Machine Learning Algorithms from Scratch

Project Overview

This project focuses on implementing various Machine Learning algorithms from scratch without using pre-built ML libraries. The goal is to understand the inner workings of algorithms like linear regression, decision trees, and more by building them step-by-step in Python. This project was developed as part of a university course.

Technologies Used

• Python
• Jupyter Notebook
• Pandas
• NumPy
• Matplotlib

Installation Instructions

1. Clone the repository or download the Jupyter Notebooks.
2. Ensure you have Python installed (preferably Python 3.x).
3. Install the required libraries:

   pip install pandas numpy matplotlib

4. Open the Jupyter Notebooks in your preferred environment (e.g., Jupyter Lab, Jupyter Notebook, or any IDE that supports Jupyter).

Features

• Build ML algorithms from scratch: Understand and implement key algorithms such as:
  • Clustering (e.g., K-Means)
  • Decision Trees
  • Linear Regression
  • MAP Classifiers (Maximum A Posteriori)
• Step-by-step development: Each algorithm is built and explained incrementally in the Jupyter Notebooks.
• No pre-built ML libraries: Algorithms are implemented without using machine learning libraries like Scikit-learn, focusing on foundational concepts.

Usage

• Open each Jupyter notebook to explore and run the algorithms.
• Follow the explanations within each notebook to understand how each algorithm is constructed and applied.

Contributing

Contributions are welcome! If you’d like to contribute:

1. Fork the repository.
2. Create a new branch for your feature or fix.
3. Submit a pull request with a clear description of your changes.

License

This project does not currently have a specified license. Feel free to fork and use it as you wish.

Screenshots/Demo

Each Jupyter notebook contains detailed explanations, code implementations, and outputs for each algorithm. Check inside the notebooks for examples and results.