scikit-learn

The classic toolkit for tabular machine learning.

scikit-learn is taught here in 12 lessons, running from Estimators and fit/predict through to Persistence, inspection and reproducibility. Each lesson takes one topic, shows the working code, and links onward to the next, so the course can be read straight through in order.

Lessons

1. Estimators and fit/predictThe uniform API behind every scikit-learn model: fit, predict, transform, and the data shapes the library silently expects.
2. Pipelines and preprocessingCompose preprocessing and a model into one object, keep the test set clean, and handle numeric and categorical columns in a single ColumnTransformer.
3. Model selection and metricsNested cross-validation, grid and randomised search, and picking a metric that reflects the cost of being wrong rather than the one that flatters the model.
4. Splitting data and cross-validation strategiestrain_test_split in detail, KFold, StratifiedKFold, GroupKFold, TimeSeriesSplit, and repeated evaluation that reports a spread instead of one lucky number.
5. Linear modelsLinear and logistic regression, Ridge, Lasso, ElasticNet, how regularisation strength behaves, and how to read coefficients without being misled.
6. Tree-based modelsDecision trees and their pruning knobs, random forests, HistGradientBoostingClassifier, and why impurity-based feature importances mislead.
7. Support vector machines and kernelsSVC and SVR, the kernel trick, tuning C and gamma, why scaling is mandatory, and when an SVM is the right call at all.
8. Clustering and manifold learningKMeans and MiniBatchKMeans, DBSCAN and AgglomerativeClustering, silhouette scores, PCA for compression and t-SNE for exploration.
9. Feature engineering and text featuresOneHotEncoder, OrdinalEncoder, KBinsDiscretizer, PolynomialFeatures, and turning raw text into a matrix with CountVectorizer and TfidfVectorizer.
10. Missing data and outliersSimpleImputer and KNNImputer inside a pipeline, indicator features for missingness, and robust scalers that stop outliers from dominating the fit.
11. Imbalanced classificationclass_weight and threshold tuning, resampling with imbalanced-learn inside a pipeline, and measuring success with precision-recall rather than accuracy.
12. Persistence, inspection and reproducibilityjoblib versus pickle trade-offs, pinning library versions, set_config and random_state discipline, and inspecting what a fitted pipeline actually learned.

More in AI & Intelligent Development

AI Basics AI Agents Math for AI Machine Learning TensorFlow PyTorch Natural Language Processing LangChain Ollama OpenCV Codex Claude Code OpenCode Vibe Coding Selenium Playwright

FAQ

Last refreshed 2026-09-18.