When you create a predictive model, you import the deployment of a machine learning model
from Watson™ Machine Learning or Open Prediction Service.
About this task
In Decision Designer, you select the
deployment that you want to import. This deployment is used by Decision Designer to generate a pre-filled predictive
model template that is connected to the machine learning model.
Procedure
- Open the decision service that you want to work in.
- Open the Predictive models tab and click
Create.
The predictive model creation wizard automatically opens
in 20.0.2. However, in 20.0.3, you must follow these steps to launch the wizard:
- Enter a name for the predictive model and click
Create.
- When the predictive model is open, click the Connect button in
the details panel on the left.
- Select the provider where the machine learning model that you want to use is stored from
the drop-down list.
The list of deployments that are available from this provider is
displayed.
- Expand the machine learning model that you want to use and select the deployment that you
need to make your prediction.
- Click Next to define the input parameters that are needed to make
the prediction.
- If an input schema was automatically generated by the provider, you can edit it if
necessary. You can update or delete existing parameters, and add new ones.
- If no input schema was generated, you can:
- Work in the Form tab and click Add to add
parameters.
- Work in the JSON tab and directly enter a JSON schema.
- Or use a JSON payload to generate a pre-populated schema by clicking Generate from
payload and pasting a JSON payload. The generated schema is editable.
- Click Next to test the model invocation.
This step is
optional and allows you to make sure that the model returns the expected results when called. To
test your model:
- Enter values for each input parameter.
- Click Run.
If the model does not return the expected
results, you can go back to the previous step to edit the input schema as required.
- Click Next to define the output values of the prediction. To
define the output schema, you can:
- Work in the Form tab and click Add to add
values.
- Work in the JSON tab and directly enter a JSON schema.
- Use a JSON payload to generate a pre-populated schema by clicking Generate from
payload and pasting a JSON payload. The generated schema is editable.
- Or use the output of the invocation test to generate a pre-populated schema. The generated
schema is editable. This option is available only if you tested the model invocation.
- Click Create.
Results
A predictive model template is generated for you, along with a data model that is specific
to the machine learning model. This data model is read-only and only usable with this predictive
model.