Progress Checklist¶
Tick off each chapter after you've done its exercises, and each capstone once you can complete it without notes.
These checkboxes don't save
The boxes are visual only on the website and reset when you reload. To track your progress, copy this page into your own notes or repository and tick the boxes there.
🌱 Beginner tier: Data Science Foundations¶
Level 0: Python for data¶
- The data landscape
- Setting up your environment
- Python essentials for data work
- NumPy
- pandas
- Data visualization
- Capstone: Analyze a real dataset end to end in a notebook
Level 1: Math foundations¶
- Linear algebra
- Matrix decompositions
- Calculus and gradients
- Probability
- Statistics
- Information theory and optimization
- Capstone: Linear regression three ways, from scratch: normal equations, gradient descent, and statistical inference
Level 2: The data science workflow¶
- SQL and data acquisition
- Data cleaning
- Exploratory data analysis
- Feature engineering
- Experimentation and A/B testing
- Communicating results
-
Capstone: A full data science investigation: SQL, cleaning, EDA, an A/B test, and a written report
-
Tier checkpoint passed (see the tier page)
🔧 Intermediate tier: Machine Learning¶
Level 3: Machine learning fundamentals¶
- What is machine learning?
- Linear regression
- Logistic regression and classification
- Generalization and the bias-variance trade-off
- Regularization
- Evaluation metrics
- Gradient descent in depth
- Capstone: Build a churn classifier from scratch in NumPy, then match it with scikit-learn
Level 4: ML algorithms in depth¶
- k-nearest neighbors and naive Bayes
- Decision trees
- Ensembles: random forests and boosting
- Support vector machines
- Clustering
- Dimensionality reduction
- Time series forecasting
- Anomaly detection and recommender systems
- Capstone: A model bake-off on a tabular dataset, with rigorous validation and a written recommendation
Level 5: Applied ML and MLOps¶
- ML pipelines
- Hyperparameter tuning
- Imbalanced data
- Interpretability
- ML in production
- Responsible ML
-
Capstone: Ship a production-ready model service: pipeline, tuning, tracking, an API, Docker, and monitoring
-
Tier checkpoint passed (see the tier page)
🚀 Expert tier: Deep Learning¶
Level 6: Neural networks from scratch¶
- From neurons to networks
- Forward and backpropagation
- A neural network in NumPy
- Optimizers
- Training deep networks
- Autograd from scratch
- Capstone: Build a tiny deep learning library with autograd, and train it to over 95% accuracy on digits
Level 7: Deep learning with PyTorch¶
- PyTorch fundamentals
- The training loop
- Convolutional neural networks
- Sequence models
- Embeddings and NLP basics
- Transfer learning
- Capstone: Train an image classifier above 90% accuracy, with augmentation, tracking, and an error analysis