Hi everyone, First of all, thank you and congrats on the amazing tools you're building. I'm working with irregular time series, and trying to do some feature engineering without resampling the data. Is there an effective way of doing this with mlforecast? I want to compute some statistics with time-based "lags". Instead of computing the mean of the past k lags, compute the mean on all observations in the past k hours. Does that make sense?

it's hard to tell whether it makes sense or not 🙂 I would argue you have to decide whether it makes sense or not, but you can test for sure. But because you will need the information also during predict, you must build a custom function to create exogenous features during forecasting. then you can call this function in lag_transforms. Maybe there is an easier way, but this is the information I can give you. It is certainly not an easy out of the box solution (unless I am missing some other functionalities, which would make your live easy here).