search

xinychen / transdim

Machine learning for transportation data imputation and prediction.
https://transdim.github.io
MIT License
1.22k stars 304 forks source link

How to input a missing data to obtain complete data after training #25

Open 1272203655 opened 1 year ago

1272203655 commented 1 year ago

Hello, thank you very much for your open source project, which has been very helpful to me! I have a question now. After training the BATF algorithm, I want to input a missing piece of data and obtain the complete data. What should I do? I would greatly appreciate it if you could reply to my question

xinychen commented 1 year ago

Thank you for this question! This seems to be a very interesting question. But our model does not work on such scenario. If you put the additional data with the training data together, then you will have a complete one which includes what you want to obtain. Or preferably, you can try to use some deep learning models such as GAIN and IGNNK.

1272203655 commented 1 year ago

Thank you for your answer. I will try the two suggestions you provided and hope to achieve good results. Thank you again

xinychen commented 1 year ago

You're welcome!