Scikit-learn

Master scikit-learn: the estimator API, pipelines and ColumnTransformer, model selection with cross-validation and hyper-parameter search, ensembles and boosting, feature engineering and selection, imbalanced data, interpretation, persistence, reproducibility and a full-pipeline project.

What you will learn

• Use the estimator API consistently: fit, predict, predict_proba, transform, score, get/set_params
• Build leak-free pipelines with ColumnTransformer for mixed numeric and categorical data
• Select models with cross-validation, grid and randomised search and nested evaluation
• Apply ensembles (random forests, gradient boosting) and compare them fairly
• Engineer and select features, handle class imbalance and calibrate thresholds
• Interpret models, persist them safely and make experiments reproducible

Who it is for: learners who know ML concepts and want production-quality workflows in scikit-learn

Prerequisites: CRS-GEN-ML-FUNDAMENTALS; pandas basics