SkillData ScientistData EngineerAI/ML EngineerForward Deployed Engineer
Library · concept
Machine learning
Train, evaluate and ship predictive models that are honest about how well they work. Named in 84% of Data Scientist and every AI/ML Engineer job description we read.
This shelf teaches classical machine learning with scikit-learn: the workflow, the evaluation and the traps. Deep learning and language models have their own shelves and build on this one.
Examples use the Palmer Penguins (CC0) and UCI Bank Marketing (CC BY 4.0) datasets and run on a laptop in seconds.
Advanced lessons for Machine learning are being written.
- 1BeginnerCredit card default risk baseline
- 2BeginnerRoute banking questions to 77 intents
- 3BeginnerSMS spam classifier with an honest baseline
- 4IntermediateLand cover from satellite images with transfer learning
- 5IntermediatePredict purchases from browsing sessions
- 6IntermediateTerm deposit propensity model for a call centre
- 7AdvancedFine-tuning versus prompting, decided with numbers
- 8AdvancedHourly bike demand forecasting with backtesting
- 9AdvancedShip a model and catch it failing