Split an existing H2O data set according to user-specified ratios. The number of subsets is always 1 more than the number of given ratios. Note that this does not give an exact split. H2O is designed to be efficient on big data using a probabilistic splitting method rather than an exact split. For example, when specifying a split of 0.75/0.25, H2O will produce a test/train split with an expected value of 0.75/0.25 rather than exactly 0.75/0.25. On small datasets, the sizes of the resulting splits will deviate from the expected value more than on big data, where they will be very close to exact.
h2o.splitFrame(data, ratios = 0.75, destination_frames, seed = -1)
data | An H2OFrame object, to be split. |
---|---|
ratios | A numeric value or array indicating the ratio of total rows contained in each split. Must total up to less than 1. e.g. c(0.8) for 80/20 split. |
destination_frames | An array of frame IDs equal to the number of values specified in the ratios array, plus one. |
seed | Random seed. |
Returns a list of split H2OFrames
# NOT RUN { library(h2o) h2o.init() iris_hf <- as.h2o(iris) iris_split <- h2o.splitFrame(iris_hf, ratios = c(0.2, 0.5)) head(iris_split[[1]]) summary(iris_split[[1]]) # }