-
Sorry if this is a silly question, but I copied the notebook DiCE_with_advanced_options.ipynb and just changed the model to xgboost. When I try to run the line
dice_exp = exp.generate_counterfactual…
-
Hello,
I am trying to generate counterfactuals for a dataset that only contains categorical features so I want to define my data interface but when I specify continuous_features to None or even not s…
-
# Generate counterfactual examples
dice_exp = exp.generate_counterfactuals(query_instance, total_CFs=4, desired_class="opposite")#,proximity_weight=1.5, diversity_weight=1.0)
# Visualize counterfact…
-
Hi i am curious on how you generate the counterfactual examples on 4.1 MNIST (specifically digit '1'), could you explain a little bit? When I ran it, I was not able to generate the counterfactual but …
-
You have based DiCE genetic on GeCo if I understand correctly. Is there a way to 'group' features as they define in their paper;
"The first statement says that education and income are correlated: Ge…
-
Hi, I really enjoyed your paper.
I've been working on XAI for the past 5-6 months and recently became interested in counterfactuals for time series models, so my understanding is still a working i…
-
Hi,
Thanks for the great package! I've recently been exploring the CounterfactualRL approach. One problem I've noticed is that whenever I save a trained explainer and then load it back later, the s…
-
I noticed that running several times the generation of CFs, that is basically an optimization, gives me different counterfactuals for different runs.... Should I tune the parameters of the optimizatio…
-
I have the following query instance, but in the output original outcome is not same as query instance, I assume they should be same otherwise it is useless.
dice_exp = exp.generate_counterfactuals(…
-
Currently, `MultiWorldHandler` instantiates and evaluates all combinations of all intervention assignments. This makes complexity exponential in the number of interventions.