Install H₂O package in R¶

Quick Start Video¶

Dependencies¶

The H2O package is built with some required packages. To properly install H2O, install the following dependencies:

• RCurl
• rjson
• statmod
• survival
• stats
• tools
• utils
• methods

If your machine does not have curl-config, you must install the dependencies outside of R. Refer to the following directions for your OS.

• For OS X: In a new terminal window, enter sudo apt-get install libcurl4-openssl-dev. After the download completes, open R and enter install.packages("RCurl").
• For Windows: Download the latest Curl package. Select curl executable as the package type, Windows/Win32 or Win64 (depending on your version of Windows), and select Generic as the flavour. If you selected Windows/Win32 as the operating system, select Unspecified as the version. Download the file, extract it, and install it in R.
• For Linux (CentOS): After you install RStudio, install the R-devel package using yum install R-devel.x86_64. Then, install curl-config using yum install libcurl-devel.x86_64.

To install the packages, use install.packages() (for example, install.packages(RCurl)).

Download zip file from h2o.ai¶

Step 1

Download a release from our website. The downloaded package will contain both the H2O jar file as well as the R tar package file for R installation. After download completes, unzip the file and navigate to the R subdirectory with the tar package.

$ unzip h2o-2.8.4.1.zip
$ cd h2o-2.8.4.1/R
$ pwd
  ~/Downloads/h2o-2.8.4.1/R

Step 2

Start R or Rstudio and install the R client package by running install.packages and entering the location of the tar file. To verify the installation, load the library and check that a simple demo script runs.

> install.packages("~/Downloads/h2o-2.8.4.1/R/h2o_2.8.4.1.tar.gz",
  repos = NULL, type = "source")
> library(h2o)
> demo(h2o.glm)

Download from CRAN¶

When downloading from CRAN, keep in mind that the initial download from CRAN contains only the R package. When running h2o.init() for the first time, R automatically downloads the corresponding H2O jar file before launching H2O.

> install.packages("h2o")
> library(h2o)
> localH2O = h2o.init()

H2O is not running yet, starting it now...
Performing one-time download of h2o.jar from
      http://s3.amazonaws.com/h2o-release/h2o/rel-knuth/11/Rjar/h2o.jar
(This could take a few minutes, please be patient...)

Download R Package directly from h2o.ai¶

Download one of releases available on our website. Select the INSTALL IN R tab, then copy and paste the following code into R to install:

# 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, install and initialize the H2O package for R.
install.packages("h2o", repos=(c("http://s3.amazonaws.com/h2o-release/h2o/master/1497/R", getOption("repos"))))
library(h2o)
localH2O = h2o.init()

# Finally, let's run a demo to see H2O at work.
demo(h2o.glm)

Make a build from Git¶

Step 1

If you are a developer who wants to make changes to the R package before building and installing it, pull the source code from Git and follow the instructions in From Source Code (Github).

Step 2

After making the build, navigate to the Rcran folder with the R package in the build’s directory, then run and install.

Amy@LENOVO-PC ~/Documents/h2o/target/Rcran (master)
$ R CMD INSTALL h2o_2.8.4.1.tar.gz
* installing to library 'C:/Users/Amy/Documents/R/win-library/3.0'
* installing *source* package 'h2o' ...
** R
** demo
** inst
** preparing package for lazy loading
Warning: package 'statmod' was built under R version 3.0.3
Creating a generic function for 'summary' from package 'base' in package 'h2o'
Creating a generic function for 'colnames' from package 'base' in package 'h2o'
Creating a generic function for 't' from package 'base' in package 'h2o'
Creating a generic function for 'colnames<-' from package 'base' in package 'h2o'
Creating a generic function for 'nrow' from package 'base' in package 'h2o'
Creating a generic function for 'ncol' from package 'base' in package 'h2o'
Creating a generic function for 'sd' from package 'stats' in package 'h2o'
Creating a generic function for 'var' from package 'stats' in package 'h2o'
Creating a generic function for 'as.factor' from package 'base' in package 'h2o'
Creating a generic function for 'is.factor' from package 'base' in package 'h2o'
Creating a generic function for 'levels' from package 'base' in package 'h2o'
Creating a generic function for 'apply' from package 'base' in package 'h2o'
Creating a generic function for 'findInterval' from package 'base' in package 'h2o'
** help
*** installing help indices
** building package indices
** testing if installed package can be loaded
*** arch - i386
Warning: package 'statmod' was built under R version 3.0.3
*** arch - x64
Warning: package 'statmod' was built under R version 3.0.3
* DONE (h2o)

Step 3

Verify that H2O installed properly:

> library(h2o)
> localH2O = h2o.init()

Upgrading Packages¶

When upgrading H2O, upgrade the R package as well. To prevent a version mismatch, we recommend manually upgrading R packages. For example, if you are running the bleeding edge developer build, it’s possible that the code has changed, but that the revision number has not. In this case, manually upgrading ensures the most current version of not only the H2O code, but the corresponding R code as well.

Simply detach the package and remove it from R before going through the installation process again:

> if ("package:h2o" %in% search()) { detach("package:h2o", unload=TRUE) }
> if ("h2o" %in% rownames(installed.packages())) { remove.packages("h2o") }