Create a k-fold vector useful for H2O algorithms that take a fold_assignments argument.
h2o.kfold_column(data, nfolds, seed = -1)
data | A dataframe against which to create the fold column. |
---|---|
nfolds | The number of desired folds. |
seed | A random seed, -1 indicates that H2O will choose one. |
Returns an H2OFrame object with fold assignments.
# NOT RUN { 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) # }