responsible-ai-toolbox
responsible-ai-toolbox copied to clipboard
microsoft
Responsible AI Toolbox is a suite of tools providing model and data exploration and assessment user interfaces and libraries that enable a better understanding of AI systems. These interfaces and libr...
## Description Add identity feature value to feature importance hover over if the identity feature column is specified. ## Checklist Screenshot below:-  - [x] I have added screenshots above...
## Description Use the API `getJointDatasetFeatureName` to get the `JointDataset` feature name. ## Checklist - [ ] I have added screenshots above for all UI changes. - [ ] I...
Implemented the table view, which is a simple Fluent UI table view. Also created framework for obtaining the explanation on-the-fly for a single image by using a base64 encoded image...
## Description Add UI tests for the new RAI text dashboard, specifically the individual feature importances for text component. This includes testing the: 1.) TextHighlighting component, which displays the text...
## Description Adding identity feature value to hover over in scatter plot in causal section. Screenshot:-  ## Checklist - [ ] I have added screenshots above for all UI...
It's a better user experience without commenting these two lines as you can copy and paste them directly in your jupyter notebook. ## Description ## Checklist - [ ] I...
## Description It seems the train sets are large which causes the causal to take longer to train the causal models. Hence, limiting train sets to 500 samples (where ever...
## Description Add the usage of `FeatureMetadata` class to pass the relevant feature metadata to the `RAIInsights` class. This notebook change adds a feature from user data as the identity...
## Description It looks like we have "Classification Error" (aka "Classification outcome") filter supported for multiclass scenario. This was added as a part of the PR https://github.com/microsoft/responsible-ai-toolbox/pull/1371. Hence, supporting the...
Hello Team, We leverage Kubeflow as the MLOps platform for the entire ML Lifecycle. I would like to call the tool box within the Kubeflow Notebook Server while doing experimentation...
