Dawie van Lill
03/23/2023, 1:54 PMhist_exog_list
and futr_exog_list
components. How would I go about running AutoNHITS with exogenous variables?Kin Gtz. Olivares
03/23/2023, 2:01 PMCristian (Nixtla)
03/23/2023, 2:09 PMAutoNHITS
so that users do not need to redefine the config dictionaryDawie van Lill
03/23/2023, 2:18 PMCristian (Nixtla)
03/23/2023, 2:22 PMfutr_exog_list
and hist_exog_list
as any other hyperparamater. For example:Cristian (Nixtla)
03/23/2023, 2:27 PMnhits_config = {
"futr_exog_list": tune.choice([YOUR_LIST]), <----------
"learning_rate": tune.choice([1e-3]),
"max_steps": tune.choice([1000]),
"input_size": tune.choice([5 * horizon]),
"batch_size": tune.choice([7]),
"windows_batch_size": tune.choice([256]),
"n_pool_kernel_size": tune.choice([[2, 2, 2], [16, 8, 1]]),
"n_freq_downsample": tune.choice([[168, 24, 1], [24, 12, 1], [1, 1, 1]]),
"activation": tune.choice(['ReLU']),
"n_blocks": tune.choice([[1, 1, 1]]),
"mlp_units": tune.choice([[[512, 512], [512, 512], [512, 512]]]),
"interpolation_mode": tune.choice(['linear']),
"val_check_steps": tune.choice([100]),
"random_seed": tune.randint(1, 10),
}
Dawie van Lill
03/23/2023, 2:30 PMKin Gtz. Olivares
03/23/2023, 2:31 PMKin Gtz. Olivares
03/23/2023, 2:31 PMDawie van Lill
03/23/2023, 2:35 PMKin Gtz. Olivares
03/23/2023, 2:40 PMDawie van Lill
03/23/2023, 2:43 PMDawie van Lill
03/23/2023, 5:38 PMfede (nixtla) (they/them)
03/23/2023, 10:19 PMMLForecast
, please help us open an issue requesting that feature. We will be happy to work on that 🙂
https://github.com/Nixtla/mlforecast/issues/new?assignees=&labels=&template=feature_request.md