o .wic@sddlmZddlmZmZmZddlmZddlm Z ddl m Z ddl m Z mZmZddlmZmZmZmZmZmZddlmZdd lmZdd lmZdd lmZdd lm Z m!Z!esbgd Z"Gddde Z#GdddeZ$GdddeZ%Gddde Z&dS))Sequence)AnyOptionalUnion)Tensor)Literal)_ClassificationTaskWrapper)BinaryPrecisionRecallCurveMulticlassPrecisionRecallCurveMultilabelPrecisionRecallCurve)_binary_auroc_arg_validation_binary_auroc_compute _multiclass_auroc_arg_validation_multiclass_auroc_compute _multilabel_auroc_arg_validation_multilabel_auroc_compute)Metric) dim_zero_cat)ClassificationTask)_MATPLOTLIB_AVAILABLE)_AX_TYPE_PLOT_OUT_TYPE)BinaryAUROC.plotMulticlassAUROC.plotMultilabelAUROC.plotc seZdZUdZdZeed<dZeed<dZeed<dZ e ed<d Z e ed < dd e e d e e eee efde edededd f fdd ZdefddZ dde e eeefde edefddZZS) BinaryAUROCa] Compute Area Under the Receiver Operating Characteristic Curve (`ROC AUC`_) for binary tasks. The AUROC score summarizes the ROC curve into an single number that describes the performance of a model for multiple thresholds at the same time. Notably, an AUROC score of 1 is a perfect score and an AUROC score of 0.5 corresponds to random guessing. As input to ``forward`` and ``update`` the metric accepts the following input: - ``preds`` (:class:`~torch.Tensor`): A float tensor of shape ``(N, ...)`` containing probabilities or logits for each observation. If preds has values outside [0,1] range we consider the input to be logits and will auto apply sigmoid per element. - ``target`` (:class:`~torch.Tensor`): An int tensor of shape ``(N, ...)`` containing ground truth labels, and therefore only contain {0,1} values (except if `ignore_index` is specified). The value 1 always encodes the positive class. As output to ``forward`` and ``compute`` the metric returns the following output: - ``b_auroc`` (:class:`~torch.Tensor`): A single scalar with the auroc score. Additional dimension ``...`` will be flattened into the batch dimension. The implementation both supports calculating the metric in a non-binned but accurate version and a binned version that is less accurate but more memory efficient. Setting the `thresholds` argument to `None` will activate the non-binned version that uses memory of size :math:`\mathcal{O}(n_{samples})` whereas setting the `thresholds` argument to either an integer, list or a 1d tensor will use a binned version that uses memory of size :math:`\mathcal{O}(n_{thresholds})` (constant memory). Args: max_fpr: If not ``None``, calculates standardized partial AUC over the range ``[0, max_fpr]``. thresholds: Can be one of: - If set to `None`, will use a non-binned approach where thresholds are dynamically calculated from all the data. Most accurate but also most memory consuming approach. - If set to an `int` (larger than 1), will use that number of thresholds linearly spaced from 0 to 1 as bins for the calculation. - If set to an `list` of floats, will use the indicated thresholds in the list as bins for the calculation - If set to an 1d `tensor` of floats, will use the indicated thresholds in the tensor as bins for the calculation. validate_args: bool indicating if input arguments and tensors should be validated for correctness. Set to ``False`` for faster computations. kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info. Example: >>> from torch import tensor >>> from torchmetrics.classification import BinaryAUROC >>> preds = tensor([0, 0.5, 0.7, 0.8]) >>> target = tensor([0, 1, 1, 0]) >>> metric = BinaryAUROC(thresholds=None) >>> metric(preds, target) tensor(0.5000) >>> b_auroc = BinaryAUROC(thresholds=5) >>> b_auroc(preds, target) tensor(0.5000) Fis_differentiableThigher_is_betterfull_state_updateplot_lower_bound?plot_upper_boundNmax_fpr thresholds ignore_index validate_argskwargsreturnc s4tjd||dd||rt|||||_dS)NFr$r%r&)super__init__r r#)selfr#r$r%r&r' __class__r*^/home/ubuntu/sommelier/.venv/lib/python3.10/site-packages/torchmetrics/classification/auroc.pyr,ms  zBinaryAUROC.