H2O & RStudio Server on Amazon Web Services (AWS), the Easy Way!
Practical walkthroughs on machine learning, data exploration and finding insight.
- Setting up an AWS Instance
- Create a VPC
- Create an EC2 Instance
- Step 1: Choose an Amazon Machine Image (AMI)
- Step 2: General Purpose Machine
- Step 3: Configure Instance Details
- Customize your Build - Advanced Details
- Step 6: Configure Security Groups
- Key Pair
In this article, I will show you the easy way to install H2O and RStudio Server on Amazon Web Services (AWS) from scratch. No need of customized AMIs or third party tools - no training wheels here. And the best part is that we can do everything from the Amazon Web Service wizard, we won’t need to terminal or putty anywhere! The key is passing all additional install commands for R, RStudio Server, and Curl in the configuration window in step 3 under ‘Advanced Details’. We’ll even have it create our RStudio user account.
For those who don’t yet know,
H2O is an open-source software for machine learning and big-data analysis. It offers various models such as GLM, GBM and Random Forest, but more importantly, offers a deep learning neural network and large-scale clustering!
For a great introduction to numerous features check out: DeepLearning_Vignette.pdf
Some important points, first, AWS isn’t free! If you follow along with the instance from this walk-through, it won’t cost you more than a few cents an hour. Just don’t forget to stop or terminate you instance once you’re done!
Manuel Amunategui - Follow me on Twitter: @amunategui