§
    ’©ºjú  ã                   ó¼   — d dl mZ d dlmZmZmZmZ d dlZd dlmZm	Z	 d dl
mZ d dlmZ d dlmZmZ d dlmZmZ d d	lmZ d d
lmZmZ esdgZ G d„ de¦  «        ZdS )é    )ÚSequence)ÚAnyÚCallableÚOptionalÚUnionN)ÚTensorÚtensor)ÚLiteral)Úretrieval_fall_out)ÚRetrievalMetricÚ_retrieval_aggregate)Ú_flexible_bincountÚdim_zero_cat)Ú_MATPLOTLIB_AVAILABLE)Ú_AX_TYPEÚ_PLOT_OUT_TYPEzRetrievalFallOut.plotc                   ó.  ‡ — e Zd ZU dZdZeed<   dZeed<   dZeed<   dZ	e
ed<   dZe
ed	<   	 	 	 	 ddedee         dee         deed         ef         deddfˆ fd„Zdefd„Zdededefd„Z	 ddeeeee         f                  dee         defd„Zˆ xZS )ÚRetrievalFallOuta×
  Compute `Fall-out`_.

    Works with binary target data. Accepts float predictions from a model output.

    As input to ``forward`` and ``update`` the metric accepts the following input:

    - ``preds`` (:class:`~torch.Tensor`): A float tensor of shape ``(N, ...)``
    - ``target`` (:class:`~torch.Tensor`): A long or bool tensor of shape ``(N, ...)``
    - ``indexes`` (:class:`~torch.Tensor`): A long tensor of shape ``(N, ...)`` which indicate to which query a
      prediction belongs

    As output to ``forward`` and ``compute`` the metric returns the following output:

    - ``fallout@k`` (:class:`~torch.Tensor`): A tensor with the computed metric

    All ``indexes``, ``preds`` and ``target`` must have the same dimension and will be flatten at the beginning,
    so that for example, a tensor of shape ``(N, M)`` is treated as ``(N * M, )``. Predictions will be first grouped by
    ``indexes`` and then will be computed as the mean of the metric over each query.

    Args:
        empty_target_action:
            Specify what to do with queries that do not have at least a negative ``target``. Choose from:

            - ``'neg'``: those queries count as ``0.0`` (default)
            - ``'pos'``: those queries count as ``1.0``
            - ``'skip'``: skip those queries; if all queries are skipped, ``0.0`` is returned
            - ``'error'``: raise a ``ValueError``

        ignore_index: Ignore predictions where the target is equal to this number.
        top_k: Consider only the top k elements for each query (default: `None`, which considers them all)
        aggregation:
            Specify how to aggregate over indexes. Can either a custom callable function that takes in a single tensor
            and returns a scalar value or one of the following strings:

            - ``'mean'``: average value is returned
            - ``'median'``: median value is returned
            - ``'max'``: max value is returned
            - ``'min'``: min value is returned

        kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info.

    Raises:
        ValueError:
            If ``empty_target_action`` is not one of ``error``, ``skip``, ``neg`` or ``pos``.
        ValueError:
            If ``ignore_index`` is not `None` or an integer.
        ValueError:
            If ``top_k`` is not ``None`` or not an integer greater than 0.

    Example:
        >>> from torchmetrics.retrieval import RetrievalFallOut
        >>> indexes = tensor([0, 0, 0, 1, 1, 1, 1])
        >>> preds = tensor([0.2, 0.3, 0.5, 0.1, 0.3, 0.5, 0.2])
        >>> target = tensor([False, False, True, False, True, False, True])
        >>> rfo = RetrievalFallOut(top_k=2)
        >>> rfo(preds, target, indexes=indexes)
        tensor(0.5000)

