h2oEnsemble R package demo (from h2o.ensemble docs)

h2o_ensemble_higgs_demo.R

# A small-data example of binary classification on a local machine using H2O Ensemble

library(h2oEnsemble)
localH2O <-  h2o.init(nthreads = -1)  # Start an H2O cluster with nthreads = num cores on your machine


# Import a sample binary outcome train/test set into R
train <- read.table("http://www.stat.berkeley.edu/~ledell/data/higgs_10k.csv", sep=",")
test <- read.table("http://www.stat.berkeley.edu/~ledell/data/higgs_test_5k.csv", sep=",")


# Convert R data.frames into H2O parsed data objects
training_frame <- as.h2o(train)
validation_frame <- as.h2o(test)
y <- "V1"
x <- setdiff(names(training_frame), y)
family <- "binomial"
training_frame[,c(y)] <- as.factor(training_frame[,c(y)])  #Force Binary classification
validation_frame[,c(y)] <- as.factor(validation_frame[,c(y)])



# Specify the base learner library & the metalearner
learner <- c("h2o.glm.wrapper", "h2o.randomForest.wrapper", 
             "h2o.gbm.wrapper", "h2o.deeplearning.wrapper")
metalearner <- "h2o.deeplearning.wrapper"


# Train the ensemble using 5-fold CV to generate level-one data
# More CV folds will take longer to train, but should increase performance
fit <- h2o.ensemble(x = x, y = y, 
                    training_frame = training_frame, 
                    family = family, 
                    learner = learner, 
                    metalearner = metalearner,
                    cvControl = list(V = 5, shuffle = TRUE))


# Generate predictions on the test set
pred <- predict.h2o.ensemble(fit, validation_frame)
predictions <- as.data.frame(pred$pred)[,c("p1")]  #p1 is P(Y==1)
labels <- as.data.frame(validation_frame[,c(y)])[,1]


# Ensemble test AUC 
library(cvAUC)  #Install from CRAN
cvAUC::AUC(predictions = predictions , labels = labels)
# 0.7888723


# Base learner test AUC (for comparison)
L <- length(learner)
auc <- sapply(seq(L), function(l) AUC(predictions = as.data.frame(pred$basepred)[,l], labels = labels)) 
data.frame(learner, auc)
#                   learner       auc
#1          h2o.glm.wrapper 0.6871288
#2 h2o.randomForest.wrapper 0.7711654
#3          h2o.gbm.wrapper 0.7817075
#4 h2o.deeplearning.wrapper 0.7425813