pytorch_forecasting.utils.groupby_apply

pytorch_forecasting.utils.groupby_apply(keys: torch.Tensor, values: torch.Tensor, bins: int = 95, reduction: str = 'mean', return_histogram: bool = False) → Union[torch.Tensor, Tuple[torch.Tensor, torch.Tensor]][source]

Groupby apply for torch tensors

Parameters

  • keys – tensor of groups (0 to bins)

  • values – values to aggregate - same size as keys

  • bins – total number of groups

  • reduction – either “mean” or “sum”

  • return_histogram – if to return histogram on top

Returns

tensor of size bins with aggregated values and optionally with counts of values

pytorch_forecasting.utils.get_embedding_size pytorch_forecasting.utils.integer_histogram