This is an introductory book in machine learning with a hands on approach. It uses Python 3 and Jupyter notebooks for all applications. The emphasis is primarily on learning to use existing libraries such as Scikit-Learn with easy recipes and existing data files that can found on-line. Topics include linear, multilinear, polynomial, stepwise, lasso, ridge, and logistic regression; ROC curves and measures of binary classification; nonlinear regression (including an introduction to gradient descent); classification and regression trees; random forests; neural networks; probabilistic methods (KNN, naive Bayes', QDA, LDA); dimensionality reduction with PCA; support vector machines; and clustering with K-Means, hierarchical, and DBScan. Appendices provide a review of probability and linear algebra. While some mathematical foundation is provided, it is not essential for understanding the implementations. The target audience is advanced community college and university students.
Features
- Jupyter notebooks
- sklearn based implementation
- recipe based implementation