§
    ’©ºjÏ  ã                   ó–   — d dl mZ d dlZd dlmZ d dlmZ 	 ddededed	eeef         fd
„Z	dedeeef         d	efd„Z
deded	efd„ZdS )é    )ÚUnionN)ÚTensor)Ú_check_same_shapeç-`Àš¡³>ÚpredsÚtargetÚepsilonÚreturnc                 óþ   — t          | |¦  «         t          j        | |z
  ¦  «        }|t          j        t          j        |¦  «        |¬¦  «        z  }t          j        |¦  «        }|                     ¦   «         }||fS )ac  Update and returns variables required to compute Mean Percentage Error.

    Check for same shape of input tensors.

    Args:
        preds: Predicted tensor
        target: Ground truth tensor
        epsilon: Specifies the lower bound for target values. Any target value below epsilon
            is set to epsilon (avoids ``ZeroDivisionError``).

    )Úmin)r   ÚtorchÚabsÚclampÚsumÚnumel)r   r   r	   Úabs_diffÚabs_per_errorÚsum_abs_per_errorÚnum_obss          úw/root/private/project/pallet_detection_v2/.venv/lib/python3.11/site-packages/torchmetrics/functional/regression/mape.pyÚ&_mean_absolute_percentage_error_updater      sr   € õ  �e˜VÑ$Ô$Ð$åŒy˜ ™Ñ(Ô(€HØ�uœ{­5¬9°VÑ+<Ô+<À'ÐJÑJÔJÑJ€Måœ	 -Ñ0Ô0Ðà�lŠl‰nŒn€Gà˜gÐ%Ð%ó    r   r   c                 ó   — | |z  S )aF  Compute Mean Absolute Percentage Error.

    Args:
        sum_abs_per_error: Sum of absolute value of percentage errors over all observations
            ``(percentage error = (target - prediction) / target)``
        num_obs: Number of predictions or observations

    Example:
        >>> target = torch.tensor([1, 10, 1e6])
        >>> preds = torch.tensor([0.9, 15, 1.2e6])
        >>> sum_abs_per_error, num_obs = _mean_absolute_percentage_error_update(preds, target)
        >>> _mean_absolute_percentage_error_compute(sum_abs_per_error, num_obs)
        tensor(0.2667)

    © )r   r   s     r   Ú'_mean_absolute_percentage_error_computer   2   s   € ð  ˜wÑ&Ð&r   c                 óH   — t          | |¦  «        \  }}t          ||¦  «        S )a  Compute mean absolute percentage error.

    Args:
        preds: estimated labels
        target: ground truth labels

    Return:
        Tensor with MAPE

    Note:
        The epsilon value is taken from `scikit-learn's implementation of MAPE`_.

    Example:
        >>> from torchmetrics.functional.regression import mean_absolute_percentage_error
        >>> target = torch.tensor([1, 10, 1e6])
        >>> preds = torch.tensor([0.9, 15, 1.2e6])
        >>> mean_absolute_percentage_error(preds, target)
        tensor(0.2667)

    )r   r   )r   r   r   r   s       r   Úmean_absolute_percentage_errorr   E   s+   € õ* "HÈÈvÑ!VÔ!VÑÐ�wÝ2Ð3DÀgÑNÔNÐNr   )r   )Útypingr   r   r   Útorchmetrics.utilities.checksr   ÚfloatÚtupleÚintr   r   r   r   r   r   ú<module>r#      s  ðð Ð Ð Ð Ð Ð à €€€Ø Ð Ð Ð Ð Ð à ;Ð ;Ð ;Ð ;Ð ;Ð ;ð ð&ð &Øð&àð&ð ð&ð ˆ6�3ˆ;Ôð	&ð &ð &ð &ð8'¸vð 'ÐPUÐVYÐ[aÐVaÔPbð 'Ðgmð 'ð 'ð 'ð 'ð&O¨&ð O¸&ð OÀVð Oð Oð Oð Oð Oð Or   