iddlmZddlmZmZmZddlZddlmZddlm Z ddl m Z m Z ddl mZddlmZdd lmZdd lmZmZesd gZGd d eZy))Sequence)AnyOptionalUnionN)Tensor)Literal)_theils_u_compute_theils_u_update)_nominal_input_validation)Metric)_MATPLOTLIB_AVAILABLE)_AX_TYPE_PLOT_OUT_TYPEz TheilsU.plotc eZdZUdZdZeed<dZeed<dZeed<dZ e ed<d Z e ed <e ed < dd e d eddee deddf fd Zde de ddfdZde fdZddee ee dfdeedefdZxZS)TheilsUaCompute `Theil's U`_ statistic measuring the association between two categorical (nominal) data series. .. math:: U(X|Y) = \frac{H(X) - H(X|Y)}{H(X)} where :math:`H(X)` is entropy of variable :math:`X` while :math:`H(X|Y)` is the conditional entropy of :math:`X` given :math:`Y`. It is also know as the Uncertainty Coefficient. Theils's U is an asymmetric coefficient, i.e. :math:`TheilsU(preds, target) \neq TheilsU(target, preds)`, so the order of the inputs matters. The output values lies in [0, 1], where a 0 means y has no information about x while value 1 means y has complete information about x. As input to ``forward`` and ``update`` the metric accepts the following input: - ``preds`` (:class:`~torch.Tensor`): Either 1D or 2D tensor of categorical (nominal) data from the first data series (called X in the above definition) with shape ``(batch_size,)`` or ``(batch_size, num_classes)``, respectively. - ``target`` (:class:`~torch.Tensor`): Either 1D or 2D tensor of categorical (nominal) data from the second data series (called Y in the above definition) with shape ``(batch_size,)`` or ``(batch_size, num_classes)``, respectively. As output of ``forward`` and ``compute`` the metric returns the following output: - ``theils_u`` (:class:`~torch.Tensor`): Scalar tensor containing the Theil's U statistic. Args: num_classes: Integer specifying the number of classes nan_strategy: Indication of whether to replace or drop ``NaN`` values nan_replace_value: Value to replace ``NaN``s when ``nan_strategy = 'replace'`` kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info. Example:: >>> from torch import randint >>> from torchmetrics.nominal import TheilsU >>> preds = randint(10, (10,)) >>> target = randint(10, (10,)) >>> metric = TheilsU(num_classes=10) >>> metric(preds, target) tensor(0.8530) Ffull_state_updateis_differentiableThigher_is_betterplot_lower_boundg?plot_upper_boundconfmat num_classes nan_strategy)replacedropnan_replace_valuekwargsreturnNc t|di|||_t||||_||_|j dtj||dy)Nrsum)dist_reduce_fx) super__init__rr rr add_statetorchzeros)selfrrrr __class__s r/Volumes/fast/ai/experiments/voice-extract-mac/.venv/lib/python3.12/site-packages/torchmetrics/nominal/theils_u.pyr%zTheilsU.__init__PsV "6"&!,0AB(!2 y%++k;"GX]^predstargetct|||j|j|j}|xj|z c_y)z*Update state with predictions and targets.N)r rrrr)r)r-r.rs r+updatezTheilsU.update`s5"5&$2B2BDDUDUW[WmWmn  r,c,t|jS)zCompute Theil's U statistic.)r r)r)s r+computezTheilsU.computees ..r,valaxc&|j||S)a&Plot a single or multiple values from the metric. Args: val: Either a single result from calling `metric.forward` or `metric.compute` or a list of these results. If no value is provided, will automatically call `metric.compute` and plot that result. ax: An matplotlib axis object. If provided will add plot to that axis Returns: Figure and Axes object Raises: ModuleNotFoundError: If `matplotlib` is not installed .. plot:: :scale: 75 >>> # Example plotting a single value >>> import torch >>> from torchmetrics.nominal import TheilsU >>> metric = TheilsU(num_classes=10) >>> metric.update(torch.randint(10, (10,)), torch.randint(10, (10,))) >>> fig_, ax_ = metric.plot() .. plot:: :scale: 75 >>> # Example plotting multiple values >>> import torch >>> from torchmetrics.nominal import TheilsU >>> metric = TheilsU(num_classes=10) >>> values = [ ] >>> for _ in range(10): ... values.append(metric(torch.randint(10, (10,)), torch.randint(10, (10,)))) >>> fig_, ax_ = metric.plot(values) )_plot)r)r3r4s r+plotz TheilsU.plotisLzz#r""r,)rr)NN)__name__ __module__ __qualname____doc__rbool__annotations__rrrfloatrrintrrrr%r0r2rrrrr7 __classcell__)r*s@r+rrs'R$t##t#!d!!e!!e! O 4=-0 __/0_$E? _  _  _  F F t //&#fhv&6<=&#(S[J\&#hv&#r,r)collections.abcrtypingrrrr'rtyping_extensionsr(torchmetrics.functional.nominal.theils_ur r %torchmetrics.functional.nominal.utilsr torchmetrics.metricr torchmetrics.utilities.importsr torchmetrics.utilities.plotrr__doctest_skip__rr#r,r+rJsB%'' %XK&@@&'p#fp#r,