Leverage stride
as a way to limit training set size in RegressionModel
s.
#1487
Projects
stride
as a way to limit training set size in RegressionModel
s.
#1487
When all the series have the same freq, the new logic (introduced here: #1399) for tabularization leverages Numpy sliding windows with a stride.
It'd be interesting to expose this
stride
as a way to limit the training set size (similar tomax_samples_per_ts
).The text was updated successfully, but these errors were encountered: