When training the model for an AI object, SQL Data Insights (SQL DI) collects key data statistics and renders them into metric scores for the model. The visualized scores can help you understand the results of AI queries on the object. You can view the data statistics and model scores on the Analyze data page of the SQL DI web UI.
Procedure
- Sign in your SQL DI web UI with a valid RACF® user ID at the following address:
https://<SQLDI-IPAddress>:<SQLDI-PortNumber>
SQL DI uses a login group to identify and authorize users. The default group name is SQLDIGRP. Make sure that the user ID that you specify is defined in your SQL DI login group.
- On the
Connections page, select a connection and click the
action menu.
- Select
List AI objects to open the AI objects page for the connection.
- Select an AI object and from the
action menu, select Analyze data.
- On the Analyze data page, toggle between the
Object
details, Data statistics, Column influence, and
Column discriminator tabs.
- The
Object details tab displays the column configuration information, including
the name, Db2 data
type, and SQL DI data
type of a column.
- The
Data statistics tab displays the column value distribution information,
including the most common value, the number of most common value, the number of unique value,
standard deviation, mean, max, and min values of a column.
- The
Column influence tab, available after successful AI query enablement on the
object, displays the column influence scores. An influence score correlates to the number of
user-specified and SQL NULL values in a column and indicates the column's influence on the training
of the object model. The fewer NULL values the column has, the higher influence score it generates.
- The
Column discriminator tab, available after successful AI query enablement on
the object, displays the column discriminator scores. A discriminator score correlates to the number
of unique values in a column and measures the column's ability to semantically distinguish its
values from other values in the table. The more unique values the column has, the higher
discriminator score it generates. The generally high discriminator score of the primary key column
is not included on the tab because it may skew the representation of the scores of other columns.
- Click the
icon to reload the page to display data updates.