-
Notifications
You must be signed in to change notification settings - Fork 4
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
Problem with WhatIfClassif counterfactual generation #7
Comments
WhatIf returns the k closest data points of |
I checked the dataset and it seems that there are lots of duplicates in the dataset. I removed them and now the results are alright. Thanks. |
Great! @susanne-207: Should we restrict the WhatIf counterfactual search space to unique observations? X_search = unique(X_search) |
A bit late, but yes :) |
@andreash0, @susanne-207 I had been working on COMPAS dataset for recidivism. The generated counterfactuals are weirdly the same. I am attaching the screenshots here:
Code snippets:
![recidivism_1](https://user-images.githubusercontent.com/21968577/133669607-91cf381a-afd8-4981-8902-02c67916bc8a.png)
![recidivism_2](https://user-images.githubusercontent.com/21968577/133669624-9c05fa97-6cff-49b6-80d4-06699bbfa7e5.png)
You can see that generated 5 counterfactuals are exactly the same:
Plot:
![Rplot_whatif](https://user-images.githubusercontent.com/21968577/133669639-da106b41-b1c2-4a75-a951-731d5faf441f.png)
The text was updated successfully, but these errors were encountered: