Module 6: Machine Learning

6. Module 6: Machine Learning#

6.1. Objectives#

Introduce classical machine learning using scikit-learn, including supervised and unsupervised learning.

6.2. Learning Outcomes#

By the end of this module, participants will be able to:

  • Understand machine learning workflows.

  • Train and evaluate models like logistic regression, decision trees, and SVMs.

  • Preprocess data and perform feature engineering.

  • Evaluate models using accuracy, F1-score, etc.

  • Avoid common pitfalls like overfitting and leakage.

6.3. Topics#

  • ML concepts, workflows

  • Supervised vs unsupervised learning

  • Preprocessing and feature engineering

  • Models: logistic regression, decision trees, random forests, SVMs

  • Unsupervised models: clustering, PCA

  • Evaluation: confusion matrix, ROC, cross-validation

  • Hyperparameter tuning with grid search

  • Use cases: TBD

Contents