o
    yi4N                     @   s  d dl mZ d dlZd dlmZ d dlmZ d dlmZmZm	Z	m
Z
mZmZmZmZmZmZmZmZ d dlmZ 		d-d	ed
edededeed  ded dedefddZ				d.dedededed dee dedefddZ					d/deded edeed!  d"eded dee dedefd#d$Z					d0deded%ededeed!  ded dee dedefd&d'Z				(				d1deded)ed* ded ee d%ee deed!  deed  d"ee dee dedefd+d,ZdS )2    )OptionalN)Tensor)Literal)"_binary_stat_scores_arg_validation_binary_stat_scores_format%_binary_stat_scores_tensor_validation_binary_stat_scores_update&_multiclass_stat_scores_arg_validation_multiclass_stat_scores_format)_multiclass_stat_scores_tensor_validation_multiclass_stat_scores_update&_multilabel_stat_scores_arg_validation_multilabel_stat_scores_format)_multilabel_stat_scores_tensor_validation_multilabel_stat_scores_update)_safe_divideglobalFtpfptnfnaverage)binarymicromacroweightednonemultidim_average)r   
samplewise
multilabelreturnc           	      C   sF  |dkrdt | | | | | |  S |dkra| j|dkrdndd} |j|dkr+dndd}|rX|j|dkr9dndd}|j|dkrEdndd}dt | | | | | |  S dt | | |  S |rsdt | | | | | |  }n	dt | | |  }|du s|dkr|S |d	kr| | }nt|}t || |jd
ddd
S )ax  Reduce classification statistics into hamming distance
    Args:
        tp: number of true positives
        fp: number of false positives
        tn: number of true negatives
        fn: number of false negatives
        normalize: normalization method.

            - `"true"` will divide by the sum of the column dimension.
            - `"pred"` will divide by the sum of the row dimension.
            - `"all"` will divide by the sum of the full matrix
            - `"none"` or `None` will apply no reduction

        multilabel: bool indicating if reduction is for multilabel tasks

    Returns:
        Accuracy score
    r      r   r   r   )dimNr   r   T)keepdim)r   sumtorch	ones_like)	r   r   r   r   r   r   r   scoreweights r*   b/home/ubuntu/.local/lib/python3.10/site-packages/torchmetrics/functional/classification/hamming.py_hamming_distance_reduce%   s&    

r,         ?Tpredstarget	thresholdignore_indexvalidate_argsc           
      C   sX   |rt ||| t| ||| t| |||\} }t| ||\}}}}	t||||	d|dS )a  Computes the average `Hamming distance`_ (also known as Hamming loss) for binary tasks:

    .. math::
        \text{Hamming distance} = \frac{1}{N \cdot L} \sum_i^N \sum_l^L 1(y_{il} \neq \hat{y}_{il})

    Where :math:`y` is a tensor of target values, :math:`\hat{y}` is a tensor of predictions,
    and :math:`\bullet_{il}` refers to the :math:`l`-th label of the :math:`i`-th sample of that
    tensor.

    Accepts the following input tensors:

    - ``preds`` (int or float tensor): ``(N, ...)``. If preds is a floating point tensor with values outside
      [0,1] range we consider the input to be logits and will auto apply sigmoid per element. Addtionally,
      we convert to int tensor with thresholding using the value in ``threshold``.
    - ``target`` (int tensor): ``(N, ...)``

    Args:
        preds: Tensor with predictions
        target: Tensor with true labels
        threshold: Threshold for transforming probability to binary {0,1} predictions
        multidim_average:
            Defines how additionally dimensions ``...`` should be handled. Should be one of the following:

            - ``global``: Additional dimensions are flatted along the batch dimension
            - ``samplewise``: Statistic will be calculated independently for each sample on the ``N`` axis.
              The statistics in this case are calculated over the additional dimensions.

        ignore_index:
            Specifies a target value that is ignored and does not contribute to the metric calculation
        validate_args: bool indicating if input arguments and tensors should be validated for correctness.
            Set to ``False`` for faster computations.

    Returns:
        If ``multidim_average`` is set to ``global``, the metric returns a scalar value. If ``multidim_average``
        is set to ``samplewise``, the metric returns ``(N,)`` vector consisting of a scalar value per sample.

