_TslibDataset#

class pytorch_forecasting.data._tslib_data_module._TslibDataset(dataset: TimeSeries, data_module: TslibDataModule, windows: list[tuple[int, int, int, int]], add_relative_time_idx: bool = False)[source]#

Bases: Dataset

Dataset class for tslib time series dataset.

Parameters:

  • dataset (TimeSeries) – The time series dataset to be used for training and validation.

  • data_module (TslibDataModule) – The data module that contains the metadata and other configurations for the dataset.

  • windows (list[tuple[int, int, int, int]]) –

    A list of tuples where each tuple contains:

    • series_idx: Index of time series in the dataset

    • start_idx: Start index of the window

    • context_length: Length of the context/encoder window

    • prediction_length: Length of the prediction/decoder window

  • add_relative_time_idx (bool) – Whether to add relative time index to the dataset.

Inherited-members: