a  dE; @sxddlmZmZmZmZddlZddlmZddlmZddl m Z ddl m Z ddl mZmZmZddlmZGd d d eZGd d d eZeeeeefd ddZeeeedddZeeedddZeeeedddZeeedddZd;eeedddZeeeeefddd Zeeeeeeeeeeeeeeeeeeef d!d"d#Zeeeeeeeeeeeed$ d%d&Zeed'd(d)Z eeeeeeeeeeeeeeeeeed* d+d,Z!deeed6eeed7eeeeeffd8d9d:Z$dS)?)ListOptionalTupleUnionN)Tensor)Literal) _check_data_shape_to_num_outputs)_check_same_shape) _bincount_cumsum dim_zero_cat)EnumStrc@s.eZdZdZdZdZdZeedddZ dS) _MetricVariantzEnumerate for metric variants.abcreturncCsdS)Nvariantrrrs/var/www/html/stable-diffusion-webui/venv/lib/python3.9/site-packages/torchmetrics/functional/regression/kendall.py_name!sz_MetricVariant._nameN) __name__ __module__ __qualname____doc__ABC staticmethodstrrrrrrrs rc@s.eZdZdZdZdZdZeedddZ dS) _TestAlternativez'Enumerate for test alternative options. two-sidedlessgreaterrcCsdS)N alternativerrrrrr-sz_TestAlternative._nameN) rrrr TWO_SIDEDLESSGREATERrr rrrrrr!&s r!)xyrcCsXt|}|j|j}}|\}}t|jdD]}||||||<q2|j|jfS)zBSort sequences in an ascent order according to the sequence ``x``.r)torchcloneTsortrangeshape)r)r*permirrr_sort_on_first_sequence2s   r3)r)r*r2rcCs@t||||ddk||||ddkddS)z>Count a total number of concordant pairs in a single sequence.Nr)r+ logical_andsum unsqueezer)r*r2rrr_concordant_element_sum=sr9)predstargetrcs*tfddtjdDdS)zDz+_count_concordant_pairs..rr+catr/r0r6r>rr>r_count_concordant_pairsBsrCc Csxtt||||ddk||||ddkt||||ddk||||ddkddS)z?Count a total number of discordant pairs in a single sequences.r4Nr)r+ logical_orr5r6r7r8rrr_discordant_element_sumGs22rEcs*tfddtjdDdS)zrrr?Ur@z+_count_discordant_pairs..rrAr>rr>r_count_discordant_pairsSsrFF)r)r.rcCs`|r|jddj}tjd|jdtj|jd}ttj||dd|ddk gddddS)z&Convert a sequence to the rank tensor.r)dimr4dtypedeviceN) r.valuesr+zerosr0int32rJr rBint)r)r.Z_onesrrr_convert_sequence_to_dense_rankXsrP)r)rcCstj|jd|j|jd}tj|jd|j|jd}tj|jd|j|jd}t|jdD]x}t|dd|f}||dk}||dd||<||d|d||<||dd|d||<q\|||fS)zWGet a total number of ties and staistics for p-value calculation for a given sequence.r4rHN?)r+rMr0rIrJr/r r6)r)ZtiesZties_p1Zties_p2rGZn_tiesrrr _get_tiesas "rT)r:r;rrc Cst||\}}t||}t||}tj|jd|jd}d}}d}} } } |tjkrt |}t |dd}t |\}}} t |\}} } ||||| || | |f S)z,Obtain statistics to calculate metric value.r)rJNT)r.) r3rCrFr+tensorr0rJrrrPrT) r:r;rconcordant_pairsdiscordant_pairsn_total preds_ties target_ties preds_ties_p1 preds_ties_p2target_ties_p1target_ties_p2rrr_get_metric_metadataps*    r_) r:r;rVrWcon_min_dis_pairsrXrYrZrrc Cs|tjkr|||S|tjkrN||dd} | || |} |t| Stjdd|jD|j|jd} tjdd|jD|j|jd} t | | } d|| d| |dS)z-Calculate Kendall's tau from metric metadata.r4rQcSsg|]}t|qSrlenunique)r=prrrr?r@z"_calculate_tau..rHcSsg|]}t|qSrra)r=trrrr?r@) rrrr+sqrtrUr-rIrJZminimum)r:r;rVrWr`rXrYrZrZtotal_combinations denominatorZ preds_uniqueZ target_uniqueZ min_classesrrr_calculate_taus      rh)t_valuercCsl|}tjjtdg|tdg|}|}|}||}| |tjt d|j |j dS)zObtain p-value for a given Tensor of t-values. Handle ``nan`` which cannot be passed into torch distributions. When t-value is ``nan``, a resulted p-value should be alson ``nan``. grRnanrH) r+ distributionsnormalZNormalrUtoisnanZ nan_to_numZcdfwherefloatrIrJ)rirJZ normal_distis_nanp_valuerrr"_get_p_value_for_t_value_from_dists , rs) r`rXrYr[r\rZr]r^rr%rc Cs||dd|d} |tjkr:d|t| d} nZ||d} | ||d} | d||| 7} | ||d| |d7} |t| } | tjkrt| } | tjtjfvr| d9} t| }| tjkr|d9}|S)z9Calculate p-value for Kendall's tau from metric metadata.r4rQrS rK) rrr+rfr!r&absr(rs)r`rXrYr[r\rZr]r^rr%Zt_value_denominator_baserimZt_value_denominatorrrrrr_calculate_p_values      ryr4)r:r; concat_preds concat_target num_outputsrcCs^|pg}|pg}t||t||||dkrB|d}|d}||||||fS)aUpdate variables required to compute Kendall rank correlation coefficient. Args: preds: Sequence of data target: Sequence of data concat_preds: List of batches of preds sequence to be concatenated concat_target: List of batches of target sequence to be concatenated num_outputs: Number of outputs in multioutput setting Raises: RuntimeError: If ``preds`` and ``target`` do not have the same shape r4)r