o yidG@sddlmZddlZddlmZddlmZddlmZmZm Z m Z m Z m Z m Z mZmZmZmZmZddlmZ d+ded ed ed ed eed deddefddZ    d,dededededdeededefddZ     d-dededed eedd ededdeededefd!d"Z     d.deded#eded eeddeddeededefd$d%Z    &    d/deded'ed(dedeed#eed eeddeedd eedeededefd)d*ZdS)0)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_divideglobaltpfptnfnaverage)binarymicromacroweightednonemultidim_average)r samplewisereturncCs|dkr t|||S|dkr.|j|dkrdndd}|j|dkr#dndd}t|||St|||}|dus=|dkr?|S|dkrH||}nt|}t|||jd d d d S) Nrrrr)dimrrT)keepdim)rsumtorch ones_like)rrrrrrspecificity_scoreweightsr)f/home/ubuntu/.local/lib/python3.10/site-packages/torchmetrics/functional/classification/specificity.py_specificity_reduce%s  r+?Tpredstarget threshold ignore_index validate_argsc CsX|rt|||t||||t||||\}}t|||\}}}} t|||| d|dS)aH Computes `Specificity`_ for binary tasks: .. math:: \text{Specificity} = \frac{\text{TN}}{\text{TN} + \text{FP}} Where :math:`\text{TN}` and :math:`\text{FP}` represent the number of true negatives and false positives respecitively. 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_specificity >>> target = torch.tensor([0, 1, 0, 1, 0, 1]) >>> preds = torch.tensor([0, 0, 1, 1, 0, 1]) >>> binary_specificity(preds, target) tensor(0.6667) Example (preds is float tensor): >>> from torchmetrics.functional.classification import binary_specificity >>> 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_specificity(preds, target) tensor(0.6667) Example (multidim tensors): >>> from torchmetrics.functional.classification import binary_specificity >>> 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_specificity(preds, target, multidim_average='samplewise') tensor([0.0000, 0.3333]) rrr)rrrrr+) r-r.r/rr0r1rrrrr)r)r*binary_specificity>s D r3rr num_classes)rrrrtop_kc Csd|rt|||||t|||||t|||\}}t|||||||\}} } } t|| | | ||dS)aComputes `Specificity`_ for multiclass tasks: .. math:: \text{Specificity} = \frac{\text{TN}}{\text{TN} + \text{FP}} Where :math:`\text{TN}` and :math:`\text{FP}` represent the number of true negatives and false positives respecitively. 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_specificity >>> target = torch.tensor([2, 1, 0, 0]) >>> preds = torch.tensor([2, 1, 0, 1]) >>> multiclass_specificity(preds, target, num_classes=3) tensor(0.8889) >>> multiclass_specificity(preds, target, num_classes=3, average=None) tensor([1.0000, 0.6667, 1.0000]) Example (preds is float tensor): >>> from torchmetrics.functional.classification import multiclass_specificity >>> 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_specificity(preds, target, num_classes=3) tensor(0.8889) >>> multiclass_specificity(preds, target, num_classes=3, average=None) tensor([1.0000, 0.6667, 1.0000]) Example (multidim tensors): >>> from torchmetrics.functional.classification import multiclass_specificity >>> 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_specificity(preds, target, num_classes=3, multidim_average='samplewise') tensor([0.7500, 0.6556]) >>> multiclass_specificity(preds, target, num_classes=3, multidim_average='samplewise', average=None) tensor([[0.7500, 0.7500, 0.7500], [0.8000, 0.6667, 0.5000]]) r2)r r r r r+) r-r.r4rr5rr0r1rrrrr)r)r*multiclass_specificitysa r6 num_labelsc Cs`|rt|||||t|||||t|||||\}}t|||\}} } } t|| | | ||dS)aTComputes `Specificity`_ for multilabel tasks. .. math:: \text{Specificity} = \frac{\text{TN}}{\text{TN} + \text{FP}} Where :math:`\text{TN}` and :math:`\text{FP}` represent the number of true negatives and false positives respecitively. 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_specificity >>> target = torch.tensor([[0, 1, 0], [1, 0, 1]]) >>> preds = torch.tensor([[0, 0, 1], [1, 0, 1]]) >>> multilabel_specificity(preds, target, num_labels=3) tensor(0.6667) >>> multilabel_specificity(preds, target, num_labels=3, average=None) tensor([1., 1., 0.]) Example (preds is float tensor): >>> from torchmetrics.functional.classification import multilabel_specificity >>> 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_specificity(preds, target, num_labels=3) tensor(0.6667) >>> multilabel_specificity(preds, target, num_labels=3, average=None) tensor([1., 1., 0.]) Example (multidim tensors): >>> from torchmetrics.functional.classification import multilabel_specificity >>> 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_specificity(preds, target, num_labels=3, multidim_average='samplewise') tensor([0.0000, 0.3333]) >>> multilabel_specificity(preds, target, num_labels=3, multidim_average='samplewise', average=None) tensor([[0., 0., 0.], [0., 0., 1.]]) r2)r rrrr+) r-r.r7r/rrr0r1rrrrr)r)r*multilabel_specificitys _r8rtask)r multiclass multilabelc Cs|dusJ|dkrt||||| | S|dkr0t|tsJt|ts%Jt||||||| | S|dkrFt|ts;Jt||||||| | Std|)aComputes `Specificity`_. .. math:: \text{Specificity} = \frac{\text{TN}}{\text{TN} + \text{FP}} Where :math:`\text{TN}` and :math:`\text{FP}` represent the number of true negatives and false positives respecitively. 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_specificity`, :func:`multiclass_specificity` and :func:`multilabel_specificity` for the specific details of each argument influence and examples. LegacyExample: >>> preds = torch.tensor([2, 0, 2, 1]) >>> target = torch.tensor([1, 1, 2, 0]) >>> specificity(preds, target, task="multiclass", average='macro', num_classes=3) tensor(0.6111) >>> specificity(preds, target, task="multiclass", average='micro', num_classes=3) tensor(0.6250) Nrr:r;z[Expected argument `task` to either be `'binary'`, `'multiclass'` or `'multilabel'` but got )r3 isinstanceintr6r8 ValueError) r-r.r9r/r4r7rrr5r0r1r)r)r* specificity\s" !r?)r)r,rNT)rr rNT)r,rrNT)r,NNrrr NT)typingrr%rtyping_extensionsr2torchmetrics.functional.classification.stat_scoresrrrrr r r r r rrrtorchmetrics.utilities.computerr+floatr=boolr3r6r8r?r)r)r)r*s   8     P  o  k