range of $0$ to $1$ by dividing the values by $255\mathrm{.}0.$

$2\mathrm{.}2.$ This also converts the sample data from integers to floating$-$point numbers:

tf$.$random.set$\_$seed$(1)$

mnist $=$ tf$.$keras.datasets.mnist

$($x$\_$train, y$\_$train$),($x$\_$test, y$\_$test$)=$ mnist.load$\_$data$()$

print$($x$\_$train.shape,y$\_$train.shape,x$\_$test.shape,y$\_$test.shape$)$

x$\_$train, x$\_$test $=$ x$\_$train $/255\mathrm{.}0,$ x$\_$test $/255\mathrm{.}0$

$3.$ Q$1$

$3\mathrm{.}1.$ Using the keras Sequential Model:

$3\mathrm{.}1\mathrm{.}1.$ Construct a neural network classification model that has two layers, input layer, and an output later.

$3\mathrm{.}1\mathrm{.}2.$ The first hidden layer has $128$ neurons and the second hidden layer has $64$ neuron.

$3\mathrm{.}1\mathrm{.}3.$ The output layer has $10$ output units since we have $10$ classes.

$3\mathrm{.}1\mathrm{.}4.$ Both the hidden layers use the 'relu' activation function.

$3\mathrm{.}1\mathrm{.}5.$ Using a learning rate of $0\mathrm{.}001,$ epochs$=10,$ batch$\_$size$=64$ and 'adam' as the optimization algorithm

$3\mathrm{.}1\mathrm{.}6.$ Print the accuracy of the model on the testing dataset, x$\_$test

$3\mathrm{.}1\mathrm{.}7.$ Accuracy will be around $97\%$

#Write your code here..

#Do NOT CHANGE THIS CODE

#Testing some images

predictions $=$ model$($x$\_$test$[$:$5]).$numpy$()$

y$\_$pred $=$ np$.$argmax$($predictions$,$axis$=1)$

print$("$Predicted Class Labels for some testing records"$)$

print$($y$\_$pred$)$

print$("$True Class Labels for some testing records"$)$

print$($y$\_$test$[$:$5])$