As September draws to a close, we thought it was time to share a bit of new Kraken goodness with you. Comparing Analysis versions is now enabled for all Analysis Card Groups. Retraining a model is now just a single click away. And the Manage Data screen now allows you to sort your datasets/connections for all providers by creation date or name.
Compare Analysis versions on all card groups
No longer limited to the Feature Importance card group, you can now compare Analysis versions in Fit, Correlations and Model Stats card groups. Simply drop down the "Viewing" control in the upper left and choose the "Compare" option. As you click among the card groups - as well as tabs within the card groups - the comparison stays enabled with the Analysis versions you selected.
Quickly generate a new Analysis version with the RETRAIN "easy button"
If you want to create a new version of an Analysis, you can now simply click the RETRAIN button on the Project Overview screen. This will generate a new version of your Analysis using the same Pipeline that is used for the currently-published Analysis version. The RETRAIN button saves time when Kraken prompts you to retrain a model, such as when new and updated Analysis metrics are available (like the recently-released ROC Curve card for binary Analyses).
Sort your datasets/connections in the Manage Data screen
When looking at your data connections in the MANAGE DATA screen, Kraken now provides the ability to sort your datasets (for file-upload CSVs) or data connections (for all other data providers) by name or creation date, as long as there are at least two entries in your list. You can click either the CREATED or NAME button once to sort in ascending order, and again to sort in descending order. By default, Kraken will display your list in descending order of creation date.
We've improved the user experience and fixed some bugs, too.
We've implemented several bug fixes, minor experience enhancements and performance improvements. A couple of noteworthy items to call out in this release include:
Experience enhancement
- Keep Up To Date prediction settings have been refined to ensure that you cannot inadvertently disable Keep Up To Date while keeping Prediction Sync enabled, as that is an invalid settings combination.
Bug fix
- Kraken encountered a problem when reading UTF-8 encoded datasets using a legacy "/r" end-of-line character. These datasets could cause Kraken to interpret every data CELL as a separate data COLUMN with no rows, which is obviously undesirable behavior.
Reminder: If Kraken is misbehaving, check KIKI first.
All Kraken users have access to KIKI, a.k.a. "Kraken Important Known Issues". If you're experiencing an issue with Kraken, KIKI is your first stop to determine if we're aware of the issue. Where possible, we provide suggested workarounds while we work to eliminate issues. KIKI will be updated as we eliminate issues through Kraken product updates, as well as when new issues are identified.
Reminder: SONAR© Guide content is just a click away! |
![]() |
As a Kraken user, you have access to SONAR© Guide, the proven training methodology from Big Squid and your key to learning everything you need to know to use Kraken effectively and become a citizen data scientist hero in the process. A link to the SONAR© Guide content library is accessible whenever you access Kraken help screens; just look for the SONAR© Guide logo on the right-hand side. It's also available in the SONAR© Guide on the Big Squid Support site.