Machine Learning Implementations in Python

This repository contains different machine learning algorithm implementations, inspired from resources. It is using Jupyter notebooks and JupyterLab.

Usage

Install dependencies

# create lockfile
uv lock
# sync dependencies
uv sync

Start JupyterLab

uv run jupyter lab

Implemented Algorithms

• Comparison of various classification models from scikit-learn: model_comparison.ipynb
• Optimization and root finding: optimization.ipynb
  • Gradient Descent
  • Bisection Method
  • Secant Method
  • Newton's Method
• Linear Regression: linear_regression.ipynb
• K-Means: kmeans.ipynb
• K-Nearest Neighbors: knn.ipynb
• Naive Bayes: naive_bayes.ipynb
• Perceptron: perceptron.ipynb
• Backpropagation: backpropagation.ipynb
• Decision Tree: decision_tree.ipynb
• Logistic Regression: logistic_regression.ipynb
• Feedforward Neural Network: feedforward.ipynb
• Support Vector Machine: svm.ipynb

Links & Resources

• scikit-learn machine learning library for Python
• An Introduction to Statistical Learning
• The Elements of Statistical Learning
• Introduction to Computation and Programming Using Python
• Algorithms From Scratch
• Kaggle
• UCI Machine Learning Resources

Package management

We are using uv Python package and dependency manager.

• Init interactively uv init
• Add package uv add package-name
• Remove package uv remove package-name
• Create lockfile uv lock
• Update dependencies uv sync
• Show available packages uv show
• Run a command in the virtualenv uv run command