Return to page

H2O Quick Start with R

H2O 3.0 is for enterprise and open-source use, with easy installations for Spark, Python, R, Yarn, Hadoop 1, Amazon EC2, Maven, laptops and standalone clusters.



Talking Points:

Read the Full Transcript



Installation of H2O Package in R

This tutorial will walk you through the installation of the H2O package in R. The prerequisite for this walkthrough includes an installation of Java, version 1.6 or newer, as well as a R version 2.13 or newer. To start, navigate to our website at on your web browser. Click on the download button, which will line you on the downloads page. Scroll down to H2O dev and the latest stable release of H2O dev. Now, hit the second tab on the menu for instructions on how to install in R. Copy the code block, then navigate to your R console and paste the code. First, remove any preexisting H2O package that's installed or loaded in your R session. Then, it downloads any dependencies that H2O packages is built on top of, which includes packages, method, stat mod, stats, graphics, Rcurl, RJson tools, and details. Next, it downloads the actual H2O package from S3. Once you've installed the H2O package, load the H2O package and initialize an instance. To get a quick demo run, demo(h2o.kmeans). If you scroll up, you'll get the code for the entire workflow you just ran, and you're done. You just finished running H2O from R.