kdgutier / esrnn_torch

MIT License
156 stars 44 forks source link

Example of use of the 'unique_id' and 'x' variables. #23

Closed CoteDave closed 4 years ago

CoteDave commented 4 years ago

Hi,

When forecasting multiple Time-series at a time, I was wondering whats the mechanics between the "unique_id" and "x" category feeded to the ESRNN ?

Does the model learns each Time series independently of each others by unique_id and learns interactions between Time series with same unique_id and different "x" categories values ?

Can we use the "x" to learn hierarchies ? For example if we decompose the same Time serie into 3 others Time series (for example using 3 different data filters), the unique_id is the same for the 3 (same original Time series) but different categories (filter1, filter2, filter3), soo each dates are multiplied 3 Times here for the same unique_id, one by category.

Whats is the mechanics here ?

Thanks!

kdgutier commented 4 years ago

There is an example of the 'unique_id' and 'x' variables in the README. https://github.com/kdgutier/esrnn_torch The 'unique_id' identifies the univariate time series from your panel data. While the the 'x' categorical variable is a static variable (one hot encoded within the model) that shows a single discrete characteristic of the time series, that is constant over time.