__init__cCs4|jdurt|jt|jfn|j}t||j|jSCompute metric.N)r$rpredstargetconfmatr r#r-stater*r*r0computezs$zBinaryAUROC.computevalaxcC |||S)aPlot 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 >>> # Example plotting a single >>> import torch >>> from torchmetrics.classification import BinaryAUROC >>> metric = BinaryAUROC() >>> metric.update(torch.rand(20,), torch.randint(2, (20,))) >>> fig_, ax_ = metric.plot() .. plot:: :scale: 75 >>> # Example plotting multiple values >>> import torch >>> from torchmetrics.classification import BinaryAUROC >>> metric = BinaryAUROC() >>> values = [ ] >>> for _ in range(10): ... values.append(metric(torch.rand(20,), torch.randint(2, (20,)))) >>> fig_, ax_ = metric.plot(values) _plotr-r9r:r*r*r0plot (r)NNNTNN)__name__ __module__ __qualname____doc__rbool__annotations__rrr floatr"rrintlistrrr,r8rrrr? __classcell__r*r*r.r0r,sB  :     rceZdZUdZdZeed<dZeed<dZeed<dZ e ed<d Z e ed <d Z e ed <   ddedeeddeeeee efdeedededdffdd ZdefddZ d deeeeefdeedefddZZS)!MulticlassAUROCaGCompute Area Under the Receiver Operating Characteristic Curve (`ROC AUC`_) for multiclass tasks. The AUROC score summarizes the ROC curve into an single number that describes the performance of a model for multiple thresholds at the same time. Notably, an AUROC score of 1 is a perfect score and an AUROC score of 0.5 corresponds to random guessing. For multiclass the metric is calculated by iteratively treating each class as the positive class and all other classes as the negative, which is referred to as the one-vs-rest approach. One-vs-one is currently not supported by this metric. By default the reported metric is then the average over all classes, but this behavior can be changed by setting the ``average`` argument. As input to ``forward`` and ``update`` the metric accepts the following input: - ``preds`` (:class:`~torch.Tensor`): A float tensor of shape ``(N, C, ...)`` containing probabilities or logits for each observation. If preds has values outside [0,1] range we consider the input to be logits and will auto apply softmax per sample. - ``target`` (:class:`~torch.Tensor`): An int tensor of shape ``(N, ...)`` containing ground truth labels, and therefore only contain values in the [0, n_classes-1] range (except if `ignore_index` is specified). As output to ``forward`` and ``compute`` the metric returns the following output: - ``mc_auroc`` (:class:`~torch.Tensor`): If `average=None|"none"` then a 1d tensor of shape (n_classes, ) will be returned with auroc score per class. If `average="macro"|"weighted"` then a single scalar is returned. Additional dimension ``...`` will be flattened into the batch dimension. The implementation both supports calculating the metric in a non-binned but accurate version and a binned version that is less accurate but more memory efficient. Setting the `thresholds` argument to `None` will activate the non-binned version that uses memory of size :math:`\mathcal{O}(n_{samples})` whereas setting the `thresholds` argument to either an integer, list or a 1d tensor will use a binned version that uses memory of size :math:`\mathcal{O}(n_{thresholds} \times n_{classes})` (constant memory). Args: num_classes: Integer specifying the number of classes average: Defines the reduction that is applied over classes. Should be one of the following: - ``macro``: Calculate score for each class and average them - ``weighted``: calculates score for each class and computes weighted average using their support - ``"none"`` or ``None``: calculates score for each class and applies no reduction thresholds: Can be one of: - If set to `None`, will use a non-binned approach where thresholds are dynamically calculated from all the data. Most accurate but also most memory consuming approach. - If set to an `int` (larger than 1), will use that number of thresholds linearly spaced from 0 to 1 as bins for the calculation. - If set to an `list` of floats, will use the indicated thresholds in the list as bins for the calculation - If set to an 1d `tensor` of floats, will use the indicated thresholds in the tensor as bins for the calculation. validate_args: bool indicating if input arguments and tensors should be validated for correctness. Set to ``False`` for faster computations. kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info. Example: >>> from torch import tensor >>> from torchmetrics.classification import MulticlassAUROC >>> preds = tensor([[0.75, 0.05, 0.05, 0.05, 0.05], ... [0.05, 0.75, 0.05, 0.05, 0.05], ... [0.05, 0.05, 0.75, 0.05, 0.05], ... [0.05, 0.05, 0.05, 0.75, 0.05]]) >>> target = tensor([0, 1, 3, 2]) >>> metric = MulticlassAUROC(num_classes=5, average="macro", thresholds=None) >>> metric(preds, target) tensor(0.5333) >>> mc_auroc = MulticlassAUROC(num_classes=5, average=None, thresholds=None) >>> mc_auroc(preds, target) tensor([1.0000, 1.0000, 0.3333, 0.3333, 0.0000]) >>> mc_auroc = MulticlassAUROC(num_classes=5, average="macro", thresholds=5) >>> mc_auroc(preds, target) tensor(0.5333) >>> mc_auroc = MulticlassAUROC(num_classes=5, average=None, thresholds=5) >>> mc_auroc(preds, target) tensor([1.0000, 1.0000, 0.3333, 0.3333, 0.0000]) FrTrrrr r!r"Classplot_legend_namemacroN num_classesaveragerPweightednoner$r%r&r'r(c >tjd|||dd||rt||||||_||_dS)NF)rQr$r%r&r*)r+r,rrRr&)r-rQrRr$r%r&r'r.r*r0r,  zMulticlassAUROC.__init__cCs8|jdurt|jt|jfn|j}t||j|j|jSr1)r$rr3r4r5rrQrRr6r*r*r0r8s$zMulticlassAUROC.computer9r:cCr;)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 >>> # Example plotting a single >>> import torch >>> from torchmetrics.classification import MulticlassAUROC >>> metric = MulticlassAUROC(num_classes=3) >>> metric.update(torch.randn(20, 3), torch.randint(3,(20,))) >>> fig_, ax_ = metric.plot() .. plot:: :scale: 75 >>> # Example plotting multiple values >>> import torch >>> from torchmetrics.classification import MulticlassAUROC >>> metric = MulticlassAUROC(num_classes=3) >>> values = [ ] >>> for _ in range(10): ... values.append(metric(torch.randn(20, 3), torch.randint(3, (20,)))) >>> fig_, ax_ = metric.plot(values) r<r>r*r*r0r?r@rrPNNTrArBrCrDrErrFrGrrr rHr"rOstrrIrrrrJrrr,r8rrrr?rKr*r*r.r0rMsH  O       rMcrL)!MultilabelAUROCa&Compute Area Under the Receiver Operating Characteristic Curve (`ROC AUC`_) for multilabel tasks. The AUROC score summarizes the ROC curve into an single number that describes the performance of a model for multiple thresholds at the same time. Notably, an AUROC score of 1 is a perfect score and an AUROC score of 0.5 corresponds to random guessing. As input to ``forward`` and ``update`` the metric accepts the following input: - ``preds`` (:class:`~torch.Tensor`): A float tensor of shape ``(N, C, ...)`` containing probabilities or logits for each observation. If preds has values outside [0,1] range we consider the input to be logits and will auto apply sigmoid per element. - ``target`` (:class:`~torch.Tensor`): An int tensor of shape ``(N, C, ...)`` containing ground truth labels, and therefore only contain {0,1} values (except if `ignore_index` is specified). As output to ``forward`` and ``compute`` the metric returns the following output: - ``ml_auroc`` (:class:`~torch.Tensor`): If `average=None|"none"` then a 1d tensor of shape (n_classes, ) will be returned with auroc score per class. If `average="micro|macro"|"weighted"` then a single scalar is returned. Additional dimension ``...`` will be flattened into the batch dimension. The implementation both supports calculating the metric in a non-binned but accurate version and a binned version that is less accurate but more memory efficient. Setting the `thresholds` argument to `None` will activate the non-binned version that uses memory of size :math:`\mathcal{O}(n_{samples})` whereas setting the `thresholds` argument to either an integer, list or a 1d tensor will use a binned version that uses memory of size :math:`\mathcal{O}(n_{thresholds} \times n_{labels})` (constant memory). Args: num_labels: Integer specifying the number of labels average: Defines the reduction that is applied over labels. Should be one of the following: - ``micro``: Sum score over all labels - ``macro``: Calculate score for each label and average them - ``weighted``: calculates score for each label and computes weighted average using their support - ``"none"`` or ``None``: calculates score for each label and applies no reduction thresholds: Can be one of: - If set to `None`, will use a non-binned approach where thresholds are dynamically calculated from all the data. Most accurate but also most memory consuming approach. - If set to an `int` (larger than 1), will use that number of thresholds linearly spaced from 0 to 1 as bins for the calculation. - If set to an `list` of floats, will use the indicated thresholds in the list as bins for the calculation - If set to an 1d `tensor` of floats, will use the indicated thresholds in the tensor as bins for the