funModeling
R package: funModeling: data cleaning, importance variable analysis and model perfomance
funModeling: R functions for the messy middle of modeling
funModeling is an R package for exploratory data analysis, data preparation, and model performance. It grew up alongside an open source book and a Spanish-language data school.
What the package holds
The package is a set of R functions around exploratory data analysis, data preparation, and model performance. The one-line description from the project page adds data cleaning, importance variable analysis, and model performance to the same picture. The intended users are named directly: people from business, research, and teaching, with professors and students called out.
A package that comes with a book
funModeling is closely tied to the Data Science Live Book, open source since 2017, because most of the package's functionality exists to explain topics the book covers. The download section lets readers buy a digital copy in PDF, mobi, or epub format at a name-your-price rate, and the project page links to the book's live site where that section lives. The book and the package share the same data science themes, so the README treats them as one story rather than two separate projects.
A Spanish-language offshoot
Spanish-speaking users are pointed at the Escuela de Datos Vivos, a data school started by the same author behind funModeling and the book. It lists free and paid courses, blog posts, and a YouTube channel, with material in R and Python. The package is presented as one piece of a wider learning setup rather than a standalone utility.
Reading the limits
The README does not publish benchmarks or usage statistics. What it does give is a short statement of scope, the connection to the book, and the community resources around it, which is enough to place the package but not to judge its performance.
Community notes