Cristian Challu

Hi @ramdhan1989, We released the fix to the scalers on March 28th. The input data must not have any NaN value, as it will propagate to all the data.

Hello, We are developing a new library with several models, including NBEATSx, in another repository: https://github.com/Nixtla/nixtlats Please refer to the documentation (https://nixtla.github.io/nixtlats/) for usage examples.

Hello @eddietaylor, thanks for your interest in the library. We have an example of decomposition components in https://github.com/Nixtla/neuralforecast/blob/main/nbs/models.nhits.ipynb.

Hi @hugogobato. This issue was fixed in #720 in August 15 for point losses. Are you using the latest version? The training loss is not scaled back, but you should...

Hi @whoknowsB! The issue is probably due to the normalization. While the `inference_input_size` limits the length of the input for the LSTM pass, the normalization statistics are computed on the...

Hi @MC-Dave. Yes, we assume the exogenous variables are known for the forecasting window. In EPF, the exogenous variables correspond to predictions of demand and offer for the forecasting window....

Hi @iamyihwa ! The predict_insample method is internally specifying the entire length of the series as the `test_size`. We currently have a limitation that `test_size-h` (length - h) must be...

The issue is that the predict insample internally sets `test_size=series_length-true_test_size` (where true_test_size is the one you defined), because it is forecasting the training data. This internal `test_size` should satisfy the...

Potential solution: - `predict_insample` always sets `step_size=1` at the beginning of the function but stores the value set by the user. - the troubling condition will always be satisfied -...

Hi @AlexMV12 . Can you provide your code or the error, please?