Tidymodels initial_split prob vs prop

Machine Learning and Modeling
,
1

Working through the examples in Tidy Modeling with R, chapter 5.1, the text says

library(tidymodels)
library(tidyverse)

ames_split <- initial_split(ames, prob = 0.80)

will result in an 80/20 split with seed(123), but I get a 75/25 split. Using prop instead of prob does the 80/20 split, as in

library(tidymodels)
library(tidyverse)

ames_split <- initial_split(ames, prop = 0.80)

The text seems misleading. Am I correct?

2

This topic was automatically closed 21 days after the last reply. New replies are no longer allowed.

If you have a query related to it or one of the replies, start a new topic and refer back with a link.