Function for visualising time series attribution

[smaeland]

🚀 Feature

Function for visualising time series along with attribution values, just like captum.attr.visualization.visualize_image_attr does for images.

Motivation

Working with time series a lot, I often copy the same plotting function around between projects, so I think it would be great to have a basic 1D plotting method built-in. Since 1D attributions are prepared the same way as for images (normalisation and choice of sign), it would fit in nicely with the existing code. I would be happy to submit a PR with my own (adapted) plotting function, but probably best to first discuss the scope and need.

Pitch

A built-in plotting function would simplify and speed up the model development cycle. But besides convenience, it could also be valuable to new users, since the applicability of Captum to time series is somewhat undercommunicated 😄

Alternatives

Users write their own custom plotting functions. This is likely to happen anyway because of the big variation in different time series' length, number of channels, etc., but in that case, a built-in function is a good starting point.

Additional context

[NarineK]

@smaeland, thank you for proposing this functionality. Sure, feel free to send a PR.
cc: i-jones

[ic085908]

@smaeland Thank you for your helpful function for plotting time series.
I tried to learn explainable method for time series and used your function for visualization. However, I am struggling with these processes of transferring my model to explainable method and visualization .
Could you give a simply example to use your function of time series? I apologize for this may disturb you, I am a green hand.

In any case, thanks for your help.

[smaeland]

Hi @ic085908, here is the script I used to produce the plots shown in #980: visualize_synthetic_data.py (data is randomly generated, so it won't look exactly identical). Let me know if you run into any problems or find things that could be improved

[ic085908]

Hello @smaeland, I really appreciate your help.
The script smoothly runs as a figure below. I will apply your script to my model.

Many thanks,

[smaeland]

Great! I'll close this then, since the corresponding PR is merged now.