gluonts.nursery.few_shot_prediction.src.meta.data.dataset module

class gluonts.nursery.few_shot_prediction.src.meta.data.dataset.TimeSeries(dataset_name: str, start_date: Optional[pandas._libs.tslibs.timestamps.Timestamp], values: torch.Tensor, item_id: Optional[str] = None, feat_static_cat: Optional[torch.Tensor] = None, scale: Optional[torch.Tensor] = None)

Bases: object

A time series contains the time series data along with metadata about the time series as well as static and dynamic features.

dataset_name: str

property end_date: pandas._libs.tslibs.timestamps.Timestamp

feat_static_cat: Optional[torch.Tensor] = None

item_id: Optional[str] = None

property mean: torch.Tensor

scale: Optional[torch.Tensor] = None

standardize(m: torch.Tensor, std: torch.Tensor)

start_date: Optional[pandas._libs.tslibs.timestamps.Timestamp]

property std: torch.Tensor

values: torch.Tensor

class gluonts.nursery.few_shot_prediction.src.meta.data.dataset.TimeSeriesDataset(series: List[gluonts.nursery.few_shot_prediction.src.meta.data.dataset.TimeSeries], prediction_length: int, freq: str, standardize: bool = True)

Bases: torch.utils.data.dataset.Dataset[gluonts.nursery.few_shot_prediction.src.meta.data.dataset.TimeSeries]

A dataset which provides time series.

property number_of_time_steps

rescale_dataset(series: torch.Tensor)

Redo standardization. The series must contain the same time series in the same order as the dataset.