etna.models.nn.PytorchForecastingDatasetBuilder

class PytorchForecastingDatasetBuilder(max_encoder_length: int = 30, min_encoder_length: int | None = None, min_prediction_idx: int | None = None, min_prediction_length: int | None = None, max_prediction_length: int = 1, static_categoricals: List[str] | None = None, static_reals: List[str] | None = None, time_varying_known_categoricals: List[str] | None = None, time_varying_known_reals: List[str] | None = None, time_varying_unknown_categoricals: List[str] | None = None, time_varying_unknown_reals: List[str] | None = None, variable_groups: Dict[str, List[int]] | None = None, constant_fill_strategy: Dict[str, str | float | int | bool] | None = None, allow_missing_timesteps: bool = True, lags: Dict[str, List[int]] | None = None, add_relative_time_idx: bool = True, add_target_scales: bool = True, add_encoder_length: bool | str = True, target_normalizer: TorchNormalizer | NaNLabelEncoder | EncoderNormalizer | str | List[TorchNormalizer | NaNLabelEncoder | EncoderNormalizer] | Tuple[TorchNormalizer | NaNLabelEncoder | EncoderNormalizer] = 'auto', categorical_encoders: Dict[str, NaNLabelEncoder] | None = None, scalers: Dict[str, StandardScaler | RobustScaler | TorchNormalizer | EncoderNormalizer] | None = None)

Bases: BaseMixin

Builder for PytorchForecasting dataset.

Note

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

Init dataset builder.

Parameters here is used for initialization of pytorch_forecasting.data.timeseries.TimeSeriesDataSet object.

Methods

create_inference_dataset(ts, horizon)	Create inference dataset.
create_train_dataset(ts)	Create train dataset.
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.

Parameters:

• max_encoder_length (int) –

• min_encoder_length (int | None) –

• min_prediction_idx (int | None) –

• min_prediction_length (int | None) –

• max_prediction_length (int) –

• static_categoricals (List[str] | None) –

• static_reals (List[str] | None) –

• time_varying_known_categoricals (List[str] | None) –

• time_varying_known_reals (List[str] | None) –

• time_varying_unknown_categoricals (List[str] | None) –

• time_varying_unknown_reals (List[str] | None) –

• variable_groups (Dict[str, List[int]] | None) –

• constant_fill_strategy (Dict[str, str | float | int | bool] | None) –

• allow_missing_timesteps (bool) –

• lags (Dict[str, List[int]] | None) –

• add_relative_time_idx (bool) –

• add_target_scales (bool) –

• add_encoder_length (bool | str) –

• target_normalizer (TorchNormalizer | NaNLabelEncoder | EncoderNormalizer | str | List[TorchNormalizer | NaNLabelEncoder | EncoderNormalizer] | Tuple[TorchNormalizer | NaNLabelEncoder | EncoderNormalizer]) –

• categorical_encoders (Dict[str, NaNLabelEncoder] | None) –

• scalers (Dict[str, StandardScaler | RobustScaler | TorchNormalizer | EncoderNormalizer] | None) –

create_inference_dataset(ts: TSDataset, horizon: int) → TimeSeriesDataSet

Create inference dataset.

This method should be used only after create_train_dataset that is used during model training.

Parameters:

• ts (TSDataset) – Time series dataset.

• horizon (int) – Size of prediction to make.

Raises:

ValueError: – if method was used before create_train_dataset

Return type:

TimeSeriesDataSet

create_train_dataset(ts: TSDataset) → TimeSeriesDataSet

Create train dataset.

Parameters:

ts (TSDataset) – Time series dataset.

Return type:

TimeSeriesDataSet

set_params(**params: dict) → Self

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()

Collect all information about etna object in dict.