Fidele Koffivi Gbagbe
07/20/2023, 5:51 PMCristian (Nixtla)
07/20/2023, 5:56 PMfutr_df
is only to be used for the future exogenous covariates (see example in https://nixtla.github.io/neuralforecast/examples/exogenous_variables.html). You should use df
to pass the usual dataset (with y
and historic exogenous covariates), and the function will return the next h
forecasts after the last date of df
.eval_data
), you can merge train_data
and eval_data
and use the cross_validation
method.