Predictive Model rule form
Completing the Configurations tab

  1. About
  2. New
  3. Predictive model
  4. Configurations
  5. Input mapping
  6. Results
  7. Statistics
  8. Pages & Classes 
  9. History

From the Configurations tab, you can define undefined functions in a PMML model. You need to use Java code for this.

Note:  This tab is available only when the uploaded PMML model contains undefined functions.

When you upload a predictive model file (a PMML file), the system scans the source file and looks for the applied functions and their definitions. If undefined functions are found, the function names are listed in the Errors section on the Predictive model tab.

PMML functions

PMML functions transform data in PMML models. These models include several predefined functions that are defined as Java code in the Pega PMML execution engine. In addition to the predefined functions, PMML producers sometimes use proprietary expressions (functions) with the PMML models that are not part of the models themselves. These functions are used for various reasons (such as performance or enhancements). In this case, the model contains undefined functions (the model contains only references to the functions and their parameters).

Configuring undefined functions

When you use custom functions, remember that a function takes a list of objects as argument. The order and type of the arguments is the same as defined in the PMML source definition. The output of the function must be the same type that is defined in the PMML source definition. Where applicable, you can use Java primitive types instead of the corresponding objects.

  1. Open an instance of the Predictive Model rule and upload a PMML model.
  2. Click the Configurations tab.
  3. Define custom functions.