pgpredict – Predictive Analytics for PostgreSQL

Wikipedia defines Predictive Analytics as ” … an area of data mining that deals with extracting information from data and using it to predict trends and behavior patterns”. pgpredict is a project in development that aims to bring this capability to PostgreSQL.

What is pgpredict?

pgpredict is a continuation of 2UDA, which allows Orange to be used to work with data stored in a PostgreSQL database. pgpredict expands that with the option to export Orange’s predictive models to .json files,  which can be transferred to where they are needed (e.g. the production server) and deployed in the database. So the project is split into extensions for Orange that can export models, and for postgres that can load and run those models. These extensions can be installed independently, e.g. given the predictive model files, only the postgres extensions are needed for their deployment.

Below is a visual representation of this process.

How can I get pgpredict?

(The Alpha 1 release of pgpredict is now available for download – April 27, 2016)

A package containing both sets of extensions, installation instructions, and an accompanying tutorial with examples is available in the form of an archive containing the latest development version. Click here to download.

Click here for a tutorial to help you jump start your pgpredict experiments.

Need more help?