Hey, I’m trying to understand how BaseWindows, used by N-Beats and NHITS generates training examples. In particular I’m trying to understand what’s happening in

training_step

,

_create_windows

and

_parse_windows

. I’m a bit confused by the code. Is there a paper or some doc that describes the idea of what’s done there?

Hi @Cyril de Catheu! Its based on the idea of the NBEATS paper (https://arxiv.org/abs/1905.10437). These models operate in windows (of size

input_size

+

horizon

). The model will take the values in the input region (of size

input_size

) to predict the future

horizon

values. The training loss is based on the forecasting accuracy on the forecasted values. During each training step, we first sample

batch_size

different time series of the dataset. Next, we sample

windows_batch_size

different windows (starting at different random timestamps) from this subset of time series.

@Cristian (Nixtla) I have a question on top of this... Do you also have the feature where if an end date is chosen at random in a batch of timeseries. And given the input_size, the start date would fall outside the span of the timeseries, then the timeseries window is padded with zeros on the left. I think this strategy was used in the DEEPAR paper to simulate cold start problems

We posted a pull request to add padding yesterday!

You are all on top of things! Awesome

it will be merged to main soon

Hey @Cristian (Nixtla) thanks a lot! I’m confused by the shape of temporal in this:

def _create_windows(self, batch, step, w_idxs=None):
        # Parse common data
        window_size = self.input_size + self.h
        temporal_cols = batch["temporal_cols"]
        temporal = batch["temporal"]

        if step == "train":
            if self.val_size + self.test_size > 0:
                cutoff = -self.val_size - self.test_size
                temporal = temporal[:, :, :cutoff]

I thought temporal would be of order 2. But it seems it’s of order 3 in

temporal = temporal[:, :, :cutoff]

I had a look at TimeSeriesDataset but it did not help me to understand Edit: is it of shape:

batchSize, numTemporalColumns, maxSeriesSize

?

Hello Cyril, yes, if I remember correctly that's the shape. If you have any doubt, you can easily find out how it works with the help of this notebook (last cell).

Ok thanks @Antoine SCHWARTZ -CROIX-! will do

@Phil we just pushed to main the padding with zeros.

Awesome! Thank you!

yes, the push. is not in pip yet