There are $2$ files main.py and us$.$py it is streamlit app that is used for predicting car price. I want you to style the app like put some car photos when a car brand selected for example Audi, Citroen,$($DO IT FOR ALL CR BRANDS AND THEIR CORRESPONDING MODEL AS YOU CAN SEE IN THE CAR BRAND AND MODEL MAPS$)$ make some front end work maybe change background play with some front end styling style the streamlit app with best versionmake home page then convert current home to another page as prediction page do your maximum please.

import pandas as pd

import numpy as np

import streamlit as st

import folium

from folium import plugins

from sklearn.ensemble import RandomForestRegressor

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

from us import about$\_$us # Assuming this is the correct import for your about us module

# Read the normalized dataframe

df$\_$normalized $=$ pd$.$read$\_$csv$(\text{'}$C:$\backslash \backslash$Users$\backslash \backslash$seyfu$\backslash \backslash$sale$\_$prediction$2.$csv$\text{'})$

# Read the original dataframe

df$\_$original $=$ pd$.$read$\_$csv$(\text{'}$C:$\backslash \backslash$Users$\backslash \backslash$seyfu$\backslash \backslash$final$\_$data$3.$csv$\text{'})$

# Map color names to numeric codes

color$\_$map $=\{$

'Alt$$n$\text{'}$: $0,$

'Bej': $1,$

'Beyaz': $2,$

'Bordo': $3,$

$\text{'}$Di$$er$\text{'}$: $4,$

$\text{'}$F$$me$\text{'}$: $5,$

'Gri': $6,$

'Gri $($G$$m$)\text{'}$: $7,$

'Gri $($metalik$)\text{'}$: $8,$

'Gri $($titanyum$)\text{'}$: $9,$

'Kahverengi': $10,$

$\text{'}$K$$rm$$z$\text{'}$: $11,$

'Lacivert': $12,$

'Mavi': $13,$

'Mavi $($metalik$)\text{'}$: $14,$

'Mor': $15,$

'Pembe': $16,$

'Sar$\text{'}$: $17,$

'Siyah': $18,$

'Turkuaz': $19,$

'Turuncu': $20,$

$\text{'}$Ye$$il$\text{'}$: $21,$

$\text{'}$Ye$$il $($metalik$)\text{'}$: $22,$

$\text{'}$ampanya$\text{'}$: $23$

$\}$

# Map brand names to numeric codes

brand$\_$map $=\{$

'Audi': $0,$

'Citroen': $1,$

'Fiat': $2,$

'Ford': $3,$

'Opel': $4,$

'Renault': $5,$

'Toyota': $6,$

'Volkswagen': $7$

$\}$

# Map model names to numeric codes

model$\_$map $=\{$

$\text{'}100\text{'}$: $0,$

$\text{'}80\text{'}$: $1,$

$\text{'}$A$1\text{'}$: $2,$

$\text{'}$A$3\text{'}$: $3,$

$\text{'}$A$4\text{'}$: $4,$

$\text{'}$A$5\text{'}$: $5,$

$\text{'}$A$6\text{'}$: $6,$

$\text{'}$A$7\text{'}$: $7,$

$\text{'}$A$8\text{'}$: $8,$

'Astra': $9,$

$\text{'}$BX$\text{'}$: $10,$

$\text{'}$C$-$Elysee': $11,$

$\text{'}$C$1\text{'}$: $12,$

$\text{'}$C$2\text{'}$: $13,$

$\text{'}$C$3\text{'}$: $14,$

$\text{'}$C$4\text{'}$: $15,$

$\text{'}$C$5\text{'}$: $16,$

$\text{'}$C$6\text{'}$: $17,$

$\text{'}$C$8\text{'}$: $18,$

'Clio': $19,$

'Corolla': $20,$

'Corsa': $21,$

'Egea': $22,$

'Evasion': $23,$

'Fiesta': $24,$

'Fluence': $25,$

'Focus': $26,$

'Golf': $27,$

'Linea': $28,$

'Polo': $29,$

$\text{'}$S$\text{'}$: $30,$

'Saxo': $31,$

$\text{'}$TT$\text{'}$: $32,$

'Xantia': $33,$

'Xsara': $34,$

$\text{'}$ZX$\text{'}$: $35$

$\}$

# Replace color, brand, and model numeric codes in the normalized dataframe

df$\_$normalized$[\text{'}$Color$\text{'}]=$ df$\_$original$[\text{'}$Color$\text{'}].$map$($color$\_$map$)$

