Prediction of multiple outputs dependent on multiple features.

JulesBelveze / time-series-autoencoder

PyTorch Dual-Attention LSTM-Autoencoder For Multivariate Time Series

Apache License 2.0

614 stars 63 forks source link

Prediction of multiple outputs dependent on multiple features. #43

Open wsefw opened 7 months ago

wsefw commented 7 months ago

Hello, I have a question. Can this code be used to perform prediction with 8 features and 3 outputs, where each output depends on the 8 features

JulesBelveze commented 7 months ago

Hey @wsefw thanks for your interest! Unfortunately, for now the repository can only be used to predict one target (a column y) or to reconstruct the full entire input (8 features in your example).

However, tweaking the first scenario to predict 3 outputs instead of 1 shouldn't require too many changes. I can give you a hand if needed 🤓

mreyessierra commented 1 month ago

Hello! I would like to know if it is possible to use the model for reconstruction but indicating that I am only interested in removing the noise from one of the time series, taking into account the information from the remaining series? Thank you!