Y_train_df.groupby('unique_id').size() unique_id Australia 72 Australia/ACT 72 Australia/ACT/Business 72 Australia/ACT/Canberra 72 Australia/ACT/Canberra/Business 72 .. Australia/Western Australia/Experience Perth/Other 72 Australia/Western Australia/Experience Perth/Visiting 72 Australia/Western Australia/Holiday 72 Australia/Western Australia/Other 72 Australia/Western Australia/Visiting 72 I'm wondering if the size is different, how to deal with it? for example: the size is 60 60 60 60 60 .. 60 50 12 12 12

That should work natively, can you give an example where it doesn't work?

Thank you Olivier. Yes, it works. I am wondering how it works, it seems amazing.😀

The cross-sectional aggregation doesn't care about missing timestamps; i.e. you just aggregate everything that is present for a particular timestamp. This can be dangerous too, I think it's always good to check for yourself the amount of missing timestamps per timeseries when using techniques like this.