PMML 2.0 -- Header Information
<!ELEMENT Header(Application?,Annotation*,Timestamp?)> <!ATTLIST Header copyright CDATA #REQUIRED description CDATA #IMPLIED > <!ELEMENT Application (EMPTY)> <!ATTLIST Application name CDATA #REQUIRED version CDATA #IMPLIED > <!ELEMENT Annotation (#PCDATA)> <!ELEMENT Timestamp (#PCDATA)> |
Header: The top level tag that marks the beginning of the header information.
copyright: This attribute contains the copyright information for this model.
description: This attribute contains a non-specific description the for the model. It should contain information necessary to use this model in further applications, but not information that could be better defined in the application element, annotation,and the data dictionary section.This attribute should only contain human readable information.
Application: This element describes the software application that generated the model. Although the PMML models are created to be portable, different mechanisms may create different models from the same data set. It is of interest to the user from which application these models were generated.
name: The name of the application that generated the model.
version: The version of the application that generated this model.
Annotation: Document modification history is embedded here. Each annotation is free text and, like the description attribute in the head element, makes sense to the human eye only. Users can store their own remarks, for example
<Annotation x-author="John Doe">This is a churn model for 1999 customers who ... </Annotation>