cvFolds: Creates cross-validation folds

In amanda-park/easytidymodels: Make tidymodels even easier to run!

Description

Create folds based on training data fed in.

Usage

cvFolds(
  data = train,
  foldNumber = 5,
  stratifyOnVar = FALSE,
  whatVarToStratifyOn = "var"
)

Arguments

data	The training data set
foldNumber	the number of folds for cross-validation. Default is 5.
stratifyOnVar	Logical. Should the folds be stratified based on the response? If so, set TRUE.
whatVarToStratifyOn	Character. What is the name of the variable to stratify on?

Value

An rsample::vfold_cv() object.

Examples

library(easytidymodels)
library(dplyr)
utils::data(penguins, package = "modeldata")
resp <- "sex"
split <- trainTestSplit(penguins, stratifyOnResponse = TRUE, responseVar = resp)
formula <- stats::as.formula(paste(resp, ".", sep="~"))
rec <- recipes::recipe(formula, data = split$train) %>% recipes::prep()
train_df <- recipes::bake(rec, split$train)
folds <- cvFolds(train_df)
folds

amanda-park/easytidymodels documentation built on Dec. 13, 2021, 11:28 a.m.