i ddlZddlmZddlZddlmZddlmZddlmZddl m Z m Z m Z m Z  ddeded ed ed d eed ef dZded efdZ ddeded ed d eed ef dZ dded ed d eed efdZy)N)Optional)Tensor)Literal)#_multiclass_confusion_matrix_update)_compute_chi_squared_drop_empty_rows_and_cols_handle_nan_in_data_nominal_input_validationpredstarget num_classes nan_strategy)replacedropnan_replace_valuereturnc|jdk(r|jdn|}|jdk(r|jdn|}t||||\}}t|||S)aCompute the bins to update the confusion matrix with for Pearson's Contingency Coefficient calculation. Args: preds: 1D or 2D tensor of categorical (nominal) data target: 1D or 2D tensor of categorical (nominal) data 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``` Returns: Non-reduced confusion matrix )ndimargmaxr r)r r r rrs |/Volumes/fast/ai/experiments/voice-extract-mac/.venv/lib/python3.12/site-packages/torchmetrics/functional/nominal/pearson.py(_pearsons_contingency_coefficient_updaters\( %zzQELLOEE!'!1V]]1 vF'v|EVWME6 .ufk JJconfmatct|}|j}t|d}||z }tj|d|zz }|j ddS)zCompute Pearson's Contingency Coefficient based on a pre-computed confusion matrix. Args: confmat: Confusion matrix for observed data Returns: Pearson's Contingency Coefficient F)bias_correctionrg?)rsumrtorchsqrtclamp)rcm_sum chi_squared phi_squaredtschuprows_t_values r)_pearsons_contingency_coefficient_computer'8sZ(0G [[]F&wFK&KK1{?$CD  # #C --rct||ttj||gj }t |||||}t |S)aJCompute `Pearson's Contingency Coefficient`_ for measuring the association between two categorical data series. .. math:: Pearson = \sqrt{\frac{\chi^2 / n}{1 + \chi^2 / n}} where .. math:: \chi^2 = \sum_{i,j} \ frac{\left(n_{ij} - \frac{n_{i.} n_{.j}}{n}\right)^2}{\frac{n_{i.} n_{.j}}{n}} where :math:`n_{ij}` denotes the number of times the values :math:`(A_i, B_j)` are observed with :math:`A_i, B_j` represent frequencies of values in ``preds`` and ``target``, respectively. Pearson's Contingency Coefficient is a symmetric coefficient, i.e. :math:`Pearson(preds, target) = Pearson(target, preds)`. The output values lies in [0, 1] with 1 meaning the perfect association. Args: preds: 1D or 2D tensor of categorical (nominal) data: - 1D shape: (batch_size,) - 2D shape: (batch_size, num_classes) target: 1D or 2D tensor of categorical (nominal) data: - 1D shape: (batch_size,) - 2D shape: (batch_size, num_classes) nan_strategy: Indication of whether to replace or drop ``NaN`` values nan_replace_value: Value to replace ``NaN``s when ``nan_strategy = 'replace'`` Returns: Pearson's Contingency Coefficient Example: >>> from torch import randint, round >>> from torchmetrics.functional.nominal import pearsons_contingency_coefficient >>> preds = randint(0, 4, (100,)) >>> target = round(preds + torch.randn(100)).clamp(0, 4) >>> pearsons_contingency_coefficient(preds, target) tensor(0.6948) )r lenr catuniquerr')r r rrr rs r pearsons_contingency_coefficientr,KsOdl,=>eii0779:K6ufkS_arsG 4W ==rmatrixct|||jd}tj|||j}t j t|dD]m\}}|dd|f|dd|f}}ttj||gj} t||| ||} t| } | x|||f<|||f<o|S)aCompute `Pearson's Contingency Coefficient`_ statistic between a set of multiple variables. This can serve as a convenient tool to compute Pearson's Contingency Coefficient for analyses of correlation between categorical variables in your dataset. Args: matrix: A tensor of categorical (nominal) data, where: - rows represent a number of data points - columns represent a number of categorical (nominal) features nan_strategy: Indication of whether to replace or drop ``NaN`` values nan_replace_value: Value to replace ``NaN``s when ``nan_strategy = 'replace'`` Returns: Pearson's Contingency Coefficient statistic for a dataset of categorical variables Example: >>> from torch import randint >>> from torchmetrics.functional.nominal import pearsons_contingency_coefficient_matrix >>> matrix = randint(0, 4, (200, 5)) >>> pearsons_contingency_coefficient_matrix(matrix) tensor([[1.0000, 0.2326, 0.1959, 0.2262, 0.2989], [0.2326, 1.0000, 0.1386, 0.1895, 0.1329], [0.1959, 0.1386, 1.0000, 0.1840, 0.2335], [0.2262, 0.1895, 0.1840, 1.0000, 0.2737], [0.2989, 0.1329, 0.2335, 0.2737, 1.0000]]) r)devicerN) r shaper onesr/ itertools combinationsranger)r*r+rr') r-rr num_variablespearsons_cont_coef_matrix_valueijxyr rvals r'pearsons_contingency_coefficient_matrixr<sDl,=>LLOM&+jj V\VcVc&d#&&u]';Q?1ad|VAqD\1%))QF+2245 :1al\mn7@X[['1-0OPQSTPT0U @ +*r)rr)r2typingrr rtyping_extensionsr7torchmetrics.functional.classification.confusion_matrixr%torchmetrics.functional.nominal.utilsrrr r intfloatrr'r,r<rrrDs  %g09), K K KK+, K   K  K4.v.&.,09), 5> 5> 5>+,5>  5>  5>t09),++ +++,++ ++ ++r