Create a k-fold vector useful for H2O algorithms that take a fold_assignments argument.
h2o.kfold_column(data, nfolds, seed = -1)
Returns an H2OFrame object with fold assignments.
A dataframe against which to create the fold column.
The number of desired folds.
A random seed, -1 indicates that H2O will choose one.
if (FALSE) {
library(h2o)
h2o.init()
f <- "https://s3.amazonaws.com/h2o-public-test-data/smalldata/iris/iris_wheader.csv"
iris <- h2o.importFile(f)
kfolds <- h2o.kfold_column(iris, nfolds = 5, seed = 1234)
}
Run the code above in your browser using DataLab