After you create, train, and save a model, you can view it in the repository, deploy it,
test the deployment, and run the prediction.
Procedure
-
Sign into the WML for z/OS web user interface with
your user name and password.
-
From the side bar, go to the Model Management page, click the Models tab, and locate the model that you want to
deploy.
-
From the ACTIONS menu for the
tentModel model, select Deploy.
-
Enter a deployment name, such as tentModelDeploy, and select
Online
for Type. Select a version of the model and then a scoring service on which
you want to deploy the version. Click Create to create a new deployment. You can
deploy the same version of the model on different scoring services or different versions of the
model on the same scoring service.
-
On the Deployments tab, verify that
the model is deployed. If necessary, edit the deployment by selecting Update
from the ACTIONS menu. You can edit
the name, model version, and scoring service of the deployment.
-
Test the model by selecting Test API from the ACTIONS menu for the
deployment.
-
On the Test API page, enter values
for a record.
For example, you might enter the values of different fields in table or JSON format for the
tentModel
model:
[{"GENDER": "M", "AGE": 27, "MARITAL_STATUS": "Single", "PROFESSION": "Trades"}]
-
Click Submit. If
you click
Clear
, repeat the last step.
-
Go back to the Model Management page,
click the Models tab, and locate to the
tentModelVMB model.
-
From the ACTIONS menu for the
tentModelVMB model, select Deploy.
-
Enter a name for the deployment, such as tentModelDeployBatch, and
select
Batch
for Type. Select a version of the model. Populate the
Input and Output fields for your TENTDATA data source
on z/OS and click Create.
-
Click to the Deployments tab and
verify that the tentModelVMBDeployBatch model is deployed. From the
ACTIONS menu for the deployment,
select Run Now to perform batch scoring against the model.