No more quarantine, no more social distancing, and no more masks! To celebrate, we knew another boring maintenance release wasn't gonna cut it. Predictions are better than ever, now with Data Explorer for prediction datasets as well as new prediction sync options. We've overhauled the Project Overview experience with more intuitive "single-click" controls and an improved layout. And behind the scenes, we've implemented substantial upgrades that are the foundation for a slew of exciting new features coming soon.
Data Explorer update
In addition to training and apply data, you can now explore prediction data in schema view, data view and Data Explorer so you can examine and visualize your prediction data without leaving Kraken.
Prediction Sync update
Kraken Enterprise users now have the ability to apply data and generate predictions using unlimited custom prediction sync schedules that are managed by your friendly neighborhood Big Squid Customer Success Manager.
Project Overview updates
- The layout has been rearranged with Analysis information and metrics at the top, and Prediction information and Scenarios below, with the most recent prediction displayed first.
- Analysis and prediction controls have been simplified and are now displayed with clearly labeled buttons on the right-hand side for quick single-click access.
- A "RUN NOW" option has been added to the Prediction Sync window for quick access to manually running your latest predictions.
- Kraken now displays the data provider connection name along with a data provider type icon for Analyses and Predictions in the Project Overview screen.
- Kraken now limits display of Correlations and Target Correlations cards to datasets with 50 or fewer columns, preventing slow browser performance or lockup.
Data Pipeline updates
- When replacing nulls in a column, Median has been added as a fourth option.
- The "three dots" menu is now available for features that Kraken has automatically excluded after you select a target, allowing you to apply pipeline steps to these features that can cause Kraken to "un-exclude" them, such as replacing nulls or finding/replacing values.
- When attempting to rename a column to a column name that already exists, Kraken now specifically informs you that you need to choose a different name.
- When adding a Pipeline step without saving it, Kraken no longer allows you to run an Analysis until the Pipeline step is either saved or deleted.
- The Split Columns option is now more robust and reliable than in previous releases.
We've also implemented lots of bug fixes and performance improvements, including more detailed and prescriptive messaging when errors are encountered.
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.