The best way to make the modules stick is to build something. These five projects take you from data analysis with pandas through an end-to-end machine learning project, deep learning with PyTorch, an LLM chatbot with LangChain, and finally a deployed MLOps pipeline.
Each one is a code-along video, so you can pause, type it out yourself and adapt it to your own datasets and ideas. Pick the project that matches the module you've just finished and come back for the rest. Together they make a solid portfolio.
Work through seven hands-on pandas projects, from filtering and sorting to cleaning the Google Play Store dataset and analyzing Premier League and NBA data.
Take a Kaggle housing dataset from loading and cleaning through visualization and linear regression, and learn how to improve and present your model.
Build and train neural networks in PyTorch, including a convolutional network for image classification, with data augmentation and GPU training.
Split text into chunks, create embeddings, store them in a vector database, and build a chatbot that answers questions about your own documents.
Bring it all together by building a sentiment model, tracking it with MLflow and DVC, containerizing it with Docker, and deploying it on AWS with CI/CD.