    Example (preds is int tensor):
        >>> from torchmetrics.functional.classification import binary_hamming_distance
        >>> target = torch.tensor([0, 1, 0, 1, 0, 1])
        >>> preds = torch.tensor([0, 0, 1, 1, 0, 1])
        >>> binary_hamming_distance(preds, target)
        tensor(0.3333)

    Example (preds is float tensor):
        >>> from torchmetrics.functional.classification import binary_hamming_distance
        >>> target = torch.tensor([0, 1, 0, 1, 0, 1])
        >>> preds = torch.tensor([0.11, 0.22, 0.84, 0.73, 0.33, 0.92])
        >>> binary_hamming_distance(preds, target)
        tensor(0.3333)

    Example (multidim tensors):
        >>> from torchmetrics.functional.classification import binary_hamming_distance
        >>> target = torch.tensor([[[0, 1], [1, 0], [0, 1]], [[1, 1], [0, 0], [1, 0]]])
        >>> preds = torch.tensor(
        ...     [
        ...         [[0.59, 0.91], [0.91, 0.99], [0.63, 0.04]],
        ...         [[0.38, 0.04], [0.86, 0.780], [0.45, 0.37]],
        ...     ]
        ... )
        >>> binary_hamming_distance(preds, target, multidim_average='samplewise')
        tensor([0.6667, 0.8333])
    r   r   r   )r   r   r   r   r,   )
r.   r/   r0   r   r1   r2   r   r   r   r   r*   r*   r+   binary_hamming_distanceX   s   Fr4   r   r!   num_classes)r   r   r   r   top_kc                 C   sd   |rt ||||| t| |||| t| ||\} }t| ||||||\}}	}
}t||	|
|||dS )aO  Computes the average `Hamming distance`_ (also known as Hamming loss) for multiclass tasks:

    .. math::
        \text{Hamming distance} = \frac{1}{N \cdot L} \sum_i^N \sum_l^L 1(y_{il} \neq \hat{y}_{il})

    Where :math:`y` is a tensor of target values, :math:`\hat{y}` is a tensor of predictions,
    and :math:`\bullet_{il}` refers to the :math:`l`-th label of the :math:`i`-th sample of that
    tensor.

    Accepts the following input tensors:

    - ``preds``: ``(N, ...)`` (int tensor) or ``(N, C, ..)`` (float tensor). If preds is a floating point
      we apply ``torch.argmax`` along the ``C`` dimension to automatically convert probabilities/logits into
      an int tensor.
    - ``target`` (int tensor): ``(N, ...)``

    Args:
        preds: Tensor with predictions
        target: Tensor with true labels
        num_classes: Integer specifing the number of classes
        average:
            Defines the reduction that is applied over labels. Should be one of the following:

            - ``micro``: Sum statistics over all labels
            - ``macro``: Calculate statistics for each label and average them
            - ``weighted``: Calculates statistics for each label and computes weighted average using their support
            - ``"none"`` or ``None``: Calculates statistic for each label and applies no reduction

        top_k:
            Number of highest probability or logit score predictions considered to find the correct label.
            Only works when ``preds`` contain probabilities/logits.
        multidim_average:
            Defines how additionally dimensions ``...`` should be handled. Should be one of the following:

            - ``global``: Additional dimensions are flatted along the batch dimension
            - ``samplewise``: Statistic will be calculated independently for each sample on the ``N`` axis.
              The statistics in this case are calculated over the additional dimensions.

        ignore_index:
            Specifies a target value that is ignored and does not contribute to the metric calculation
        validate_args: bool indicating if input arguments and tensors should be validated for correctness.
            Set to ``False`` for faster computations.

    Returns:
        The returned shape depends on the ``average`` and ``multidim_average`` arguments:

        - If ``multidim_average`` is set to ``global``:

          - If ``average='micro'/'macro'/'weighted'``, the output will be a scalar tensor
          - If ``average=None/'none'``, the shape will be ``(C,)``

        - If ``multidim_average`` is set to ``samplewise``:

          - If ``average='micro'/'macro'/'weighted'``, the shape will be ``(N,)``
          - If ``average=None/'none'``, the shape will be ``(N, C)``

