End-to-end modeling workflow with Azure¶
DataRobot offers an in-depth API that allows you to produce fully automated workflows in your coding environment of choice. This accelerator shows how to enable end-to-end processing of data stored natively in Azure.
In this notebook you'll see how data stored in Azure can be used to train a collection of models on DataRobot. You'll then deploy a recommended model and use DataRobot's batch prediction API to produce predictions and write them back to the source Azure container.
This accelerator notebook covers the following activities:
- Acquire a training dataset from an Azure storage container
- Build a new DataRobot project
- Deploy a recommended model
- Score via DataRobot's batch prediction API
- Write results back to the source Azure container