All Products
Search
Document Center

Platform For AI:Construct a request for a PMML service

Last Updated:Dec 25, 2023

This topic describes how to construct a request for a Predictive Model Markup Language (PMML) service that is based on a universal processor.

Notes on input data

When a model is deployed as a service based on the PMML processor, the service requires requests that contain a serialized list of strings. The requests can be concurrently processed by multiple threads. The format of each object in the list must meet the requirements described in DataDictionary of the PMML model file.

For example, the following PMML model has three features: sex, cp, and fbs. Its label field is ifhealth. The format of the request data is [{"sex":0,"cp":1,"fbs":1},{"sex":1,"cp":0,"fbs":1},{"sex":0,"cp":0,"fbs":0}].

<PMML version="4.3">
<Header/>
<DataDictionary numberOfFields="4">
  <DataField name="sex" optype="continuous" dataType="double"/>
  <DataField name="cp" optype="continuous" dataType="double"/>
  <DataField name="fbs" optype="continuous" dataType="double"/>
  <DataField name="ifhealth" optype="categorical" dataType="double">
    <Value value="1"/>
    <Value value="0"/>
  </DataField>
</DataDictionary>
... a model ...
</PMML>