Stream Deployment dialog
On this dialog you specify whether you want to deploy the stream for scoring purposes only, or for model refresh as well. If you choose scoring only, you just need to designate a terminal node as the scoring node. For model refresh, you need to designate additional nodes to enable the model to be refreshed.
You also specify on this screen whether you want to deploy as a stream (for use with IBM® SPSS® Modeler Advantage or IBM SPSS Collaboration and Deployment Services).
- <none>. The stream will not be deployed to the repository. All options are disabled except stream description preview.
- Scoring Only. The stream is deployed to the repository when you click the Store button. Data can be scored using the node that you designate in the Scoring node field.
- Model Refresh. Same as for Scoring Only but in addition, the model can be updated in the repository using the objects that you designate in the Modeling node and Model nugget fields. Note that automatic model refresh is not supported by default in IBM SPSS Collaboration and Deployment Services, so you must choose this deployment type if you want to use this feature when running a stream from the repository. See Model Refresh for more information.
Scoring node. Select a graph, output or export node to identify the stream branch to be used for scoring the data. While the stream can actually contain any number of valid branches, models, and terminal nodes, one and only one scoring branch must be designated for purposes of deployment. This is the most basic requirement to deploy any stream.
Scoring Parameters. Allows you to specify parameters that can be modified when the scoring branch is run. See Scoring and modeling parameters for more information.
Modeling node. For model refresh, specifies the modeling node used to regenerate or update the model in the repository. Must be a modeling node of the same type as that specified for Model nugget.
Model Build Parameters. Allows you to specify parameters that can be modified when the modeling node is run. See Scoring and modeling parameters for more information.
Model nugget. For model refresh, specifies the model nugget that will be updated or regenerated each time the stream is updated in the repository (typically as part of a scheduled job). The model must be located on the scoring branch. While multiple models may exist on the scoring branch, only one can be designated. Note that when the stream is initially created this may effectively be a placeholder model that is updated or regenerated as new data is available.
Deploy as stream. Click this option if you want to use the stream with IBM SPSS Modeler Advantage or IBM SPSS Collaboration and Deployment Services.
Check. Click this button to check whether this is a valid stream for deployment. All streams must have a designated scoring node before they can be deployed. Error messages are displayed if these conditions are not satisfied.
Store. Deploys the stream if it is valid. If not, an error message is displayed. Click the Fix button, correct the error, and try again.
Preview Stream Description. Enables you to view the contents of the stream description that IBM SPSS Modeler creates for the stream. See Stream descriptions for more information.