NBeatsBaseModel

class NBeatsBaseModel(net: etna.models.nn.nbeats.nets.NBeatsBaseNet, window_sampling_limit: Optional[int] = None, train_batch_size: int = 1024, test_batch_size: int = 1024, trainer_params: Optional[dict] = None, train_dataloader_params: Optional[dict] = None, test_dataloader_params: Optional[dict] = None, val_dataloader_params: Optional[dict] = None, split_params: Optional[dict] = None, random_state: Optional[int] = None)

Bases: etna.models.base.DeepBaseModel

Base class for N-BEATS models.

Init DeepBaseModel.

Parameters

• net (NBeatsBaseNet) – network to train

• encoder_length – encoder length

• decoder_length – decoder length

• train_batch_size (int) – batch size for training

• test_batch_size (int) – batch size for testing

• trainer_params (Optional[dict]) – Pytorch ligthning trainer parameters (api reference pytorch_lightning.trainer.trainer.Trainer)

• train_dataloader_params (Optional[dict]) – parameters for train dataloader like sampler for example (api reference torch.utils.data.DataLoader)

• test_dataloader_params (Optional[dict]) – parameters for test dataloader

• val_dataloader_params (Optional[dict]) – parameters for validation dataloader

• split_params (Optional[dict]) –

  dictionary with parameters for torch.utils.data.random_split() for train-test splitting

  • train_size: (float) value from 0 to 1 - fraction of samples to use for training

  • generator: (Optional[torch.Generator]) - generator for reproducibile train-test splitting

  • torch_dataset_size: (Optional[int]) - number of samples in dataset, in case of dataset not implementing __len__

• window_sampling_limit (Optional[int]) –

• random_state (Optional[int]) –

Inherited-members

Methods

fit(ts)	Fit model.
forecast(ts, prediction_size[, ...])	Make predictions.
get_model()	Get model.
load(path)	Load an object.
params_to_tune()	Get grid for tuning hyperparameters.
predict(ts, prediction_size[, return_components])	Make predictions.
raw_fit(torch_dataset)	Fit model on torch like Dataset.
raw_predict(torch_dataset)	Make inference on torch like Dataset.
save(path)	Save the object.
set_params(**params)	Return new object instance with modified parameters.
to_dict()	Collect all information about etna object in dict.

Attributes

context_size

Context size of the model.