Analyst firm IDC recently placed SAS Viya as a leader in its MLOps Platforms evaluation, praising SAS for our support of a wide variety of languages and platforms. Using our open source package, python-sasctl, SAS Model Manager, containers and more, we will demonstrate how to create an end-to-end MLOps process for Python models on SAS Viya. Using python-sasctl, we will automatically generate scoring code and important metadata files for models developed using the most popular Python frameworks, including sklearn, xgboost, MLflow and more. These models are sent to SAS Model Manager directly from the Python development environment. From SAS Model Manager, these models are compared, tested, deployed into containers, and monitored. Review this presentation and come away with a better understanding of how to leverage SAS Viya to develop a MLOps process inclusive of Python models.
To learn more about python-sasctl, check out the following resources:
Presentation slides are attached to this post.
