ledell

# 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=",")

ledell

# Also available here: http://h2o-release.s3.amazonaws.com/h2o/rel-simons/7/index.html#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.
if (! ("methods" %in% rownames(installed.packages()))) { install.packages("methods") }
if (! ("statmod" %in% rownames(installed.packages()))) { install.packages("statmod") }
if (! ("stats" %in% rownames(installed.packages()))) { install.packages("stats") }

ledell

library(h2o)
localH2O <- h2o.init(nthreads = -1)  #Start up H2O cluster using nthreads = ncores


# Get training data:
data <- h2o.importFile("http://www.stat.berkeley.edu/~ledell/data/wisc-diag-breast-cancer-shuffled.csv",
  destination_frame = "breast_cancer")
y <- "diagnosis"  #Response column
x <- setdiff(names(data), c(y, "id"))  #remove 'id' and response col

ledell

library(miniCRAN)
library(gender)
library(stringr)

# Get package description data
# This took about an hour to run, so you can load the data directly below
# pkgs <- available.packages("http://cran.rstudio.com/src/contrib")
# desc <- getCranDescription(pkgs, repos = c(CRAN="http://cran.rstudio.com")) 
desc <- read.csv("http://www.stat.berkeley.edu/~ledell/data/RStudioCRAN_pkgDesc_20141216.csv")