Example of ML preprocessing in h2o (RECS dataset)

h2o.preprocessing.R

# Initiate remote h2o cluster (receives and processes dataset)
# No modeling is done locally - an address key is saved to reference the remote version
h2o.init(nthreads = -1)
# Prepare h2o inputs for modeling
recs.reduced2.h2o <- as.h2o(recs.reduced2)  # Coerce DF to an h2o object
set.seed(0)   # For reproducibility of train/test split
# Split h2o data into training, validation, and test frames
data.split <- h2o.splitFrame(recs.reduced2.h2o,ratios = c(.7,.2))
train <- data.split[[1]]  # For training
valid <- data.split[[2]]  # For validating trained models and comparing different hyperparameter vectors
test <- data.split[[3]] # For final evaluation of model performance
y = "KWH"
x <- setdiff(x = colnames(train), y = "KWH")