df$\_$normalized$[\text{'}$Car Brand'$]=$ df$\_$original$[\text{'}$Car Brand'$].$map$($brand$\_$map$)$

df$\_$normalized$[\text{'}$Model$\text{'}]=$ df$\_$original$[\text{'}$Model$\text{'}].$map$($model$\_$map$)$

# Ensure that all features are properly encoded

X $=$ df$\_$normalized.drop$([\text{'}$Price$\text{'},$ 'City', 'District'$],$ axis$=1)$

y $=$ df$\_$normalized$[\text{'}$Price$\text{'}]$

# Split the dataset into training and testing sets

X$\_$train, X$\_$test, y$\_$train, y$\_$test $=$ train$\_$test$\_$split$($X$,$ y$,$ test$\_$size$=0\mathrm{.}2,$ random$\_$state$=100)$

# Train a RandomForestRegressor model

rf $=$ RandomForestRegressor$()$

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

# Streamlit app navigation

navigation $=$ st$.$sidebar.radio$("$Navigation$",["$Home$",$ "About Us$"])$

if navigation $==$ "Home":

st$.$sidebar.header$(\text{'}$User Input Parameters'$)$

# Add sliders, text inputs, or any other widgets for user input

year $=$ st$.$sidebar.slider$(\text{'}$Select Car Year', min$\_$value$=$X$[\text{'}$Year$\text{'}].$min$(),$ max$\_$value$=$X$[\text{'}$Year$\text{'}].$max$(),$

value$=$int$($X$[\text{'}$Year$\text{'}].$mean$()))$

kilometers $=$ st$.$sidebar.number$\_$input$(\text{'}$Select Car Kilometers', min$\_$value$=$X$[\text{'}$Kilometers$\text{'}].$min$(),$

max$\_$value$=$X$[\text{'}$Kilometers$\text{'}].$max$(),$ value$=$int$($X$[\text{'}$Kilometers$\text{'}].$mean$()))$

engine $=$ st$.$sidebar.slider$(\text{'}$Select Engine Size', min$\_$value$=$X$[\text{'}$Engine$\text{'}].$min$(),$ max$\_$value$=$X$[\text{'}$Engine$\text{'}].$max$(),$

value$=$X$[\text{'}$Engine$\text{'}].$mean$())$

color $=$ st$.$sidebar.selectbox$(\text{'}$Select Car Color', list$($color$\_$map.keys$()))$

brand $=$ st$.$sidebar.selectbox$(\text{'}$Select Car Brand', list$($brand$\_$map.keys$()))$

model $=$ st$.$sidebar.selectbox$(\text{'}$Select Car Model', list$($model$\_$map.keys$()))$

# Define a predict button

predict$\_$button $=$ st$.$sidebar.button$(\text{'}$Predict$\text{'})$

if predict$\_$button:

# Retrieve the numeric code for the selected color, brand, and model

color$\_$numeric $=$ color$\_$map$[$color$]$

brand$\_$numeric $=$ brand$\_$map$[$brand$]$

model$\_$numeric $=$ model$\_$map$[$model$]$

# Perform prediction

user$\_$input $=[[$year$,$ kilometers, engine, color$\_$numeric, brand$\_$numeric, model$\_$numeric$]]$

prediction $=$ rf$.$predict$($user$\_$input$)$

# Display prediction result

st$.$write$(\text{'}$## Car Price Prediction'$)$

st$.$write$($f$\text{'}$The predicted price for the selected car is: TRY $\{$prediction$[0]$:$\mathrm{.}2$f$\}\text{'})$

elif navigation $==$ "About Us$"$:

about$\_$us$()$ # Call the about$\_$us function from the about$\_$us module