Importing and exporting models as PMML

PMML, or predictive model markup language, is an XML format for describing data mining and statistical models, including inputs to the models, transformations used to prepare data for data mining, and the parameters that define the models themselves. IBM® SPSS® Modeler can import and export PMML, making it possible to share models with other applications that support this format, such as IBM SPSS Statistics.

For more information about PMML, see the Data Mining Group website (http://www.dmg.org).

To export a model

PMML export is supported for most of the model types generated in IBM SPSS Modeler. See the topic Model types supporting PMML for more information.

  1. Right-click a model nugget on the models palette. (Alternatively, double-click a model nugget on the canvas and select the File menu.)
  2. On the menu, click Export PMML.
  3. In the Export (or Save) dialog box, specify a target directory and a unique name for the model.
Note:

You can change options for PMML export in the User Options dialog box. On the main menu, click:

Tools > Options > User Options

and click the PMML tab.

See the topic Setting PMML Export Options for more information.

To import a model saved as PMML

Models exported as PMML from IBM SPSS Modeler or another application can be imported into the models palette. See the topic Model types supporting PMML for more information.

  1. In the models palette, right-click the palette and select Import PMML from the menu.
  2. Select the file to import and specify options for variable labels as required.
  3. Click Open.

Use variable labels if present in model. The PMML may specify both variable names and variable labels (such as Referrer ID for RefID) for variables in the data dictionary. Select this option to use variable labels if they are present in the originally exported PMML.

If you have selected the variable label option but there are no variable labels in the PMML, the variable names are used as normal.