scikit-learn model deployment on SageMaker

This notebook uses ElasticNet models trained on the diabetes dataset described in Track scikit-learn model training with MLflow. The notebook shows how to:

  • Select a model to deploy using the MLflow experiment UI

  • Deploy the model to SageMaker using the MLflow API

  • Query the deployed model using the sagemaker-runtime API

  • Repeat the deployment and query process for another model

  • Delete the deployment using the MLflow API

For information on how to configure AWS authentication so that you can deploy MLflow models in AWS SageMaker from Databricks, see Set up AWS authentication for SageMaker deployment.

MLflow scikit-learn model training notebook

Open notebook in new tab

Deploy on Model Serving

If you prefer to serve your registered model using Databricks, see Model serving with Databricks.