error reimplementing the pytorch jupyter example

[jaeho3690]

Hello, thank you for sharing a detailed explanation of your work.
Currently, I am facing two issues.

1. Running the Arem.ipynb results in the following error

2. Does your TimeSHAP algorithm only work on binary classification? is there a reason for using only two class in the pytorch example?

Thank you for your time.

[JoaoPBSousa]

Hello @jaeho3690 ,
1 - From what I can gather from your printscreen, it seems like TimeSHAP is not being able to calculate feature explanations on the method feat_explain_all. Just so I am aware of any changes, did you alter anything on the notebook or are you running it default? If you are running it default, could you please delete the pruning and event csv's or change their filenames in order to force TimeSHAP to calculate everything from scratch?

2- TimeSHAP explains one class/prediction at a time, so there is no restrictions of its application to the binary classification domain. If is possible to apply TimeSHAP to a multi-class problem but you need to explain the prediction of each class individually.

[JoaoPBSousa]

Closed this issue due to inactivity. If you have any further questions feel free to re-open the issue or create a new one.