Amit Sharma

@dayongfu As Ram mentioned, that bug was likely due to an encoding mismatch. We have released a new version (0.5) on PyPI that does not have this encoding issue--- `generate_counterfactuals`...

Sorry missed your message @dayongfu DiCE can be used for any Pytorch/tensorflow model. Although we haven't tested it on a LSTM-based model, it should work as long as the model...

This is a great question and depends on the causal relationships between features. We had some [preliminary work](https://arxiv.org/abs/1912.03277) on this but it may take some time to be integrated fully...

@iuush I looked through your messages above and did not find the attached notebook or model. Can you reshare it? We need a minimum reproducible code to understand the issue.

> > I tried the following locally, added the error code, and verified that it did not seem to be working properly. > > ```shell > $ flake8 . --count...

That should not be happening. Can you share a working example of the exact code you are running to get this output? It will be helpful to debug. Are you...

@ninaspreitzer thanks for your patience. This should be fixed in the latest update. Can you clone from main branch and check if the error still persists?

yes, integrating scikit-learn is a high-priority feature and we are working on it. Should have an update in the next few weeks.

@konabuta DiCE supports any ML model that respects the scikit-learn API for `predict` and `predict_proba`. So if your model has these two functions, you can use it with the "sklearn"...

That's a good idea. And I believe some methods in Azua support it. We can add an optional parameter `graph_prior` as, ``` graph = dowhy.learngraph(data, graph_prior=user_graph, method_name="azua.models.vicause.VICause", other_params_for_azua) ``` where...