How mohitpunglia/machine_learning_algorithms works
Project type and purpose
• This is an educational, open-source Python library of machine learning algorithms implemented from scratch, organized as a collection of Jupyter Notebooks and supporting data files.
• Its goal is to help learners step through core ML algorithms (regression, classification, clustering, dimensionality reduction) with clean, modular code and visual explanations.
File structure
• Top-level folders each correspond to an algorithm or algorithm family (e.g., “Decision Tree”, “KNN”, “Gradient Boosting”, “Clustering”, etc.).
• Inside each folder: one or more .ipynb notebooks implementing the algorithm, plus any CSV datasets used for demos.
• A few special files/directories:
• streamlit-decision-tree/ (an interactive Streamlit app for decision trees)
• README.md describing overall purpose, features, and installation.
README for additional insights
• Emphasizes clean modular code, Jupyter notebooks for step-by-step execution, included datasets, and mathematical derivations.
• No heavy external “service” or microservice architecture—main dependencies are Python libraries (NumPy, pandas, matplotlib, etc.) and Jupyter.