i\dddlmZmZmZddlZddlmZmZddlmZddl m Z m Z m Z m Z mZmZmZmZmZmZmZmZddlmZmZmZddlmZmZddlmZdd lm Z dd l!m"Z" d*d eeeefd eeeefd eeddeede#def dZ$ d+dee#deee%e&e#efdee%ddfdZ' d,deee(eeffdeedee#de%def dZ) d-dededee#deee%e&e#efdee%de*defdZ+ d.de%d eeddeee%e&e#efdee%ddf dZ, d/deee(eeffde%d eeddeedef d Z- d0dedede%d eeddeee%e&e#efdee%de*defd!Z. d1d"e%d eed#deee%e&e#efdee%ddf d$Z/ d2deee(eeffd"e%d eed#deedee%def d%Z0 d0deded"e%d eed#deee%e&e#efdee%de*defd&Z1 d3deded'ed(deee%e&e#efdee%d"ee%d eeddee#dee%de*deefd)Z2y)4)ListOptionalUnionN)Tensortensor)Literal) -_binary_precision_recall_curve_arg_validation%_binary_precision_recall_curve_format0_binary_precision_recall_curve_tensor_validation%_binary_precision_recall_curve_update1_multiclass_precision_recall_curve_arg_validation)_multiclass_precision_recall_curve_format4_multiclass_precision_recall_curve_tensor_validation)_multiclass_precision_recall_curve_update1_multilabel_precision_recall_curve_arg_validation)_multilabel_precision_recall_curve_format4_multilabel_precision_recall_curve_tensor_validation)_multilabel_precision_recall_curve_update)_binary_roc_compute_multiclass_roc_compute_multilabel_roc_compute)_auc_compute_without_check _safe_divide) _bincount)ClassificationTask)rank_zero_warnfprtpraverage)macroweightednoneweights directionreturnc Vt|tr t|trt|||d}n>tjt ||Dcgc]\}}t|||c}}}||dk(r|Stj |jrtd|dttj |}|dk(r||jS|dk(r8|6t||||j}|||zjStd cc}}w) z8Reduce multiple average precision score into one number.)r$axis)r$r"zUAverage precision score for one or more classes was `nan`. Ignoring these classes in z-averager r!zBReceived an incompatible combinations of inputs to make reduction.) isinstancerrtorchstackzipisnananyr UserWarningmeanrsum ValueError) rrrr#r$resxyidxs /Volumes/fast/ai/experiments/voice-extract-mac/.venv/lib/python3.12/site-packages/torchmetrics/functional/classification/auroc.py _reduce_aurocr8-s #v:c6#:(cYQOkk]`adfi]jk]jUYUVXY5aiP]jkl'V+  {{3cdkcllt u   ;;s  C'3x}}*!4ws|WS\-=-=-?@C7"'')) Y ZZlsD% max_fpr thresholds ignore_indexc|t|||.t|tsd|cxkrdkrnytd|yyy)Nrr'z@Arguments `max_fpr` should be a float in range (0, 1], but got: )r r)floatr2)r9r:r;s r7_binary_auroc_arg_validationr>IsL 2*lK:gu#=!gBRQRBR[\c[deffCS#=state pos_labelct|||\}}}|+|dk(s&|jdk(s|jdk(r t||dSt|tr |j n|dj }t ||}tj||dd} ||| dz z || || dz z z } tj|| dz || | } tj|d| | jdg}tj|d| |jdg}t||d} d|dzz} dd| | z || z z zzS) Nr'r?)deviceT) out_int32rightg?) rr1rr)rrDrr* bucketizelerpcatview)r@r:r9rArr__devicemax_areastopweight interp_tpr partial_aucmin_areas r7_binary_auroc_computerTSsO &eZCKCa'Q,#'')q.CGGIN)#sC88&sF3cjjQGgg6H ??8SD EDTAX&3t9s4!8}+D EFCqM3t9fEJ ))S$Z!34 5C ))S$Zq!12 3C-S#s;KXq[(H !{X-(X2EFF GGr?predstarget validate_argsc|rt|||t|||t||||\}}}t|||}t |||S)a 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. Accepts the following input tensors: - ``preds`` (float tensor): ``(N, ...)``. Preds should be a tensor 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`` (int tensor): ``(N, ...)``. Target should be a tensor 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. 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: preds: Tensor with predictions target: Tensor with true labels 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. 