InterpretationInterpretation

This extension gives you additional operators from the space of interpretation and explainable AI. At the moment it covers LIME, SHAP and Shapely. Note that this is an alpha version.

=== Version 0.4.0 ===

  • Added a new Operator Generate Univariate Interpretation which currently provides PDP as an algorithm.
  • Fixed a bug which made Shapely fail on data sets with 2 attributes

 

=== Version 0.3.0 ===

  • Added a new operator Generate Neighborhood which returns the LIME-weighted Neighborhood
  • Fixed a major bug in LIME, which made the weights incorrect.

=== Version 0.2.0 ===

* Grouped models are now supported

* Fixed an issue which made the result not reproduceable, even though a static random seed was used

* Fixed a bug which influenced the calculation of LIME on nominals. Nominals were treated like numericals.

 

=== Version 0.1.1 ===

* Added an icon

* Fixed an error that there was no proper UserError if types of training and testing were different

* Fixed an error that real and integers were considered of different types.


Product Details

Version 0.4.0
File size 83 kB
Downloads 681 (7 Today)681 downloads
Vendor RapidMiner Labs
Category Machine Learning
Released 10/14/21
Last Update 10/14/21 7:39 AM
(Changes)
License AGPL
Product web site
Rating 0.0 stars(0)