rr7append)r:r;rzr{r|rrr_kendall_corrcoef_updates      r~)r:r;rr%rc Cst|||\ }}}}}} } } } ||} t||||| | || | }|r\t| | |||| | | || nd}|jddkr|}|dur|nd}|dd|fS)a/Compute Kendall rank correlation coefficient, and optionally p-value of corresponding statistical test. Args: Args: preds: Sequence of data target: Sequence of data variant: Indication of which variant of Kendall's tau to be used alternative: Alternative hypothesis for for t-test. Possible values: - 'two-sided': the rank correlation is nonzero - 'less': the rank correlation is negative (less than zero) - 'greater': the rank correlation is positive (greater than zero) Nrr4rK)r_rhryr0Zsqueezeclamp)r:r;rr%rVrWrYr[r\rZr]r^rXr`taurrrrr_kendall_corrcoef_computesD  rrr")rrr)r"r#r$)r:r;rt_testr%rc Cst|tstdt|d|r2|dur2tdtt|}|rRtt|nd}t||gg|j dkrndn|j dd\}}t t |t |||\} } | dur| | fS| S)a Compute `Kendall Rank Correlation Coefficient`_. .. math:: tau_a = \frac{C - D}{C + D} where :math:`C` represents concordant pairs, :math:`D` stands for discordant pairs. .. math:: tau_b = \frac{C - D}{\sqrt{(C + D + T_{preds}) * (C + D + T_{target})}} where :math:`C` represents concordant pairs, :math:`D` stands for discordant pairs and :math:`T` represents a total number of ties. .. math:: tau_c = 2 * \frac{C - D}{n^2 * \frac{m - 1}{m}} where :math:`C` represents concordant pairs, :math:`D` stands for discordant pairs, :math:`n` is a total number of observations and :math:`m` is a ``min`` of unique values in ``preds`` and ``target`` sequence. Definitions according to Definition according to `The Treatment of Ties in Ranking Problems`_. Args: preds: Sequence of data of either shape ``(N,)`` or ``(N,d)`` target: Sequence of data of either shape ``(N,)`` or ``(N,d)`` variant: Indication of which variant of Kendall's tau to be used t_test: Indication whether to run t-test alternative: Alternative hypothesis for t-test. Possible values: - 'two-sided': the rank correlation is nonzero - 'less': the rank correlation is negative (less than zero) - 'greater': the rank correlation is positive (greater than zero) Return: Correlation tau statistic (Optional) p-value of corresponding statistical test (asymptotic) Raises: ValueError: If ``t_test`` is not of a type bool ValueError: If ``t_test=True`` and ``alternative=None`` Example (single output regression): >>> from torchmetrics.functional.regression import kendall_rank_corrcoef >>> preds = torch.tensor([2.5, 0.0, 2, 8]) >>> target = torch.tensor([3, -0.5, 2, 1]) >>> kendall_rank_corrcoef(preds, target) tensor(0.3333) Example (multi output regression): >>> from torchmetrics.functional.regression import kendall_rank_corrcoef >>> preds = torch.tensor([[2.5, 0.0], [2, 8]]) >>> target = torch.tensor([[3, -0.5], [2, 1]]) >>> kendall_rank_corrcoef(preds, target) tensor([1., 1.]) Example (single output regression with t-test) >>> from torchmetrics.functional.regression import kendall_rank_corrcoef >>> preds = torch.tensor([2.5, 0.0, 2, 8]) >>> target = torch.tensor([3, -0.5, 2, 1]) >>> kendall_rank_corrcoef(preds, target, t_test=True, alternative='two-sided') (tensor(0.3333), tensor(0.4969)) Example (multi output regression with t-test): >>> from torchmetrics.functional.regression import kendall_rank_corrcoef >>> preds = torch.tensor([[2.5, 0.0], [2, 8]]) >>> target = torch.tensor([[3, -0.5], [2, 1]]) >>> kendall_rank_corrcoef(preds, target, t_test=True, alternative='two-sided') (tensor([1., 1.]), tensor([nan, nan])) z>Argument `t_test` is expected to be of a type `bool`, but got .NzCArgument `alternative` is required if `t_test=True` but got `None`.r4rK)r|) isinstancebool ValueErrortyperZfrom_strr r!r~ndimr0rr ) r:r;rrr%Z_variantZ _alternative_preds_targetrrrrrrkendall_rank_corrcoefAsK   r)F)NNr4)N)rFr")%typingrrrrr+rZtyping_extensionsrZ(torchmetrics.functional.regression.utilsrZtorchmetrics.utilities.checksr Ztorchmetrics.utilities.datar r r Ztorchmetrics.utilities.enumsr rr!r3rOr9rCrErFrrPrTr_rhrsryr~rrrrrrs           )  $   ( ?