AI & ML · Ebook

Scikit-Learn: Practical Machine Learning in Python

by Shriira Press

A comprehensive, self-contained guide to scikit-learn, the library that, more than any other, is how machine learning actually gets done in Python. Where the companion Machine Learning book teaches why the algorithms work — the mathematics of linear regression, SVMs, trees, and the rest — this book teaches how to wield them: the unified estimator API, the preprocessing and pipeline patterns that prevent subtle bugs, rigorous model selection and evaluation, and the end-to-end workflow that turns a dataset into a trustworthy, deployable model. It blends intuition, the concepts behind the API, and runnable code you can adapt immediately.

Contents

1. 1Preface
2. 2Chapter 1 — What Is Scikit-Learn?
3. 3Chapter 2 — The Estimator API and Core Design
4. 4Chapter 3 — Data, Datasets, and the Train/Test Split
5. 5Chapter 4 — Regression
6. 6Chapter 5 — Classification
7. 7Chapter 6 — Trees, Forests, and Gradient Boosting
8. 8Chapter 7 — Support Vector Machines and Other Models
9. 9Chapter 8 — Preprocessing and Feature Engineering
10. 10Chapter 9 — Pipelines and Composite Estimators
11. 11Chapter 10 — Model Selection and Hyperparameter Tuning
12. 12Chapter 11 — Evaluation Metrics and Model Diagnosis
13. 13Chapter 12 — Unsupervised Learning: Clustering and Dimensionality Reduction
14. 14Chapter 13 — End-to-End, Production, and the Ecosystem
15. 15Appendix A — Glossary and API Quick Reference
16. 16Appendix B — Further Reading and Resources