Managing predictive deployments
For proper deployment, you must set up a deployment space and then select and configure a specific deployment type. After you deploy assets, you can manage and update them to make sure they are performing well and to monitor their accuracy.
To be able to deploy assets from a space, you must have a Machine Learning service instance provisioned and associated with that space. For information on how to do that, refer to Associating a service instance with a space.
Online and batch deployments provide simple ways to create an online scoring endpoint or do batch scoring with your models.
If you want to implement custom logic:
- Create a Python function to use for creating your online endpoint
- Write a notebook or script to perform batch scoring
Note that if you create a notebook or a script to perform batch scoring such an asset runs as a platform job, not as a batch deployment.
Deployable assets
Here is the list of assets that you can deploy from a Watson Machine Learning space, with information on applicable deployment types:
| Asset type | Batch deployment | Online deployment |
|---|---|---|
| Functions | Yes | Yes |
| Models | Yes | Yes |
| Scripts | Yes | No |
An R Shiny app is the only asset type supported for web app deployments.
Notes:
- A deployment job is a way of running a batch deployment, or a self-contained asset like a flow in Watson Machine Learning. You can select input and output for your job and choose to run it manually or on a schedule. For details, refer to Creating a deployment job.
- Notebooks and flows use notebook environments. You can run them in a deployment space, but they are not deployable.
For more information, refer to:
After you deploy assets, you can manage and update them to make sure they are performing well and to monitor their accuracy. Here are some ways that you can manage or update a deployment:
-
Manage deployment jobs. After you create one or more jobs, you can view and manage them from the Jobs tab of your deployment space.
-
Update a deployment. For example, you can replace a model with a better-performing version without having to create a new deployment.
-
Scale a deployment to increase availability and throughput by creating replicas of the deployment.
-
Delete a deployment to remove a deployment and free up resources.
Learn more
Parent topic: Deploying and managing models