Version 2.1.1 - Bugfix Release

Fix the statsmodels version for python 3.10

Version 2.1.0 - New Feature Release

• Added spline definition support for numerical variables
• Added categorical grouping support for categorical variables
• Added sample weight and offset handling, and improved exposure handling
• Improved validation and persistent error handling in model training configuration
• Improved one-way, lift chart, and variable level stats behavior and fixes

Version 2.0.3 - Patch Release

• Bugfix on binary classification

Version 2.0.2 - Patch Release

• Ability for non Admin to run the webapp
• Size reduction of the compiled css
• Bugfixes

Version 2.0.1 - Patch Release

• Small UI improvements
• Bugfix on explicit Train/Test
• Performance improvement

Version 2.0.0 - New Feature Release

Visual Webapp to train GLMs and assess their fit
Removal of the custom Model View
Interactions added to the GLM in the Visual ML

Versions 1.1.1 - Bugfix Release

Fix the saved model view, with the change of interface of the PredictionModelHandler

Version 1.1.0 - Library Upgrade Release

Move the underlying library from statsmodels to glum for better performance (Memory and Speed)

Version 1.0.2 Bugfix Release

Dataiku v11 interface for binary classification changed, which broke the plugin. This fix is compatible with v11 and v10, the two supported versions of the plugin.

Version 1.0.1 Bugfix Release

Fix webapp when using python 3.7 by upgrading dash package requirement