Olivier Sprangers

Thanks for the suggestion; Unfortunately I don't have a timeline for that atm. For now, I'd suggest to make a forecast for these exogenous too - this can be rather...

I can reproduce, it seems there is incorrect parsing of the input data. I can get it to produce a Forecast sheet by formatting the timestamp differently in Excel, but...

@jmoralez I have a working implementation of DeepNPTS in NeuralForecast already, happy to pick this one up.

AutoARIMA's `fit` takes in a dataframe containing the columns `ds, unique_id, y, ex_1, ex_2, ...., ex_n`. The first three are the timestamp, the id of the timeseries and the value...

Indeed, your understanding of the exogenous is now correct. Code seems plausible; You're right about the difference between `forward ` and `forecast`: the latter will fit the model again.

I see you commented the DistributionLoss - what distribution are you using when you see the error? And, does the error also occur you change the distribution type?

Can you test with a Normal distribution? I want to exclude the possibility of this being an issue related to the distributions. Also, the initial error you showed above is...

Hey @zzzrbx just checking in - did you have any luck trying out with the Normal distribution?

> @elephaint I think `HINT` is the only missing one. It's a little bit special. It should be `multivariate` but probabilistic forecast (!), no point forecast, yes Auto, exog depends...

Thanks for submitting a PR! What is the use case for this?