On this page
Edit this page

Method 1: Launch an AWS Instance

You can launch PredictionIO on Amazon Web Services. This is a hassle-free way to get a well-configured PredictionIO server quickly.

There is also a AWS Cloudformation version for PredictionIO.

Method 2: Quick Install

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 installation for you.

You can proceed to Choosing an Engine Template, or continue the QuickStart guide of the Engine template if you have already chosen one.

Method 3: Manual Install

Prerequisites

It is very important to meet the minimum version of the following technologies that power PredictionIO.

  • Apache Hadoop 2.4.0 (optional, required only if YARN and HDFS are needed)
  • Apache Spark 1.3.0 for Hadoop 2.4
  • Java SE Development Kit 7

and one of the following sets:

  • PostgreSQL 9.1

or

  • MySQL 5.1

or

  • Apache HBase 0.98.6
  • Elasticsearch 1.4.0

If you are running on a single machine, we recommend a minimum of 2GB memory.

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.

Installing PredictionIO

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:

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.

Method 4: Terminal.com

Public snaps are available on our Terminal.com page.

Instance type must be set to medium or higher for PredictionIO to function correctly.