Closed PotosnakW closed 5 months ago
Thanks for the excellent report. If anyone wants to pick this up the fix is to provide those values to the parent class init (BaseWindows) as is done for NHITS: https://github.com/Nixtla/neuralforecast/blob/37717f43fabcd9c502dc5f0ef089013c6adcc265/neuralforecast/models/nhits.py#L285-L287
which makes sure the inputs are actually lists: https://github.com/Nixtla/neuralforecast/blob/37717f43fabcd9c502dc5f0ef089013c6adcc265/neuralforecast/common/_base_windows.py#L119-L121
instead of manually doing it here https://github.com/Nixtla/neuralforecast/blob/37717f43fabcd9c502dc5f0ef089013c6adcc265/neuralforecast/models/tft.py#L496-L498
What happened + What you expected to happen
When training TFT model with exogenous features, an error occurs (below). This error does not occur if exogenous variables are 'None' (eg., 'hist_exog_list'=None). Other models (NHITS, LSTM, MLP, TCN, RNN) do not have this issue.
File "/neuralforecast/neuralforecast/common/_base_model.py", line 55, in _get_temporal_exogenous_cols set(temporal_cols.tolist()) & set(self.hist_exog_list + self.futr_exog_list) TypeError: can only concatenate tuple (not "list") to tuple
Code is provided to replicate the error.
Versions / Dependencies
neuralforecast==1.7.0 (all recent updates pulled)
OS: Springdale Open Enterprise Linux (--> based on Red Hat Enterprise Linux) Browser: N/A Version: 8.7 Moderna
Reproduction script
Issue Severity
High: It blocks me from completing my task.