Early draft of our "Feature Engineering and Selection" book

Kjell and I are writing another book on predictive modeling, this time focused on all the things that you can do with predictors. It's about 60% done and we'd love to get feedback. You cna take a look at http://feat.engineering and provide feedback at https://github.com/topepo/FES/issues.

The current TOC is:

1. Introduction
2. Illustrative Example: Predicting Risk of Ischemic Stroke
3. A Review of the Predictive Modeling Process
4. Exploratory Visualizations
5. Encoding Categorical Predictors
6. Engineering Numeric Predictors
7. Detecting Interaction Effects (these later chapters are not finished yet)
8. Flattening Profile Data
9. Handling Missing Data
10. Feature Engineering Without Overfitting
11. Feature Selection

tidyposterior slides

tidyposterior is an R package for comparing models based on their resampling statistics. There are a few case studies on the webpage to illustrate the process.

I gave a talk at the Open Data Science Conference (ODSC) yesterday. A pdf of the slides are here and the animated gif above is here.

New Workshop in Washington DC (August)

I'll be conducting a workshop called "Applied Machine Learning" in Washington DC on August 15 and 16. The last one, at the RStudio conference, sold out quickly.

The 2 day course is a blend of caret and the newer tidy modeling pacakges (recipes, rsample, etc):

Machine learning is the study and application of algorithms that learn from and make predictions on data. From search results to self-driving cars, it has manifested itself in all areas of our lives and is one of the most exciting and fast-growing fields of research in the world of data science.

This two-day course will provide an overview of using R for supervised learning. The session will step through the process of building, visualizing, testing, and comparing models that are focused on prediction. The goal of the course is to provide a thorough workflow in R that can be used with many different regression or classification techniques. Case studies on real data will be used to illustrate the functionality and several different predictive models are illustrated.

The course focuses on both high-level approaches to modeling (e.g., the caret package) and newer modeling packages in the tidyverse: recipes, rsample, yardstick, and tidyposterior. Basic familiarity with R and the tidyverse is required.