The GEQE tool (pronounced "Jeh Key") is aimed at leveraging geo-located temporal text data in order to identify locations or events of similar nature.
The project is currently in public beta and likely to undergo significant changes as we progress.
Project Overview
Provide machine learning and ETL capabilities written in python for Apache Spark. We store our processed datasets as parquet files in HDFS. Currently we use a Random Forest Regression Model to identify similar locations or events.
Provide an API server to support front end applications. Currently we use StrongLoop with MongoDB to support all application data.
Provide a Front end Web-UI written in NodeJS to allow users to build, save, and apply machine learning models.
For more information read our white paper here. and checkout our code from github