Request to add linear interpolation imputation method as a new naive model

[colesussmeier]

1. Model description

Linear interpolation (Lerp) imputation method:

• Lerp will linearly interpolate missing values between the nearest non-missing values.
• If there are missing values at the beginning or end of the series, they will be back-filled or forward-filled with the nearest non-missing value, respectively.
• If an entire series is empty, all 'nan' values will be filled with zeros.

I think linear interpolation is a great naive baseline to compare more complicated models to, and would love to see it become part of PyPOTS! I have the code implemented already, so I can make a PR to dev with your consent.

2. Check open-source status

• [X] The model implementation is publicly available

3. Provide useful information for the implementation

Implementation is relatively straight-forward and uses numpy.interp under the hood. I don't have an official paper on it for this use-case but it has been widely used in many domains for many years. Please let me know if you have any questions and if I can submit a PR! Email: colesussmeier@gmail.com :)

[github-actions[bot]]

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. 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]

Thanks for proposing this idea, @colesussmeier! We previously used pandas to help generate linear interpolation results, but I think it would be cool to add one implementation into PyPOTS ;-) Could you please make a PR to submit yours? I'll help review your code.