This is a general maintenance release of Kraken, so these notes are going to be a quick read for you. 🙂
We've improved the user experience and fixed some bugs for you.
We've implemented several bug fixes, minor experience enhancements and performance improvements. A few noteworthy items to call out in this release include:
- Kraken now clearly indicates that datasets are limited to 501 columns if you attempt to load a dataset wider than that.
- When training a Timeseries Analysis, Kraken now indicates that it may take several minutes to complete model training.
- When training a Binary, Multiclass or Regression Analysis, the lower left-hand corner of the screen now indicates the progress of the model training as well as which algorithm is currently being run.
- The model metrics screen for Analyses built with Automatic Hyperparameter Optimization now clearly indicates that the individual HPO model metrics are generated from training data.
- Resolved: Safari users may have experienced an occasional issue where, upon login, Kraken would present a "something went wrong" message.
- Resolved: Kraken now automatically drops dataset rows that are completely null when training Analyses as well as when generating predictions.
- Resolved: If a column has been excluded in an Analysis Pipeline, and if you delete the column in the source dataset, Kraken will no longer produce an error when processing the Analysis Pipeline that attempts to drop a column that no longer exists.
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.