Course 6 : Time Series Forecasting
Lecture 6 : Lecture6a.pdf, Lecture6b.pdf
Notebook of Lecture 6 : Lecture6a.ipynb, Lecture6b.ipynb, Lecture6c.ipynb
Datasets : internet-traffic.csv, quebec.csv, calendar.csv, sales_train_evaluation.csv, sell_prices.csv
Lab 6 : Lab6.pdf.
Dataset : PJME_hourly.csv
Course 5 : More about uncertainty management
Lecture 5 : Lecture5.pdf
Notebook of Lecture 5 : Lecture5a.ipynb, Lecture5b.ipynb
Dataset : diamonds.csv
An example with synthetic data
Refresher on quantile : website of Piketty
Split Conformal Prediction for regression
Split Conformal Prediction for classification
Material in French of R. Vaucher (ERIC-Lyon 2)
Lab 5 : Lab5.pdf
Dataset : dataset.csv
Course 4 : A flavour of eXplainaible AI (XAI)
Permutation Feature Importance : PFI.ipynb. Dataset : credit_score.csv
Partial Dependence Profile :here, PDP.ipynb. Dataset : adult.csv
Tutorial on LIME : TutorialLIME.ipynb. Dataset : BostonHousing.csv
Tutorial on SHAP : TutorialSHAP.ipynb. Dataset : telco_data.csv
More on XGBoost : this website or this one
More on LightGBM : this website
Course 3 : Decision Trees and Ensemble methods
Lecture 3: Lecture 3a.pdf, Lecture3b.pdf and Lecture3c.pdf.
Notebooks of Lecture 3a : Lecture3a.ipynb, Lecture3b.ipynb.
Datasets : PimaDiabets.csv
Lab 3 : Lab3.pdf. Datasets : rent.csv, hostel_factors.csv
Additional websites on Decision Trees : visualization and basics on decision trees
Additional website on Random Forest : Importance Measures with RF
More on tabular data
Foundation models for tabular data
McElfresh, Duncan, et al. When do neural nets outperform boosted trees on tabular data?. Advances in Neural Information Processing Systems 36 (2024). pdf
Kim, Myung Jun, Léo Grinsztajn, and Gaël Varoquaux. CARTE: pretraining and transfer for tabular learning. arXiv preprint arXiv:2402.16785 (2024). pdf
Course 2 : Beyond OLS
Lecture 2 : Lecture2.pdf
Notebook of Lecture 2 : Lecture2.ipynb
Practical Session 2 : PracticalSession2.pdf
Datasets : diabetes.csv, Hitters.csv
Course 1 : Basics on supervised learning and optimisation
Lecture 1a : Lecture1a.pdf
Lecture 1b : Lecture1b.pdf
Lecture 1c : Lecture1c.pdf
Practical Session 1 : PracticalSession1.pdf