Add access for explainability (TimeSHAP)

[edpclau]

1. Feature description

Changes to the classify() and forward() methods to make the models compatible with TimeSHAP and other XAI methods.

2. Motivation

I would like to be able to understand which timesteps and features were most relevant for a particular prediction.

3. Your contribution

I don't know enough about how the models are structured to feel confident in changing the api.

[WenjieDu]

Hi there 👋,

Thank you so much for your attention to PyPOTS! If you find PyPOTS helpful to your work, please star⭐️ this repository. Your star is your recognition, which can help more people notice PyPOTS and grow PyPOTS community. It matters and is definitely a kind of contribution to the community.

I have received your message and will respond ASAP. Thank you for your patience! 😃

Best,
Wenjie

[WenjieDu]

Hey Eddie, many thanks for this interesting proposal. I'll take a look at TimeSHAP lib and its paper to see if it's possible for us to integrate it with PyPOTS.

[edpclau]

Hey @WenjieDu,

A friend of mine and I actually got it to work. We had to do a lot of changes to the code. I'll share it here in case it helps you find a better solution.

https://github.com/edpclau/timeshap/tree/main/notebooks/GRU-D