o yi@sddlZddlmZmZddlZddlmZddlmZddlm Z ddl m Z m Z m Z mZ  dd ed ed ed ed deeeefdef ddZdedefddZ  dd ed ed ed deeeefdef ddZ  dded ed deeeefdefddZdS)N)OptionalUnion)Tensor)Literal)#_multiclass_confusion_matrix_update)_compute_chi_squared_drop_empty_rows_and_cols_handle_nan_in_data_nominal_input_validationreplacepredstarget num_classes nan_strategy)r dropnan_replace_valuereturncCsN|jdkr |dn|}|jdkr|dn|}t||||\}}t|||S)aComputes 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 specifing 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 rrrrr[/home/ubuntu/.local/lib/python3.10/site-packages/torchmetrics/functional/nominal/pearson.py(_pearsons_contingency_coefficient_updates rconfmatcCsBt|}|}t|dd}||}t|d|}|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_correctionrr g?)rsumrtorchsqrtclamp)rcm_sum chi_squared phi_squaredtschuprows_t_valuerrr)_pearsons_contingency_coefficient_compute7s    r%cCs8t||tt||g}t|||||}t|S)aQCompute `Pearson's Contingency Coefficient`_ measuring the association between two categorical (nominal) 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 torchmetrics.functional import pearsons_contingency_coefficient >>> _ = torch.manual_seed(42) >>> preds = torch.randint(0, 4, (100,)) >>> target = torch.round(preds + torch.randn(100)).clamp(0, 4) >>> pearsons_contingency_coefficient(preds, target) tensor(0.6948) )r lenrcatuniquerr%)r rrrrrrrr pearsons_contingency_coefficientIs 2r)matrixc Cst|||jd}tj|||jd}tt|dD]8\}}|dd|f|dd|f}}tt ||g } t ||| ||} t | } | |||f<|||f<q|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 torchmetrics.functional.nominal import pearsons_contingency_coefficient_matrix >>> _ = torch.manual_seed(42) >>> matrix = torch.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 shaperonesr+ itertools combinationsranger&r'r(rr%) r*rr num_variablespearsons_cont_coef_matrix_valueijxyrrvalrrr'pearsons_contingency_coefficient_matrixs ! "r8)r r )r.typingrrrrtyping_extensionsr7torchmetrics.functional.classification.confusion_matrixr%torchmetrics.functional.nominal.utilsrrr r intfloatrr%r)r8rrrrs^       :