:j ddlZddlmZddlZddlmZddlmZddlmZddl m Z m Z m Z m Z mZmZ ddeded ed ed d eed ef dZdeded efdZ ddededed ed d eed ef dZ ddeded ed d eed ef dZy)N)Optional)Tensor)Literal)#_multiclass_confusion_matrix_update)_compute_bias_corrected_values_compute_chi_squared_drop_empty_rows_and_cols_handle_nan_in_data_nominal_input_validation&_unable_to_use_bias_correction_warningpredstarget 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 Tschuprow's T 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 rrrrs /home/mcse/projects/srt_converter/srt-converter-venv/lib/python3.12/site-packages/torchmetrics/functional/nominal/tschuprows.py_tschuprows_t_updater s\( %zzQELLOEE!'!1V]]1 vF'v|EVWME6 .ufk JJconfmatbias_correctionct|}|j}t||}||z }|j\}}|rt ||||\}}} t j || dk(r6tdt jtd|jSt j|t j|dz | dz zz } nvt j||j} t j||j} t j|t j| dz | dz zz } | jddS)aCompute Tschuprow's T statistic based on a pre-computed confusion matrix. Args: confmat: Confusion matrix for observed data bias_correction: Indication of whether to use bias correction. Returns: Tschuprow's T statistic rz Tschuprow's T) metric_namenandeviceg?) r sumrshapertorchminr tensorfloatr#sqrtclamp) rrcm_sum chi_squared phi_squarednum_rowsnum_colsphi_squared_correctedrows_correctedcols_correctedtschuprows_t_value n_rows_tensor n_cols_tensors r_tschuprows_t_computer8:s0(0G [[]F&w@K&K Hh@^ 8VA =~~ 99^^ 4 9 2 O<<e W^^D D"ZZ(= N]^L^cqtucuKv@w(wx Xk6H6HI  Xk6H6HI "ZZ ejj-RSBSXehiXiAj6k(kl  # #C --rct||ttj||gj }t |||||}t ||S)a;Compute `Tschuprow's T`_ statistic measuring the association between two categorical (nominal) data series. .. math:: T = \sqrt{\frac{\chi^2 / n}{\sqrt{(r - 1) * (k - 1)}}} 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. Tschuprow's T is a symmetric coefficient, i.e. :math:`T(preds, target) = T(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) bias_correction: Indication of whether to use bias correction. nan_strategy: Indication of whether to replace or drop ``NaN`` values nan_replace_value: Value to replace ``NaN``s when ``nan_strategy = 'replace'`` Returns: Tschuprow's T statistic Example: >>> from torch import randint, round >>> from torchmetrics.functional.nominal import tschuprows_t >>> preds = randint(0, 4, (100,)) >>> target = round(preds + torch.randn(100)).clamp(0, 4) >>> tschuprows_t(preds, target) tensor(0.4930) )r lenr'catuniquerr8)r rrrrrrs r tschuprows_tr=ZsPfl,=>eii0779:K"5&+|M^_G / ::rmatrixct|||jd}tj|||j}t j t|dD]l\}}|dd|f|dd|f} }ttj|| gj} t|| | ||} t| |x|||f<|||f<n|S)aCompute `Tschuprow's T`_ statistic between a set of multiple variables. This can serve as a convenient tool to compute Tschuprow's T statistic 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 bias_correction: Indication of whether to use bias correction. nan_strategy: Indication of whether to replace or drop ``NaN`` values nan_replace_value: Value to replace ``NaN``s when ``nan_strategy = 'replace'`` Returns: Tschuprow's T statistic for a dataset of categorical variables Example: >>> from torch import randint >>> from torchmetrics.functional.nominal import tschuprows_t_matrix >>> matrix = randint(0, 4, (200, 5)) >>> tschuprows_t_matrix(matrix) tensor([[1.0000, 0.0637, 0.0000, 0.0542, 0.1337], [0.0637, 1.0000, 0.0000, 0.0000, 0.0000], [0.0000, 0.0000, 1.0000, 0.0000, 0.0649], [0.0542, 0.0000, 0.0000, 1.0000, 0.1100], [0.1337, 0.0000, 0.0649, 0.1100, 1.0000]]) rr"rN) r r&r'onesr# itertools combinationsranger:r;r<rr8) r>rrr num_variablestschuprows_t_matrix_valueijxyrrs rtschuprows_t_matrixrJsHl,=>LLOM % =-PVP]P] ^&&u]';Q? 1ad|VAqD\1%))QF+2245 &q![,HYZLa _M  !!Q$'*CAqD*I   %$r)rr$)Trr$)rAtypingrr'rtyping_extensionsr7torchmetrics.functional.classification.confusion_matrixr%torchmetrics.functional.nominal.utilsrrr r r r intr*rboolr8r=rJrrrRs/ %g09), K K KK+, K   K  K4.6.D.V.F!/8), 6; 6; 6;6;+, 6;   6;  6;v!/8), .% .%.%+,.%  .%  .%r