calculation. validate_args: bool indicating if input arguments and tensors should be validated for correctness. Set to ``False`` for faster computations. kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info. Example: >>> from torch import tensor >>> from torchmetrics.classification import MultilabelAUROC >>> preds = tensor([[0.75, 0.05, 0.35], ... [0.45, 0.75, 0.05], ... [0.05, 0.55, 0.75], ... [0.05, 0.65, 0.05]]) >>> target = tensor([[1, 0, 1], ... [0, 0, 0], ... [0, 1, 1], ... [1, 1, 1]]) >>> ml_auroc = MultilabelAUROC(num_labels=3, average="macro", thresholds=None) >>> ml_auroc(preds, target) tensor(0.6528) >>> ml_auroc = MultilabelAUROC(num_labels=3, average=None, thresholds=None) >>> ml_auroc(preds, target) tensor([0.6250, 0.5000, 0.8333]) >>> ml_auroc = MultilabelAUROC(num_labels=3, average="macro", thresholds=5) >>> ml_auroc(preds, target) tensor(0.6528) >>> ml_auroc = MultilabelAUROC(num_labels=3, average=None, thresholds=5) >>> ml_auroc(preds, target) tensor([0.6250, 0.5000, 0.8333]) FrTrrrr r!r"LabelrOrPN num_labelsrR)microrPrTrUr$r%r&r'r(c rV)NF)r]r$r%r&r*)r+r,rrRr&)r-r]rRr$r%r&r'r.r*r0r,rWzMultilabelAUROC.__init__cCs<|jdurt|jt|jfn|j}t||j|j|j|jSr1) r$rr3r4r5rr]rRr%r6r*r*r0r8s$zMultilabelAUROC.computer9r:cCr;)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 >>> # Example plotting a single >>> import torch >>> from torchmetrics.classification import MultilabelAUROC >>> metric = MultilabelAUROC(num_labels=3) >>> metric.update(torch.rand(20,3), torch.randint(2, (20,3))) >>> fig_, ax_ = metric.plot() .. plot:: :scale: 75 >>> # Example plotting multiple values >>> import torch >>> from torchmetrics.classification import MultilabelAUROC >>> metric = MultilabelAUROC(num_labels=3) >>> values = [ ] >>> for _ in range(10): ... values.append(metric(torch.rand(20,3), torch.randint(2, (20,3)))) >>> fig_, ax_ = metric.plot(values) r<r>r*r*r0r?r@rrXrArYr*r*r.r0r[GsH  M      r[c@seZdZdZ       ddeddeddeeee e e fd eed eed eed d ee deede de defddZde de ddfddZdddZdS)AUROCaCompute Area Under the Receiver Operating Characteristic Curve (`ROC AUC`_). The AUROC score summarizes the ROC curve into an single number that describes the performance of a model for multiple thresholds at the same time. Notably, an AUROC score of 1 is a perfect score and an AUROC score of 0.5 corresponds to random guessing. This module 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 :class:`~torchmetrics.classification.BinaryAUROC`, :class:`~torchmetrics.classification.MulticlassAUROC` and :class:`~torchmetrics.classification.MultilabelAUROC` for the specific details of each argument influence and examples. Legacy Example: >>> from torch import tensor >>> preds = tensor([0.13, 0.26, 0.08, 0.19, 0.34]) >>> target = tensor([0, 0, 1, 1, 1]) >>> auroc = AUROC(task="binary") >>> auroc(preds, target) tensor(0.5000) >>> preds = tensor([[0.90, 0.05, 0.05], ... [0.05, 0.90, 0.05], ... [0.05, 0.05, 0.90], ... [0.85, 0.05, 0.10], ... [0.10, 0.10, 0.80]]) >>> target = tensor([0, 1, 1, 2, 2]) >>> auroc = AUROC(task="multiclass", num_classes=3) >>> auroc(preds, target) tensor(0.7778) NrPTclstask)binary multiclass multilabelr$rQr]rRrSr#r%r&r'r(c Kst|}| |||d|tjkrt|fi| S|tjkr8t|ts/tdt |dt ||fi| S|tj krUt|tsLtdt |dt ||fi| Std|d)zInitialize task metric.r)z+`num_classes` is expected to be `int` but `z was passed.`z*`num_labels` is expected to be `int` but `zTask z not supported!) rfrom_strupdateBINARYr MULTICLASS isinstancerI ValueErrortyperM MULTILABELr[) r`rar$rQr]rRr#r%r&r'r*r*r0__new__s      z AUROC.__new__argscOt|jjd)zUpdate metric state.zM metric does not have a global `update` method. Use the task specific metric.NotImplementedErrorr/rB)r-rnr'r*r*r0rf z AUROC.updatecCro)r2zN metric does not have a global `compute` method. Use the task specific metric.rp)r-r*r*r0r8rrz AUROC.compute)NNNrPNNT)r(N)rBrCrDrErkrrrrIrJrHrrFrrrmrfr8r*r*r*r0r_sD#    r_N)'collections.abcrtypingrrrtorchrtyping_extensionsr torchmetrics.classification.baser2torchmetrics.classification.precision_recall_curver r r ,torchmetrics.functional.classification.aurocr r rrrrtorchmetrics.metricrtorchmetrics.utilities.datartorchmetrics.utilities.enumsrtorchmetrics.utilities.importsrtorchmetrics.utilities.plotrr__doctest_skip__rrMr[r_r*r*r*r0s(         ~