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: A single scalar with the auroc score Example: >>> from torchmetrics.functional.classification import binary_auroc >>> preds = torch.tensor([0, 0.5, 0.7, 0.8]) >>> target = torch.tensor([0, 1, 1, 0]) >>> binary_auroc(preds, target, thresholds=None) tensor(0.5000) >>> binary_auroc(preds, target, thresholds=5) tensor(0.5000) )r>r r r rT)rUrVr9r:r;rWr@s r7 binary_aurocrYnsV~$Wj,G8 U EeVU_am nE6: 1% LE  G <>> from torchmetrics.functional.classification import multiclass_auroc >>> preds = torch.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 = torch.tensor([0, 1, 3, 2]) >>> multiclass_auroc(preds, target, num_classes=5, average="macro", thresholds=None) tensor(0.5333) >>> multiclass_auroc(preds, target, num_classes=5, average=None, thresholds=None) tensor([1.0000, 1.0000, 0.3333, 0.3333, 0.0000]) >>> multiclass_auroc(preds, target, num_classes=5, average="macro", thresholds=5) tensor(0.5333) >>> multiclass_auroc(preds, target, num_classes=5, average=None, thresholds=5) tensor([1.0000, 1.0000, 0.3333, 0.3333, 0.0000]) )r_rrrrd)rUrVrZrr:r;rWr@s r7multiclass_aurocrfse\(gz<X>> from torchmetrics.functional.classification import multilabel_auroc >>> preds = torch.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 = torch.tensor([[1, 0, 1], ... [0, 0, 0], ... [0, 1, 1], ... [1, 1, 1]]) >>> multilabel_auroc(preds, target, num_labels=3, average="macro", thresholds=None) tensor(0.6528) >>> multilabel_auroc(preds, target, num_labels=3, average=None, thresholds=None) tensor([0.6250, 0.5000, 0.8333]) >>> multilabel_auroc(preds, target, num_labels=3, average="macro", thresholds=5) tensor(0.6528) >>> multilabel_auroc(preds, target, num_labels=3, average=None, thresholds=5) tensor([0.6250, 0.5000, 0.8333]) )rjrrrrn)rUrVrgrr:r;rWr@s r7multilabel_aurocrpPsgd(Wj,W>> preds = torch.tensor([0.13, 0.26, 0.08, 0.19, 0.34]) >>> target = torch.tensor([0, 0, 1, 1, 1]) >>> auroc(preds, target, task='binary') tensor(0.5000) >>> preds = torch.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 = torch.tensor([0, 1, 1, 2, 2]) >>> auroc(preds, target, task='multiclass', num_classes=3) tensor(0.7778) z+`num_classes` is expected to be `int` but `z was passed.`z*`num_labels` is expected to be `int` but `N) rfrom_strBINARYrY MULTICLASSr)intr2typerf MULTILABELrp) rUrVrqr:rZrgrr9r;rWs r7aurocr|sR  & &t ,D !(((E67J m\\ !,,,+s+J4P[K\J]]jkl lv{GZQ]_lmm !,,,*c*I$zJZI[[hij jvz7JP\^kll r?)r NrC)NNN)Nr')NNNT)r NN)r N)r NNT)NN)N)NNNr NNT)3typingrrrr*rrtyping_extensionsr=torchmetrics.functional.classification.precision_recall_curver r r r r rrrrrrr*torchmetrics.functional.classification.rocrrrtorchmetrics.utilities.computerrtorchmetrics.utilities.datartorchmetrics.utilities.enumsrtorchmetrics.utilities.printsrr=r8rylistr>tuplerTboolrYr_rdrfrjrnrpr|r?r7rsv)( %     T1;8 ?F $ [ vtF|# $[ vtF|# $[g9: ;[f  [  [  [: $<@"&g e_gsDK789g3-g g $ H vv~.. /H He_H H  H< $<@"& D= D= D=e_D=sDK789 D= 3- D=  D= D=R?F<@"& j j g9: ; jsDK789 j3- j  j?F#'  vv~.. /  g9: ;    &?F<@"&UN UN UNUNg9: ; UN sDK789 UN 3- UNUN UNv=A"& j j gBC D jsDK789 j3- j  j"#'  vv~.. /gBC D  3-   @HO<@"&Y[ Y[ Y[Y[gBC D Y[ sDK789 Y[ 3- Y[Y[ Y[@=A!% $>E#"&4 4 4 6 74sDK789 4 # 4  4g9: ;4e_43-44f4r?