Viewing an AI object model with SQL DI web UI

When an AI object is enabled for AI query, SQL Data Insights (SQL DI) creates and trains a model for the object. You can view the model on the Model details page of the SQL DI user interface.

Before you begin

Make sure that you have the authorization that is required for a specific task in SQL DI. See Managing SQL DI user permissions and Configuring setup user ID for SQL DI for details.

Procedure

  1. 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.

  2. On the Connections page, select a connection and click the Action selection menu action menu.
  3. Select List AI objects to open the AI objects page for the connection.
  4. On the AI objects page, select an object and click the Action selection menu action menu.
  5. Select View model to open the Model details page.
    You can toggle and navigate to different tabs to view the following details of the object model:
    • The Training history tab keeps a training history of the model, including the start time, the end time, and the current status.
    • The Cluster minimums tab collects the minimum values in cluster data ranges that are computed for numeric columns. Value "-7.2e+75" represents the EMPTY cluster where out-of-bounds values are congregated.
    • The Column configuration tab displays the column configuration you created for training and retraining the model. If you want to update the column configuration, disable the object for AI query and then enable it again.
    • The Training log tab displays the training instance log from the last or latest model training job. If needed, download the log file. The downloaded archive file also includes supplemental logs, such as IBM data2vec log, Base10 clustering log, and unstructured data processing log, and other output files from various training services.