Fully managed cloud. 30-day FREE full featured trial. Start Now
cancel
Showing results for 
Search instead for 
Did you mean: 
exa-Umit
Team Exasol
Team Exasol

Exasol provides Sagemaker-Extension, enabling you to develop an end-to-end machine learning project on data stored in Exasol using the AWS SageMaker Autopilot service. In this article, we are going to briefly explain what the extension can do for you.

 

Background

Recently, a variety of machine learning techniques have been extensively applied to many problems such as churn rate detection, demand prediction, recommendation systems. In order to increase the efficiency and effectiveness of developing predictive models in these applications, Automated Machine Learning (AutoML) approaches have been developed.

AWS SageMaker also services an AutoML tool called Autopilot, in which repetitive ML development steps are automatized.

 

Introduction to SageMaker-Extension

Autopilot covers a complete pipeline of developing an end-to-end machine learning project, from raw data to a deployable model. It is able to automatically build, train and tune a number of machine learning models by inspecting your data set. In this way, the ML tasks, which are repeatedly applied by ML-experts in machine learning projects, are automated. The Exasol Sagemaker Extension takes these advantages of AWS Autopilot and enables users to easily create effective and efficient machine learning models without expert knowledge.

Overview of Exasol SageMaker-Extension

The Exasol Sagemaker Extension provides a Python library together with Exasol Scripts and UDFs that train Machine Learning Models on data stored in Exasol using AWS SageMaker Autopilot service.


The extension basically exports a given Exasol table into AWS S3 and then triggers Machine Learning training using the AWS Autopilot service with the specified parameters. In addition, the training status can be polled using the auxiliary scripts provided within the scope of the project. In order to perform prediction on a trained Autopilot model, one of the methods is to deploy the model to the real-time AWS endpoint. This extension provides Lua scripts for creating/deleting real-time endpoints and creates a model-specific UDF script for making real-time predictions. The following figure indicates the overview of this solution.

 

sme_overview.png

 

In summary, developing effective predictive models from your precious data in your Exasol database through the AWS SageMaker Autopilot service is now very easy with this extension. For more information, please check the References

Additional References

 

We're happy to get your experiences and feedback on this article below!