    Example (preds is int tensor):
        >>> from torchmetrics.functional.classification import multiclass_hamming_distance
        >>> target = torch.tensor([2, 1, 0, 0])
        >>> preds = torch.tensor([2, 1, 0, 1])
        >>> multiclass_hamming_distance(preds, target, num_classes=3)
        tensor(0.1667)
        >>> multiclass_hamming_distance(preds, target, num_classes=3, average=None)
        tensor([0.5000, 0.0000, 0.0000])

    Example (preds is float tensor):
        >>> from torchmetrics.functional.classification import multiclass_hamming_distance
        >>> target = torch.tensor([2, 1, 0, 0])
        >>> preds = torch.tensor([
        ...   [0.16, 0.26, 0.58],
        ...   [0.22, 0.61, 0.17],
        ...   [0.71, 0.09, 0.20],
        ...   [0.05, 0.82, 0.13],
        ... ])
        >>> multiclass_hamming_distance(preds, target, num_classes=3)
        tensor(0.1667)
        >>> multiclass_hamming_distance(preds, target, num_classes=3, average=None)
        tensor([0.5000, 0.0000, 0.0000])

    Example (multidim tensors):
        >>> from torchmetrics.functional.classification import multiclass_hamming_distance
        >>> target = torch.tensor([[[0, 1], [2, 1], [0, 2]], [[1, 1], [2, 0], [1, 2]]])
        >>> preds = torch.tensor([[[0, 2], [2, 0], [0, 1]], [[2, 2], [2, 1], [1, 0]]])
        >>> multiclass_hamming_distance(preds, target, num_classes=3, multidim_average='samplewise')
        tensor([0.5000, 0.7222])
        >>> multiclass_hamming_distance(preds, target, num_classes=3, multidim_average='samplewise', average=None)
        tensor([[0.0000, 1.0000, 0.5000],
                [1.0000, 0.6667, 0.5000]])
    r3   )r	   r   r
   r   r,   )r.   r/   r5   r   r6   r   r1   r2   r   r   r   r   r*   r*   r+   multiclass_hamming_distance   s   cr7   
num_labelsc              	   C   sb   |rt ||||| t| |||| t| ||||\} }t| ||\}}	}
}t||	|
|||ddS )aQ  Computes the average `Hamming distance`_ (also known as Hamming loss) for multilabel tasks:

    .. math::
        \text{Hamming distance} = \frac{1}{N \cdot L} \sum_i^N \sum_l^L 1(y_{il} \neq \hat{y}_{il})

    Where :math:`y` is a tensor of target values, :math:`\hat{y}` is a tensor of predictions,
    and :math:`\bullet_{il}` refers to the :math:`l`-th label of the :math:`i`-th sample of that
    tensor.

    Accepts the following input tensors:

    - ``preds`` (int or float tensor): ``(N, C, ...)``. If preds is a floating point tensor with values outside
      [0,1] range we consider the input to be logits and will auto apply sigmoid per element. Addtionally,
      we convert to int tensor with thresholding using the value in ``threshold``.
    - ``target`` (int tensor): ``(N, C, ...)``

    Args:
        preds: Tensor with predictions
        target: Tensor with true labels
        num_labels: Integer specifing the number of labels
        threshold: Threshold for transforming probability to binary (0,1) predictions
        average:
            Defines the reduction that is applied over labels. Should be one of the following:

            - ``micro``: Sum statistics over all labels
            - ``macro``: Calculate statistics for each label and average them
            - ``weighted``: Calculates statistics for each label and computes weighted average using their support
            - ``"none"`` or ``None``: Calculates statistic for each label and applies no reduction

        multidim_average:
            Defines how additionally dimensions ``...`` should be handled. Should be one of the following:

            - ``global``: Additional dimensions are flatted along the batch dimension
            - ``samplewise``: Statistic will be calculated independently for each sample on the ``N`` axis.
              The statistics in this case are calculated over the additional dimensions.

        ignore_index:
            Specifies a target value that is ignored and does not contribute to the metric calculation
        validate_args: bool indicating if input arguments and tensors should be validated for correctness.
            Set to ``False`` for faster computations.