    FÚis_differentiableÚhigher_is_betterÚfull_state_updateç        Úplot_lower_boundç      ð?Úplot_upper_boundÚposNÚmeanÚempty_target_actionÚignore_indexÚtop_kÚaggregation)r   ÚmedianÚminÚmaxÚkwargsÚreturnc                 ó¨   •—  t          ¦   «         j        d|||dœ|¤Ž |�*t          |t          ¦  «        r|dk    st	          d¦  «        ‚|| _        d S )N)r   r   r!   r   z,`top_k` has to be a positive integer or None© )ÚsuperÚ__init__Ú
isinstanceÚintÚ
ValueErrorr    )Úselfr   r   r    r!   r%   Ú	__class__s         €úo/root/private/project/pallet_detection_v2/.venv/lib/python3.11/site-packages/torchmetrics/retrieval/fall_out.pyr*   zRetrievalFallOut.__init__b   sv   ø€ ð 	�‰ŒÔð 	
Ø 3Ø%Ø#ð	
ð 	
ð ð		
ð 	
ð 	
ð Ð¥j°½Ñ&<Ô&<ÐÀÈÂÀÝÐKÑLÔLÐLØˆŒ
ˆ
ˆ
ó    c                 óô  ‡— t          | j        ¦  «        }t          | j        ¦  «        Št          | j        ¦  «        }t	          j        |¦  «        \  }}‰|         Š||         }t          |¦  «                             ¦   «                              ¦   «          	                    ¦   «         }g }t          t	          j        ‰|d¬¦  «        t	          j        ||d¬¦  «        ¦  «        D ]»\  }}d|z
                       ¦   «         sv| j        dk    rt          d¦  «        ‚| j        dk    r#|                     t!          d¦  «        ¦  «         Œd| j        dk    r"|                     t!          d	¦  «        ¦  «         Œ’|                     |                      ||¦  «        ¦  «         Œ¼|r4t%          t	          j        ˆfd
„|D ¦   «         ¦  «        | j        ¬¦  «        n!t!          d	¦  «                             ‰¦  «        S )a€  First concat state ``indexes``, ``preds`` and ``target`` since they were stored as lists.

        After that, compute list of groups that will help in keeping together predictions about the same query. Finally,
        for each group compute the `_metric` if the number of negative targets is at least 1, otherwise behave as
        specified by `self.empty_target_action`.

        r   )Údimé   ÚerrorzC`compute` method was provided with a query with no negative target.r   r   Únegr   c                 ó:   •— g | ]}|                      ‰¦  «        ‘ŒS r(   )Úto)Ú.0ÚxÚpredss     €r0   ú
<listcomp>z,RetrievalFallOut.compute.<locals>.<listcomp>—   s#   ø€ Ð-GÐ-GÐ-G¸a¨a¯dªd°5©k¬kÐ-GÐ-GÐ-Gr1   )r!   )r   Úindexesr;   ÚtargetÚtorchÚsortr   ÚdetachÚcpuÚtolistÚzipÚsplitÚsumr   r-   Úappendr	   Ú_metricr   Ústackr!   r8   )	r.   r=   r>   ÚindicesÚsplit_sizesÚresÚ
mini_predsÚmini_targetr;   s	           @r0   ÚcomputezRetrievalFallOut.computeu   sÝ  ø€ õ ˜tœ|Ñ,Ô,ˆÝ˜TœZÑ(Ô(ˆÝ˜dœkÑ*Ô*ˆå œ: gÑ.Ô.Ñˆ�Ø�g”ˆØ˜”ˆå(¨Ñ1Ô1×8Ò8Ñ:Ô:×>Ò>Ñ@Ô@×GÒGÑIÔIˆàˆÝ'*ÝŒK˜˜{°Ð2Ñ2Ô2µE´KÀÈÐYZÐ4[Ñ4[Ô4[ñ(
ô (
ð 	Bð 	BÑ#ˆJ˜ð ˜‘O×(Ò(Ñ*Ô*ð 	BØÔ+¨wÒ6Ð6Ý$Ð%jÑkÔkÐkØÔ+¨uÒ4Ð4Ø—J’J�v c™{œ{Ñ+Ô+Ð+Ð+ØÔ-°Ò6Ð6Ø—J’J�v c™{œ{Ñ+Ô+Ð+øð —
’
˜4Ÿ<š<¨
°KÑ@Ô@ÑAÔAÐAÐAð ð'Õ ¥¤Ð-GÐ-GÐ-GÐ-GÀ3Ð-GÑ-GÔ-GÑ!HÔ!HÐVZÔVfÐgÑgÔgÐgå˜‘”—’ Ñ&Ô&ð	
r1   r;   r>   c                 ó0   — t          ||| j        ¬¦  «        S )N)r    )r   r    )r.   r;   r>   s      r0   rH   zRetrievalFallOut._metricœ   s   € Ý! %¨°t´zÐBÑBÔBÐBr1   ÚvalÚaxc                 ó.   — |                       ||¦  «        S )a[  Plot a single or multiple values from the metric.

