Explore techniques for handling high cardinality predictors in data analysis using tidymodels, focusing on effect and likelihood encodings. Learn through a practical demonstration using #TidyTuesday data on museums in the UK. Follow along as the screencast covers reading the data, setting up the model, implementing feature engineering techniques, and building the final model. Gain insights into effectively managing complex categorical variables in your data science projects. Access the accompanying code on Julia Silge's blog for further study and implementation.
Overview
Syllabus
Introduction
Reading the data
Setting up the model
Feature engineering
The model
Summary
Taught by
Julia Silge
