Cristian Challu

Hi @sdmishra123, you can split the data into sets using the `cross_validation` function. You can specify the length of the validation and test sets (measured by the number of timestamps)....

The function only supports specifying the number of timestamps or the number of windows (of size h). You can compute the losses for each set after recovering the forecasts and...

Hi @ArvidWeyrauch, the idea of our default config was precisely to only use it if `config==None`. This has the negative effect of requiring modifications (like removing `input_size_multiplier`) if you want...

Thanks for the suggestion, we will improve the documentation.

Hi @tinased95. We added the possibility of specifying an `available_mask` in the input dataframe (as a new column, 1:available, 0:missing). You can impute missing values (so models can use them...

Hi @AngelBerihuete. The library only supports evenly sampled time series. We will improve the documentation with your suggestion.

Hi @rnjv . What model/s are you using? The `save` and `load` methods will work regardless of the number of time series of the data. We have updated the windows-based...

Hi @candalfigomoro. We have a tutorial on how to use `HyperOptSearch` in https://nixtla.github.io/neuralforecast/examples/automatic_hyperparameter_tuning.html

This issue should be solved with the new PyTorch Lightning and Tune versions.