        Args:
            val: Either a single result from calling `metric.forward` or `metric.compute` or a list of these results.
                If no value is provided, will automatically call `metric.compute` and plot that result.
            ax: An matplotlib axis object. If provided will add plot to that axis

        Returns:
            Figure and Axes object

        Raises:
            ModuleNotFoundError:
                If `matplotlib` is not installed

        .. plot::
            :scale: 75

            >>> import torch
            >>> from torchmetrics.retrieval import RetrievalFallOut
            >>> # Example plotting a single value
            >>> metric = RetrievalFallOut()
            >>> metric.update(torch.rand(10,), torch.randint(2, (10,)), indexes=torch.randint(2,(10,)))
            >>> fig_, ax_ = metric.plot()

        .. plot::
            :scale: 75

            >>> import torch
            >>> from torchmetrics.retrieval import RetrievalFallOut
            >>> # Example plotting multiple values
            >>> metric = RetrievalFallOut()
            >>> values = []
            >>> for _ in range(10):
            ...     values.append(metric(torch.rand(10,), torch.randint(2, (10,)), indexes=torch.randint(2,(10,))))
            >>> fig, ax = metric.plot(values)

        )Ú_plot)r.   rQ   rR   s      r0   ÚplotzRetrievalFallOut.plotŸ   s   € ðP �zŠz˜#˜rÑ"Ô"Ð"r1   )r   NNr   )NN)Ú__name__Ú
__module__Ú__qualname__Ú__doc__r   ÚboolÚ__annotations__r   r   r   Úfloatr   Ústrr   r,   r   r
   r   r   r*   r   rO   rH   r   r   r   rU   Ú__classcell__)r/   s   @r0   r   r      s¤  ø€ € € € € € ð:ð :ðx $Ð�tÐ#Ð#Ñ#Ø"Ð�dÐ"Ð"Ñ"Ø#Ð�tÐ#Ð#Ñ#Ø!Ð�eÐ!Ð!Ñ!Ø!Ð�eÐ!Ð!Ñ!ð $)Ø&*Ø#ØPVðð à ðð ˜s”mðð ˜Œ}ð	ð
 ˜7Ð#AÔBÀHÐLÔMðð ðð 
ðð ð ð ð ð ð&%
˜ð %
ð %
ð %
ð %
ðNC˜Vð C¨Vð C¸ð Cð Cð Cð Cð _cð(#ð (#Ø˜E &¨(°6Ô*:Ð":Ô;Ô<ð(#ØIQÐRZÔI[ð(#à	ð(#ð (#ð (#ð (#ð (#ð (#ð (#ð (#r1   r   )Úcollections.abcr   Útypingr   r   r   r   r?   r   r	   Útyping_extensionsr
   Ú*torchmetrics.functional.retrieval.fall_outr   Útorchmetrics.retrieval.baser   r   Útorchmetrics.utilities.datar   r   Útorchmetrics.utilities.importsr   Útorchmetrics.utilities.plotr   r   Ú__doctest_skip__r   r(   r1   r0   ú<module>rh      s+  ðð %Ð $Ð $Ð $Ð $Ð $Ø 1Ð 1Ð 1Ð 1Ð 1Ð 1Ð 1Ð 1Ð 1Ð 1Ð 1Ð 1à €€€Ø  Ð  Ð  Ð  Ð  Ð  Ð  Ð  Ø %Ð %Ð %Ð %Ð %Ð %à IÐ IÐ IÐ IÐ IÐ IØ MÐ MÐ MÐ MÐ MÐ MÐ MÐ MØ HÐ HÐ HÐ HÐ HÐ HÐ HÐ HØ @Ð @Ð @Ð @Ð @Ð @Ø @Ð @Ð @Ð @Ð @Ð @Ð @Ð @àð 1Ø/Ð0Ððh#ð h#ð h#ð h#ð h#�ñ h#ô h#ð h#ð h#ð h#r1   