This message was deleted Nixtla Community #neural-forecast

Join Slack

This message was deleted.

# neural-forecast

Slackbot

11/23/2022, 2:31 PM

This message was deleted.

Kin Gtz. Olivares

11/23/2022, 2:55 PM

Hi @J T, The way that one can accomodate seasonalities in the NHITS model is through the

n_freq_downsample

parameter. • In your case with monthly data you can try for example

n_freq_downsample=[6,3,1]

. • It seems that the scale of your data might be challenging too, you might want to try the

scaler_type='norm'

to help the optimization of the network (even ReLU nonlinearities might struggle with very large signals). • You might want to train the network for a bit longer epochs.

J T

11/23/2022, 4:11 PM

@Kin Gtz. Olivares, thanks for advice. i have increase the epochs = 100, and added downsamples as you suggested. thing did changed afterwards. but still not close. may try scaler next. but seasonality is not included it the model, so far.

J T

11/23/2022, 4:16 PM

i check a post and it seems their nbeats not forecasting seasonality ups an downs either: https://pytorch-forecasting.readthedocs.io/en/stable/tutorials/ar.html

J T

11/23/2022, 4:28 PM

also, how to import AutoNHITS? from neuralforecast.models import AutoNHITS , AutoNBEATS does not work.

Kin Gtz. Olivares

11/23/2022, 4:30 PM

Copy code

from neuralforecast.auto import (
    AutoMLP, AutoNBEATS, 
    AutoRNN, AutoTCN, AutoDilatedRNN,
)

👍 1

Kin Gtz. Olivares

11/23/2022, 4:31 PM

I think that the scale might be challenging to the models. Can you try the Box-Cox transform, taking logarithms of your data and then training the network?

9 Views

Open in Slack

Previous Next