Jupyter notebooks with example code and exercises from the first edition of Hands-on Machine Learning with Scikit-Learn and TensorFlow.
Hands-on Machine Learning is a collection of Jupyter notebooks containing all example code and exercise solutions from the first edition of the book *Hands-on Machine Learning with Scikit-Learn and TensorFlow*. It provides a practical, interactive resource for learning machine learning fundamentals through implementation. The project covers topics from data preprocessing to neural networks with TensorFlow.
Beginners and intermediate learners who want to learn machine learning through practical coding exercises using Python, Scikit-Learn, and TensorFlow. Ideal for students, data scientists, and developers following the book.
Provides the complete hands-on companion to a popular machine learning book with executable code and verified solutions. Offers multiple deployment options including cloud notebooks and Docker for easy setup and reproducibility.
⛔️ DEPRECATED – See https://github.com/ageron/handson-ml3 or handson-mlp instead.
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
Includes every coding example from the book in executable Jupyter notebooks, ensuring learners can replicate all exercises precisely.
Provides solutions to all end-of-chapter exercises, as noted in the README, enabling hands-on practice and self-assessment.
Offers one-click runs on Colaboratory, Binder, or Deepnote without local installation, detailed in the quick start section.
Includes Docker and Anaconda instructions for consistent local deployment, reducing environment conflicts.
Based on the 2017 first edition, it uses TensorFlow 1.x and older Scikit-Learn versions, which are deprecated and lack modern features.
Limited to the book's original scope, missing newer techniques and content from the third edition or industry advancements.
Requires managing Conda environments, GPU drivers, and specific Python versions, which can be error-prone despite detailed guides.