You can launch PredictionIO on Amazon Web Services. This is a hassle-free way to get a well-configured PredictionIO server quickly.
On Linux / Mac OS X, PredictionIO can now be installed with a single command:
$ bash -c "$(curl -s https://install.prediction.io/install.sh)"
The above script will complete the rest of the instructions on this page for you and you can proceed to the Choosing an Engine Template.
It is very important to meet the minimum version of the following technologies that power PredictionIO.
and one of the following sets:
or
or
If you are running on a single machine, we recommend a minimum of 2GB memory.
INFO: If you are using Linux, Apache Spark local mode, which is the default operation mode without further configuration, may not work. In that case, configure your Apache Spark to run in standalone cluster mode.
PredictionIO runs on a Java virtual machine, so it runs on most platforms. Choose your platform below:
You may also use one of the community-contributed packages to install PredictionIO:
//: # (* (coming soon) Installing PredictionIO with Homebrew)
WARNING: 0.8.2 contains schema changes from the previous versions, if you have installed the previous versions, you may need to clear both HBase and Elasticsearch. See more here.
//: # (Deployment](/production/deploy.html) guide.)
Public snaps are available on our Terminal.com page.
Instance type must be set to medium or higher for PredictionIO to function correctly.