Closed kkckk1110 closed 7 months ago
Hey @kkckk1110, thanks for using neuralforecast. Can you provide the full stacktrace for the error you're getting? For the auto models you have to provide the exogenous features in the config.
Thank you very much for your attention!
Thanks. That seems to be a protobuf error, can you try the fix suggested here?
That's really helpful! Thank you very much!
What happened + What you expected to happen
I came across a bug when running the getting_started.ipynb in the following codes: the bug is:
ValueError: you tried to log -1 which is currently not supported. Try a dict or a scalar/tensor.
Also, I have a problem with the implementation of exogenous features. If I want to use Auto version of models, how can I add exogenous features to it? When I attempted to add futr_exog_list to AutoLSTM(h=h, config=config_lstm, loss=MQLoss(), num_samples=2), it raises an error that futr_exog_list argument cannot be found.
Versions / Dependencies
I have neuralforecast==1.6.4
Reproduction script
%%capture horizon = 12
models = [LSTM(h=horizon, # Forecast horizon max_steps=500, # Number of steps to train scaler_type='standard', # Type of scaler to normalize data encoder_hidden_size=64, # Defines the size of the hidden state of the LSTM decoder_hidden_size=64,), # Defines the number of hidden units of each layer of the MLP decoder NHITS(h=horizon, # Forecast horizon input_size=2 * horizon, # Length of input sequence max_steps=100, # Number of steps to train n_freq_downsample=[2, 1, 1]) # Downsampling factors for each stack output ] nf = NeuralForecast(models=models, freq='M') nf.fit(df=Y_df)
Issue Severity
None