azul

We should include an exception when missing values are passed in the `y` column. The loss becomes `nan` during training but it is hard to notice that the problem is...

Unused inferred frequency

1

I think the inferred frequency here is not used. Should we remove it? https://github.com/Nixtla/neuralforecast/blob/09ce6d0075bbf287d78483d04f107dec7505fc5c/neuralforecast/data/tsdataset.py#L117

Trying tu run mqesrnn using GPU the following error appears,

**Is your feature request related to a problem? Please describe.** Right now the forecast method assumes: - All series end with the same timestamp. - The datestamp column (`ds`) of...

The logs printed by `M4.load` claim an error, but the downloaded data is correct. 

I'm running the following code, ``` library(fable) library(tsibble) library(lubridate) library(dplyr) library(readr) library(tidyr) # Aggregate data as required agg_tourism % aggregate_key(State / Region, Trips = sum(Trips)) # Select training data train_df...

Hi, I would like to include a faster version of the autoarima model. Is the package still maintained?

**Is your feature request related to a problem? Please describe.** It's not entirely straightforward to transform prediction intervals into quantiles. **Describe the solution you'd like** The argument `quantile`. It should...

**Is your feature request related to a problem? Please describe.** For `StatsForecast.forecast_fitted_values` to work properly with `levels`, the baseline models (`HistoricAverage`, `Naive`, `SeasonalNaive`, `RandomWalkWithDrift`) need to have the in-sample prediction...

**Describe the bug** Some methods receive the `level` argument to calculate prediction intervals but are not implemented or supported (for example, intermittent models, as @MMenchero pointed out). **Additional context** We...