What's New with SAS Model Manager? Publish SAS models to Azure Machine Learning
Have you ever wanted to expand utility of your SAS models? Have you wanted to score SAS models within a Power BI report or Microsoft Power Apps low-code app? Great news! This is now a lot easier with the latest SAS and Microsoft integration. Deploying SAS and open-source models to Azure Machine Learning has never been easier.
With SAS Viya 2021.1.3 stable release, SAS Model Manager now supports publishing SAS models directly to Azure Machine Learning. This is the second phase of SAS Model Manager's planned integration point, with more integrations planned. Check out this article for the initial integration effort supporting publishing Python models to Azure Machine Learning.
Users with an Azure Machine Leaning (AML) tenant and SAS Model Manager on SAS Viya (MM) license can use their Azure AD single-sign-on to quickly publish SAS models directly into AML. Users need to register SAS models, already registered into MM, using a configured Azure Machine Learning publishing destination allowing MM to dynamically discover available AML workspaces for model registration. MM takes care of passing all the necessary artifacts to AML. AML then creates an AML container, using a specially configured base container. This might sound complex, but the user experience is incredibly simple. Just choose your AML publishing destination, select your AML workspace and select "publish". SAS Model Manager and Azure Machine Learning developers took care of everything for you!
The following video walks through the simple and integrated SAS and Microsoft connection to publish SAS models into Azure Machine Learning.
SAS Models
Which SAS models you might ask? Any SAS model with executable score.sas or .sasast (astore) registered in SAS Model Manager on SAS Viya is supported. This includes models created in SAS Enterprise Miner, Base SAS, SAS Enterprise Guide, SAS Visual Data Mining Machine, SAS Visual Text Analytics, and SAS Studio.
Azure Machine Learning Publishing Destination
Admin users can leverage this example notebook to create an Azure Machine Learning (AML) publishing destination in SAS Environment Manager using their AML Subscription ID.
Score SAS models with confidence in Azure Machine Learning
SAS Model Manager offers a simple Publish option that dynamically discovers available AML workspaces for registering your SAS models. Once published, it's easy to validate whether SAS models will run successfully in AML using SAS Model Manager’s Publishing Validation option. This feature dynamically creates a temporary Azure compute resource. Select test data, and SAS Model Manager will pass the data directly into the Azure Machine Learning Inference Computer cluster. Once AML runs the data in the container, the compute cluster shuts down automatically. Results of the Publishing Validation process return to SAS Model Manager for review. SAS Model Manager also offers an option to Deploy published models to Azure Kubernetes Service (AKS) to immediately provide a useable endpoint to score your SAS models in Azure.
Check out how easy it is to deploy SAS and Python models from SAS Model Manager to Azure Kubernetes Service.
For more information about using AML as a SAS Model Manager publishing destination, see the SAS Model Manager: User’s Guide documentation.
With Microsoft Azure as the preferred cloud provider for SAS Cloud, we are working together to provide the best experience and value to our customers as they transition to the cloud. We will build deep integrations of our SAS® Viya® Platform with Azure services, develop joint market-ready solutions in different industry verticals, and share in go-to-market activities across the globe. For more information on the strategic partnership, visit www.sas.com/Microsoft.
Discover new SAS Viya 2021.1.3 features:
Discover new SAS Model Manager features:
- Simple filtering dashboards plus enhanced search options
- Customize SAS Model Manager performance monitoring reports with embedded web components
- pzmm (Python Zip Model Management) module updates
- New/updated Model Management Macros generating JSON files
- Enhanced support for R models
- New Project Wizard
- Home page
- Publish Python models to Azure Machine Learning
- Updated performance report
Now's your turn. We're thinking about other SAS Model Manager and Microsoft integrations. Perhaps ways to enhance Team collaboration. What do you suggest? Leave us your suggestion in a comment below.
