Gradient_descent

Different gradient descent algorithms written from scratch in Python.
Explore the docs »

View Demo · Report Bug · Request Feature

Table of Contents

1. About The Project
   • Built With
2. Getting Started
   • Prerequisites
   • Installation
3. Usage
4. Roadmap
5. Contributing
6. License
7. Contact
8. Acknowledgments

About The Project

Gradient Descent is a streamlit project that will create and train a logistic regression model in Python using the MNIST dataset (no PyTorch). To properly train the logistic regression model on the Training Set, stochastic gradient descent must be used. On the Test Set, its accuracy should be between 90 and 93%..

(back to top)

Getting Started

To get a local copy up and running follow these simple example steps.

Prerequisites

This is an example of how to list things you need to use the package and how to install them.

Installation

1. Clone the repo

   git clone https://github.com/tuhinmallick/gradient_descent.git

2. Go to the project directory

   cd gradient_descent

3. Install environment or dependecies

   conda env create -n ENVNAME --file docs/environment.yml

   or

   pip install -r requirements.txt

4. Run the file

    setup.sh

5. Run the streamlit app

   streamlit run app/dashboard.py

(back to top)

Usage

For more examples, please refer to the Notebook

(back to top)

Roadmap

• Granger casaulty test
• AD Fuller test
• Feature 3
  • Nested Feature

See the open issues for a full list of proposed features (and known issues).

(back to top)

Contributing

Contributions are what make the open source community such an amazing place to learn, inspire, and create. Any contributions you make are greatly appreciated.

If you have a suggestion that would make this better, please fork the repo and create a pull request. You can also simply open an issue with the tag "enhancement". Don't forget to give the project a star! Thanks again!

1. Fork the Project
2. Create your Feature Branch (git checkout -b feature/AmazingFeature)
3. Commit your Changes (git commit -m 'Add some AmazingFeature')
4. Push to the Branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

(back to top)

🛡 License

This project is licensed under the terms of the MIT license. See LICENSE for more details.

(back to top)

Authors

• @tuhinmallick

Contact

Your Name - @tuhinmallick - tuhin.mllk@gmail.com

Project Link: https://github.com/tuhinmallick/gradient_descent

(back to top)

Acknowledgments

• ilyaryabov

(back to top)