Welcome to Applied Predictive Modeling

This project aims to distill the content and examples in Applied Predictive Modeling [KJ13], which focuses on the R programming language, using Python and/or Rust instead. It’s meant to help readers of the book follow along using executable Jupyter Notebooks with a Python kernel, while digging into low-level optimizations in Rust when appropriate. You can leverage this project as a Python module w/ Rust crate, a series of executable Jupyter Notebooks, and/or a website or PDF document to follow along.

The applied_predictive_modeling Python module and Rust crate encapsulate and structure code required to perform examples from the book in a manner that allows readers to focus on learning the statistical model concepts. Care in producing clean, well-tested code will be taken, which hopefully provide the reader with best-practices they can take with them when writing their own. Books such as Clean Code{cite}``

APM Book

• 1. Chapter 1
  • 1.1. Introduction
• 2. Chapter 2
  • 2.1. A Short Tour of the Predictive Modeling Process
• 3. Chapter 3
  • 3.1. Data Pre-processing
• 4. Chapter 4
  • 4.1. Over-Fitting and Model Tuning
• 5. Chapter 5
  • 5.1. Measuring Performance in Regression Models
• 6. Chapter 6
  • 6.1. Linear Regression and Its Cousins
• 7. Chapter 7
  • 7.1. Nonlinear Regression Models
• 8. Chapter 8
  • 8.1. Regression Trees and Rule-Based Models
• 9. Chapter 9
  • 9.1. A Summary of Solubility Models
• 10. Chapter 10
  • 10.1. Case Study: Compressive Strength of Concrete Mixtures
• 11. Chapter 11
  • 11.1. Measuring Performance in Classification Models
• 12. Chapter 12
  • 12.1. Discriminant Analysis and Other Linear Classification Models
• 13. Chapter 13
  • 13.1. Nonlinear Classification Models
• 14. Chapter 14
  • 14.1. Classification Trees and Rule-Based Models
• 15. Chapter 15
  • 15.1. A Summary of Grant Application Models
• 16. Chapter 16
  • 16.1. Remedies for Severe Class Imbalance
• 17. Chapter 17
  • 17.1. Case Study: Job Scheduling
• 18. Chapter 18
  • 18.1. Measuring Predictor Importance
• 19. Chapter 19
  • 19.1. An Introduction to Feature Selection
• 20. Chapter 20
  • 20.1. Factors That Can Affect Model Performance
• 21. Appendix
  • 21.1. Appendix

APM Module

• applied_predictive_modeling Documentation
  • applied_predictive_modeling
    • applied_predictive_modeling.test

APM Project

• Frequently Asked Questions (FAQ)

[KJ13]

Max Kuhn and Kjell Johnson. Applied Predictive Modeling. Springer, 2013.