o yi@sTddlmZddlZddlmZmZddlmZmZddlm Z Gddde Z dS))AnyN)Tensortensor)_r2_score_compute_r2_score_update)Metricc seZdZUdZdZeed<dZeed<dZeed<e ed<e ed<e ed <e ed < dde de de de ddf fdd Z de de ddfddZde fddZZS)R2Scorea Computes r2 score also known as `R2 Score_Coefficient Determination`_: .. math:: R^2 = 1 - \frac{SS_{res}}{SS_{tot}} where :math:`SS_{res}=\sum_i (y_i - f(x_i))^2` is the sum of residual squares, and :math:`SS_{tot}=\sum_i (y_i - \bar{y})^2` is total sum of squares. Can also calculate adjusted r2 score given by .. math:: R^2_{adj} = 1 - \frac{(1-R^2)(n-1)}{n-k-1} where the parameter :math:`k` (the number of independent regressors) should be provided as the `adjusted` argument. The score is only proper defined when :math:`SS_{tot}\neq 0`, which can happen for near constant targets. In this case a score of 0 is returned. By definition the score is bounded between 0 and 1, where 1 corresponds to the predictions exactly matching the targets. As input to ``forward`` and ``update`` the metric accepts the following input: - ``preds`` (:class:`~torch.Tensor`): Predictions from model in float tensor with shape ``(N,)`` or ``(N, M)`` (multioutput) - ``target`` (:class:`~torch.Tensor`): Ground truth values in float tensor with shape ``(N,)`` or ``(N, M)`` (multioutput) As output of ``forward`` and ``compute`` the metric returns the following output: - ``r2score`` (:class:`~torch.Tensor`): A tensor with the r2 score(s) In the case of multioutput, as default the variances will be uniformly averaged over the additional dimensions. Please see argument ``multioutput`` for changing this behavior. Args: num_outputs: Number of outputs in multioutput setting adjusted: number of independent regressors for calculating adjusted r2 score. multioutput: Defines aggregation in the case of multiple output scores. Can be one of the following strings: * ``'raw_values'`` returns full set of scores * ``'uniform_average'`` scores are uniformly averaged * ``'variance_weighted'`` scores are weighted by their individual variances kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info. Raises: ValueError: If ``adjusted`` parameter is not an integer larger or equal to 0. ValueError: If ``multioutput`` is not one of ``"raw_values"``, ``"uniform_average"`` or ``"variance_weighted"``. Example: >>> from torchmetrics import R2Score >>> target = torch.tensor([3, -0.5, 2, 7]) >>> preds = torch.tensor([2.5, 0.0, 2, 8]) >>> r2score = R2Score() >>> r2score(preds, target) tensor(0.9486) >>> target = torch.tensor([[0.5, 1], [-1, 1], [7, -6]]) >>> preds = torch.tensor([[0, 2], [-1, 2], [8, -5]]) >>> r2score = R2Score(num_outputs=2, multioutput='raw_values') >>> r2score(preds, target) tensor([0.9654, 0.9082]) Tis_differentiablehigher_is_betterFfull_state_updatesum_squared_error sum_errorresidualtotalruniform_average num_outputsadjusted multioutputkwargsreturnNc stjd i|||_|dkst|tstd||_d}||vr)td|||_|jdt |jdd|jdt |jdd|jd t |jdd|jd t ddddS) Nrz?`adjusted` parameter should be an integer larger or equal to 0.) raw_valuesrvariance_weightedzFInvalid input to argument `multioutput`. Choose one of the following: r sum)defaultdist_reduce_fxr rr) super__init__r isinstanceint ValueErrorrr add_statetorchzerosr)selfrrrrallowed_multioutput __class__rN/home/ubuntu/.local/lib/python3.10/site-packages/torchmetrics/regression/r2.pyr[szR2Score.__init__predstargetcCsNt||\}}}}|j|7_|j|7_|j|7_|j|7_dS)z*Update state with predictions and targets.N)rr r rr)r%r*r+r r rrrrr)updatevs zR2Score.updatecCst|j|j|j|j|j|jS)z)Computes r2 score over the metric states.)rr r rrrr)r%rrr)computeszR2Score.compute)rrr)__name__ __module__ __qualname____doc__r bool__annotations__r r rr strrrr,r- __classcell__rrr'r)rs2  ;   r) typingrr#rr%torchmetrics.functional.regression.r2rrtorchmetrics.metricrrrrrr)s