The best way to make the modules stick is to build something. These five projects take you from exploratory data analysis through classification and regression models, then into NLP with sentiment analysis, and finally an end-to-end MLOps pipeline.
Each one is a code-along video, so you can pause, type it out yourself and adapt it to your own datasets. Pick the project that matches the module you've just finished and come back for the rest.
Work through a complete exploratory data analysis in a Jupyter Notebook with Pandas, a hands-on drill for the wrangling and visualization modules.
Build a classification model in Python that predicts which Titanic passengers survived, a classic first machine learning project.
Go through the full data science process on a housing dataset, from exploring the data to training a model that predicts prices.
Classify Amazon reviews as positive or negative with NLTK's VADER and a pretrained Hugging Face model, a practical introduction to NLP.
Take a model from data collection to production with MLflow, DVC, Flask, Docker, and CI/CD, then connect it to a Chrome extension.