-
Notifications
You must be signed in to change notification settings - Fork 834
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
docs: add explanation dashboard integration example notebook #1236
docs: add explanation dashboard integration example notebook #1236
Conversation
249e9fb
to
158676d
Compare
/azp run |
Azure Pipelines successfully started running 1 pipeline(s). |
Codecov Report
@@ Coverage Diff @@
## master #1236 +/- ##
==========================================
+ Coverage 83.57% 83.59% +0.01%
==========================================
Files 264 264
Lines 12919 12919
Branches 634 634
==========================================
+ Hits 10797 10799 +2
+ Misses 2122 2120 -2
Continue to review full report at Codecov.
|
158676d
to
76b5b87
Compare
/azp run |
Azure Pipelines successfully started running 1 pipeline(s). |
/azp run |
Azure Pipelines successfully started running 1 pipeline(s). |
/azp run |
Azure Pipelines successfully started running 1 pipeline(s). |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
As discussed on Teams, please add a comment for the "!pip install" command for Synapse. The rest looks great! Thank you so much!
76b5b87
to
a3f3f14
Compare
/azp run |
Azure Pipelines successfully started running 1 pipeline(s). |
/azp run |
Azure Pipelines successfully started running 1 pipeline(s). |
/azp run |
Azure Pipelines successfully started running 1 pipeline(s). |
/azp run |
Azure Pipelines successfully started running 1 pipeline(s). |
Using this PR and creating a new notebook instead of updating an existing notebook: #1228
Closing the other PR based on comments.
======== Description from previous PR:
This PR integrates the RAI widgets with the SHAP interpretability notebook.
Specifically, it demonstrates how to create an interpret-community style explanation from the local importance values, which can then be visualized in the ExplanationDashboard widget locally and optionally uploaded to AzureML.
In a near-term future TODO, the ExplanationAdapter can be integrated directly into the SHAP explainer with explain_local and explain_global APIs, so the explainer can output the explanation directly.
Please add this image in the examples URL which demonstrates how the ExplanationDashboard will look like after passing the interpret-community explanation to it: