Car-Price-Predictions

Car-Price-Predictions

Table of Content

• Demo
• Overview
• Technical Aspect
• Installation
• Run
• Deployment on Heroku
• Directory Tree
• To Do
• Technologies Used
• Team
• Credits
• References

Demo

Link:- https://carpricepredictioner.herokuapp.com/

Overview

This is a simple car price predictor Flask app. It shows the selling price of your car by putting the values/features like year in which the car was bought, ex-showroom price of the car, the distance completed by the car in km, the number of owners the car has previously had, Fuel type of the car, whether the seller is a dealer or an individual, and whether the car is manual or automatic. By using this data it will predict the cars selling price. All the data contain in a .csv file.

Technical Aspect

This project is divided into two parts:-

1. Build model using python.
2. Design an app using Flask framework.
3. Host a Flask app on Heroku cloud.

• A user can fill all the fields that are given.
• Click on Calculate the Selling Price button. It will show the selling price below that Calculate the Selling Price button.
• Used Vehicle dataset from cardekho Kaggle.
• Used Heroku platform to make this app public.

Installation

The code is written in Python 3.6. If you don't have Python installed you can find it here .To install the required packages and libraries, run this command in the project directory after clonning the repository. pip install -r requirements.txt

Run

Step1.

To run this on local machine, click on run button in flask_app.py file.

Step2.

Copy the link for e.g. http://127.0.0.1:5000/ and past it on your browser and hit enter.

Deployement on Heroku

Step1.

Maintain necessary files like requirements.txt, Procfile . Givent in the project directory check there.

Step2.

This step would be to follow the instructions given on Heroku Documnetation to deploy a web app.

Directory Tree

|--static/css
| |--css
| | |--all.css
| | |--all.min.css
| |--webfonts
| | |--fa-brands-400.lot
| | |--fa-brands-400.svg
| |--main.css
|--templates
| |--index.html
|--app.py
|--car data.csv
|--Car data_model.ipynp
|--Procfile
|--README.md
|--requirements.txt
|--rf_model.pkl

To Do

1. Improve the model accuracy by increase the data size and apply some advance machine learning techniques.
2. Add better UI and animations.

Technologies Used

Team

Rohit Sharma

Credits

All the creadits of this project goes to Krish Niak. ❤️

References

• Dataset