h2o.R

# The following two commands remove any previously installed H2O packages for R.
if ("package:h2o" %in% search()) { detach("package:h2o", unload=TRUE) }
if ("h2o" %in% rownames(installed.packages())) { remove.packages("h2o") }

# Next, we download packages that H2O depends on.
pkgs <- c("methods","statmod","stats","graphics","RCurl","jsonlite","tools","utils")
for (pkg in pkgs) {
  if (! (pkg %in% rownames(installed.packages()))) { install.packages(pkg) }
}

# Now we download, install and initialize the H2O package for R.
install.packages("h2o", type = "source", repos = "http://h2o-release.s3.amazonaws.com/h2o/rel-turnbull/2/R")

# Installing 'rsparkling' from CRAN
install.packages("rsparkling")
options(rsparkling.sparklingwater.version = "2.0.3")
library(rsparkling) 

# Reinstalling 'sparklyr' 
install.packages("sparklyr")
library(sparklyr)
spark_install(version = "2.0.0")

# Connecting to Spark version 2.0.0
sc <- spark_connect(master = "local", version =  "2.0.0")

h2o_context(sc)

library(dplyr)
mtcars_tbl <- copy_to(sc, mtcars, overwrite = TRUE)
mtcars_tbl
mtcars_hf <- as_h2o_frame(sc, mtcars_tbl)
mtcars_hf

spark_disconnect_all()