Machine-Learning-Algorithms-From-Scratch

This repository gathers the essential Machine Learning algorithms coded from scratch using only:

• Numpy: for algebraic, and statistical operations
• Sklearn: for generating testing data

Getting Started:

• Start by setting up a python virtual environment by running:

   python -m virtual_env_name /path/to/new/virtual/environment

• Activate the virtual environment:

   .\virtual_env_name\Scripts\activate

• Install the required libraries:

   pip install -r requirements.txt

• All the folders contain at least two files:
  • model_name.py: contains the class that implements a specific ML model or technique.
  • main.py: contains the testing script, it usually has an accuracy check or a plotting of the result. To test the implementation, you can drag and drop the main file to the main directory \
  
  

then, you can run:

   python main.py

Resources:

• The tutorial that engaged me in creating this repository is this one, it helps to understand the coding phase of the algorithms, and it contains pretty usefull testing scripts that I have used.
• Although the previous tutorial was mostly enriching, in the theoretical part, I have taken advantage of insightful blogs written in Towards DataScience, Ask Python, and Wikipedia. I have included all the blogs that I have read to write the code implementation in its corresponding file.
• For people who like to visualize things, I recommend the following youtube channels: StatQuest, Visually Explained, and Intuitive Machine Learning.

Happy Learning!