Imputation Work Flow on whole dataset

[wasay464]

Issue description

Kudos to the team for the wonderful repo. I have some questions regarding imputation workflow.
I have a custom univariate dataset with half hourly samples and the missing values are in random chunks throughout the dataset. What should I do to get the the imputed values in this case as these NaNs are distributed throughout the train, val and test sets. Furthermore, in this case, the rate of masking is set to be zero as the NaNs values are already masked. So what should be the workflow in this case.
Another question is if i have to implement my own model (say, some modification of TimesNet), how should I add it in the repo. there should be some tutorial for this case as well.

Your contribution

Already starred the repo

[github-actions]

Hi there 👋,

Thank you so much for your attention to PyPOTS! You can follow me on GitHub to receive the latest news of PyPOTS.
If you find PyPOTS helpful to your work, please star⭐️ this repository to get this issue prioritized.
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.

Best,
Wenjie

[github-actions]

This issue had no activity for 14 days. It will be closed in 1 week unless there is some new activity. Is this issue already resolved?

[WenjieDu]

Hi Sultan, thanks for raising the discussion here.

Regarding the workflow, I believe our data preprocessing pipelines in BenchPOTS here https://github.com/WenjieDu/BenchPOTS/blob/main/benchpots/datasets can help. To add the model into PyPOTS, you should refer to some models that you're familiar with in PyPOTS. Their implementations can help you figure out how the framework operates.