Partitioned (Micro) Models - Teradata Vantage

ClearScape Analytics ModelOps User Guide

Deployment
VantageCloud
VantageCore
Edition
Enterprise
IntelliFlex
VMware
Product
Teradata Vantage
Release Number
7.0
Published
April 2023
Language
English (United States)
Last Update
2023-04-19
dita:mapPath
rfi1654194187578.ditamap
dita:ditavalPath
ayr1485454803741.ditaval
dita:id
B700-1175
ModelOps supports partitioned (micro) modeling where an individual model is trained on a specific partition of the data for each model version. For example, if you have a dataset of product sales and you want to create a predictive model for future sales for every product, you can use micro modeling.

A model can have thousands or even millions of model partitions, though it is represented as one model version in the UI. A micro-model is recognized by the fact that it generates a partitions artifact after the training.

  1. From the Model Versions list, select a micro-model version and select
    under View Events.


    The Model Version Lifecycle page displays.

  2. Expand the Training Details section.
    The training details section expands showing all details of the model version training.
    For details of the model version lifecycle, see Model Lifecycle.
  3. Select View Training Details for Model Partitions under Training Artefacts.

    The Model Partitions list displays the following details:

    Property Description
    Partition ID Specifies the partition ID.
    Partition Records Specifies the number of records in the partition.
    Total Rows Displays the total number of records in all partitions.
    Total Partitions Displays the total number of partitions of the model version.
  4. Select Select Hyper Parameters to select hyper parameters to display in the Partitions list.
  5. Hover on a field in the Available Fields list and select "".

    The field adds to the Selected Fields list.

  6. Add all the required fields to the Selected Fields list and click Select.
    The values of the selected parameters display in the Partitions list for all the partitions.