    Returns:
        The returned shape depends on the ``average`` and ``multidim_average`` arguments:

        - If ``multidim_average`` is set to ``global``:

          - If ``average='micro'/'macro'/'weighted'``, the output will be a scalar tensor
          - If ``average=None/'none'``, the shape will be ``(C,)``

        - If ``multidim_average`` is set to ``samplewise``:

          - If ``average='micro'/'macro'/'weighted'``, the shape will be ``(N,)``
          - If ``average=None/'none'``, the shape will be ``(N, C)``

    Example (preds is int tensor):
        >>> from torchmetrics.functional.classification import multilabel_hamming_distance
        >>> target = torch.tensor([[0, 1, 0], [1, 0, 1]])
        >>> preds = torch.tensor([[0, 0, 1], [1, 0, 1]])
        >>> multilabel_hamming_distance(preds, target, num_labels=3)
        tensor(0.3333)
        >>> multilabel_hamming_distance(preds, target, num_labels=3, average=None)
        tensor([0.0000, 0.5000, 0.5000])

    Example (preds is float tensor):
        >>> from torchmetrics.functional.classification import multilabel_hamming_distance
        >>> target = torch.tensor([[0, 1, 0], [1, 0, 1]])
        >>> preds = torch.tensor([[0.11, 0.22, 0.84], [0.73, 0.33, 0.92]])
        >>> multilabel_hamming_distance(preds, target, num_labels=3)
        tensor(0.3333)
        >>> multilabel_hamming_distance(preds, target, num_labels=3, average=None)
        tensor([0.0000, 0.5000, 0.5000])

    Example (multidim tensors):
        >>> from torchmetrics.functional.classification import multilabel_hamming_distance
        >>> target = torch.tensor([[[0, 1], [1, 0], [0, 1]], [[1, 1], [0, 0], [1, 0]]])
        >>> preds = torch.tensor(
        ...     [
        ...         [[0.59, 0.91], [0.91, 0.99], [0.63, 0.04]],
        ...         [[0.38, 0.04], [0.86, 0.780], [0.45, 0.37]],
        ...     ]
        ... )
        >>> multilabel_hamming_distance(preds, target, num_labels=3, multidim_average='samplewise')
        tensor([0.6667, 0.8333])
        >>> multilabel_hamming_distance(preds, target, num_labels=3, multidim_average='samplewise', average=None)
        tensor([[0.5000, 0.5000, 1.0000],
                [1.0000, 1.0000, 0.5000]])
    T)r   r   r   )r   r   r   r   r,   )r.   r/   r8   r0   r   r   r1   r2   r   r   r   r   r*   r*   r+   multilabel_hamming_distance  s   ar9   r   task)r   
multiclassr   c              	   C   s   |dusJ |dkrt | ||||	|
S |dkr0t|tsJ t|ts%J t| ||||||	|
S |dkrFt|ts;J t| ||||||	|
S td| )a  Computes the average `Hamming distance`_ (also known as Hamming loss):

    .. math::
        \text{Hamming distance} = \frac{1}{N \cdot L} \sum_i^N \sum_l^L 1(y_{il} \neq \hat{y}_{il})

    Where :math:`y` is a tensor of target values, :math:`\hat{y}` is a tensor of predictions,
    and :math:`\bullet_{il}` refers to the :math:`l`-th label of the :math:`i`-th sample of that
    tensor.

    This function is a simple wrapper to get the task specific versions of this metric, which is done by setting the
    ``task`` argument to either ``'binary'``, ``'multiclass'`` or ``multilabel``. See the documentation of
    :func:`binary_hamming_distance`, :func:`multiclass_hamming_distance` and :func:`multilabel_hamming_distance` for
    the specific details of each argument influence and examples.

    Legacy Example:
        >>> target = torch.tensor([[0, 1], [1, 1]])
        >>> preds = torch.tensor([[0, 1], [0, 1]])
        >>> hamming_distance(preds, target, task="binary")
        tensor(0.2500)
    Nr   r;   r   z[Expected argument `task` to either be `'binary'`, `'multiclass'` or `'multilabel'` but got )r4   
isinstanceintr7   r9   
ValueError)r.   r/   r:   r0   r5   r8   r   r   r6   r1   r2   r*   r*   r+   hamming_distance|  s"   !r?   )r   F)r-   r   NT)r   r!   r   NT)r-   r   r   NT)r-   NNr   r   r!   NT)typingr   r&   r   typing_extensionsr   2torchmetrics.functional.classification.stat_scoresr   r   r   r   r	   r
   r   r   r   r   r   r   torchmetrics.utilities.computer   boolr,   floatr=   r4   r7   r9   r?   r*   r*   r*   r+   <module>   s   8	

6
R
	
q
	
m

	
