etna.models.nn.NBeatsInterpretableModel#

class NBeatsInterpretableModel(input_size: int, output_size: int, loss: Literal['mse'] | Literal['mae'] | Literal['smape'] | Literal['mape'] | Module = 'mse', trend_blocks: int = 3, trend_layers: int = 4, trend_layer_size: int = 256, degree_of_polynomial: int = 2, seasonality_blocks: int = 3, seasonality_layers: int = 4, seasonality_layer_size: int = 2048, num_of_harmonics: int = 1, lr: float = 0.001, window_sampling_limit: int | None = None, optimizer_params: dict | None = None, train_batch_size: int = 1024, test_batch_size: int = 1024, trainer_params: dict | None = None, train_dataloader_params: dict | None = None, test_dataloader_params: dict | None = None, val_dataloader_params: dict | None = None, split_params: dict | None = None, random_state: int | None = None)[source]#

Bases: NBeatsBaseModel

Interpretable N-BEATS model.

Paper: https://arxiv.org/pdf/1905.10437.pdf

Official implementation: ServiceNow/N-BEATS

Note

This model requires torch extension to be installed. Read more about this at installation page.

Init interpretable N-BEATS model.

Parameters:

input_size (int) – Input data size.
output_size (int) – Forecast size.
loss (Literal['mse'] | ~typing.Literal['mae'] | ~typing.Literal['smape'] | ~typing.Literal['mape'] | torch.nn.Module) – Optimisation objective. The loss function should accept three arguments: y_true, y_pred and mask. The last parameter is a binary mask that denotes which points are valid forecasts. There are several implemented loss functions available in the etna.models.nn.nbeats.metrics module.
trend_blocks (int) – Number of trend blocks.
trend_layers (int) – Number of inner layers in each trend block.
trend_layer_size (int) – Inner layer size in trend blocks.
degree_of_polynomial (int) – Polynomial degree for trend modeling.
seasonality_blocks (int) – Number of seasonality blocks.
seasonality_layers (int) – Number of inner layers in each seasonality block.
seasonality_layer_size (int) – Inner layer size in seasonality blocks.
num_of_harmonics (int) – Number of harmonics for seasonality estimation.
lr (float) – Optimizer learning rate.
window_sampling_limit (int | None) – Size of history for sampling training data. If set to None full series history used for sampling.
optimizer_params (dict | None) – Additional parameters for the optimizer.
train_batch_size (int) – Batch size for training.
test_batch_size (int) – Batch size for testing.
optimizer_params – Parameters for optimizer for Adam optimizer (api reference torch.optim.Adam).
trainer_params (dict | None) – Pytorch lightning trainer parameters (api reference lightning.pytorch.trainer.trainer.Trainer).
train_dataloader_params (dict | None) – Parameters for train dataloader like sampler for example (api reference torch.utils.data.DataLoader).
test_dataloader_params (dict | None) – Parameters for test dataloader.
val_dataloader_params (dict | None) – Parameters for validation dataloader.
split_params (dict | None) –
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__
random_state (int | None) – Random state for train batches generation.

Methods

`fit`(ts)	Fit model.
`forecast`(ts, prediction_size[, ...])	Make predictions.
`get_model`()	Get model.
`load`(path[, ts])	Load an object.
`params_to_tune`()	Get default 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

This class stores its __init__ parameters as attributes.

context_size

Context size of the model.

fit(ts: TSDataset) → DeepBaseModel[source]#

Fit model.

Model continues training after each fit call.

Parameters:: ts (TSDataset) – TSDataset with features
Returns:: Model after fit
Return type:: DeepBaseModel

forecast(ts: TSDataset, prediction_size: int, return_components: bool = False) → TSDataset[source]#

Make predictions.

This method will make autoregressive predictions.

Parameters:

ts (TSDataset) – Dataset with features and expected decoder length for context
prediction_size (int) – Number of last timestamps to leave after making prediction. Previous timestamps will be used as a context.
return_components (bool) – If True additionally returns forecast components

Returns:

Dataset with predictions

Return type:

TSDataset

get_model() → DeepBaseNet[source]#

Get model.

Returns:: Torch Module
Return type:: DeepBaseNet

classmethod load(path: Path, ts: TSDataset | None = None) → Self[source]#

Load an object.

Warning

This method uses dill module which is not secure. It is possible to construct malicious data which will execute arbitrary code during loading. Never load data that could have come from an untrusted source, or that could have been tampered with.

Parameters:

path (Path) – Path to load object from.
ts (TSDataset | None) – TSDataset to set into loaded pipeline.

Returns:

Loaded object.

Return type:

Self

params_to_tune() → Dict[str, BaseDistribution][source]#

Get default grid for tuning hyperparameters.

This grid tunes parameters: trend_blocks, trend_layers, trend_layer_size, degree_of_polynomial, seasonality_blocks, seasonality_layers, seasonality_layer_size, lr. Other parameters are expected to be set by the user.

Returns:: Grid to tune.
Return type:: Dict[str, BaseDistribution]

predict(ts: TSDataset, prediction_size: int, return_components: bool = False) → TSDataset[source]#

Make predictions.

This method will make predictions using true values instead of predicted on a previous step. It can be useful for making in-sample forecasts.

Parameters:

ts (TSDataset) – Dataset with features and expected decoder length for context
prediction_size (int) – Number of last timestamps to leave after making prediction. Previous timestamps will be used as a context.
return_components (bool) – If True additionally returns prediction components

Returns:

Dataset with predictions

Return type:

TSDataset

raw_fit(torch_dataset: Dataset) → DeepBaseModel[source]#

Fit model on torch like Dataset.

Parameters:: torch_dataset (Dataset) – Torch like dataset for model fit
Returns:: Model after fit
Return type:: DeepBaseModel

raw_predict(torch_dataset: Dataset) → Dict[Tuple[str, str], ndarray][source]#

Make inference on torch like Dataset.

Parameters:: torch_dataset (Dataset) – Torch like dataset for model inference
Returns:: Dictionary with predictions
Return type:: Dict[Tuple[str, str], ndarray]

save(path: Path)[source]#

Save the object.

Parameters:: path (Path) – Path to save object to.

set_params(**params: dict) → Self[source]#

Return new object instance with modified parameters.

Method also allows to change parameters of nested objects within the current object. For example, it is possible to change parameters of a model in a Pipeline.

Nested parameters are expected to be in a <component_1>.<...>.<parameter> form, where components are separated by a dot.

Parameters:: **params (dict) – Estimator parameters
Returns:: New instance with changed parameters
Return type:: Self

Examples

>>> from etna.pipeline import Pipeline
>>> from etna.models import NaiveModel
>>> from etna.transforms import AddConstTransform
>>> model = NaiveModel(lag=1)
>>> transforms = [AddConstTransform(in_column="target", value=1)]
>>> pipeline = Pipeline(model, transforms=transforms, horizon=3)
>>> pipeline.set_params(**{"model.lag": 3, "transforms.0.value": 2})
Pipeline(model = NaiveModel(lag = 3, ), transforms = [AddConstTransform(in_column = 'target', value = 2, inplace = True, out_column = None, )], horizon = 3, )

to_dict()[source]#: Collect all information about etna object in dict.

property context_size: int[source]#: Context size of the model.