Machine Learning in Python with scikit-learn by France Université Numérique
This course is an in-depth introduction to predictive modeling with scikit-learn. Step-by-step and didactic lessons introduce the fundamental methodological and software tools of machine learning, and is as such a stepping stone to more advanced challenges in artificial intelligence, text mining, or data science. The course official page
- Module 1. The predictive modeling pipeline [lectures | solutions]
- Tabular data exploration
- Fitting scikit-learn model on numerical data
- Handling categorical data
- Module 2. Selecting the best model [lectures | solutions]
- Overfitting and underfitting
- Validation and learning curves
- Bias versus variance trade-off
- Module 3. Hyperparameters tuning [lectures | solutions]
- Manual tuning
- Automated tuning
- Module 4. Linear models [lectures | solutions]
- Intuitions on linear models
- Linear regressions
- Modelling with a non-linear relationship data-target
- Regularization in linear model
- Linear model for classification
- Module 5. Decision tree models [lectures | solutions]
- Intuitions on tree-based models
- Decision tree in classification
- Decision tree in regression
- Hyperparameters of decision tree
- Module 6. Ensemble of models [lectures | solutions]
- Ensemble method using bootstrapping
- Ensemble based on boosting
- Hyperparameters tuning with ensemble methods
- Module 7. Evaluating model performance [lectures | solutions]
- Comparing a model with simple baselines
- Choice of cross-validation
- Nested cross-validation
- Classification metrics
- Regression metrics
The repository includes both notebooks from lectures and notebooks with my solutions to the given exercises and tests.