https://github.com/lakshmankishore/loanprediction

An end to end ML project.
https://github.com/lakshmankishore/loanprediction

bootstrap github-pages html-css logistic-regression machine-learning pyscript python uigradients

Last synced: 17 days ago
JSON representation

An end to end ML project.

• Host: GitHub
• URL: https://github.com/lakshmankishore/loanprediction
• Owner: LakshmanKishore
• Created: 2021-09-17T09:27:42.000Z (over 3 years ago)
• Default Branch: main
• Last Pushed: 2023-11-27T16:02:25.000Z (about 1 year ago)
• Last Synced: 2024-10-24T16:54:51.395Z (2 months ago)
• Topics: bootstrap, github-pages, html-css, logistic-regression, machine-learning, pyscript, python, uigradients
• Language: Jupyter Notebook
• Homepage:
• Size: 273 KB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        

# Loan Prediction

End to End ML project with free deployment.

This project demonstrates how to build a loan prediction application using the PyScript framework. The application utilizes a machine learning model to predict whether a loan applicant will be approved or rejected.

## Background

The original version of this project was built using the Flask framework and was deployed on Heroku. However, due to the discontinuation of the Heroku free tier, the application needed to be migrated.

## Solution

To address this challenge, the project was reimplemented using the PyScript framework. PyScript is a lightweight and versatile framework that allows you to create web applications directly in Python. This approach eliminates the need for a separate web server, making the application easier to deploy and maintain.

## Acknowledgments

This project draws inspiration from the tutorials and guidance provided by Krish Naik. His videos on Flask framework and ML model deployment were instrumental in developing the initial version of this project.

## Disclaimer

This application is for demonstration purposes only and should not be used to make actual loan decisions. The model's predictions are based on historical data and may not always be accurate.

Found dataset from [here](https://www.kaggle.com/altruistdelhite04/loan-prediction-problem-dataset)

## Tech Stack

**Client:** HTML5, CSS, Bootstrap, JavaScript, py-script

  

## Lessons Learned

I successfully linked the machine learning model to the web using the PyScript framework. Key takeaways include:

Learnt more about:

* Logistic Regression.

* Exploratory Data Analysis.

* Feature Engineering.

* How to use py-script framework.

## Related

Here are some related projects

* [Color Name Prediction](https://github.com/LakshmanKishore/colorNamePrediction)

* [Iris Classification](https://github.com/LakshmanKishore/irisClassification)

# You can watch the code live [here](https://lakshmankishore.github.io/loanPrediction)