o yi@s&ddlZddlmZmZddlZddlmZddlmZddlm Z ddl m Z m Z m Z mZmZmZ  dd ed ed ed ed deeeefdef ddZdededefddZ   dd ed eded ed deeeefdef ddZ   ddeded ed deeeefdef ddZdS)N)OptionalUnion)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_warningreplacepredstarget 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 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 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)rrrrrr^/home/ubuntu/.local/lib/python3.10/site-packages/torchmetrics/functional/nominal/tschuprows.py_tschuprows_t_update s rconfmatbias_correctionc Cst|}|}t||}||}|j\}}|rJt||||\}}} t|| dkr9tddtjt d|j dSt |t |d| d} n tj||j d} tj||j d} t |t | d| d} | ddS)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_namenandevicerg?) r sumrshapertorchminr tensorfloatr"sqrtclamp) rrcm_sum chi_squared phi_squaredn_rowsn_colsphi_squared_correctedrows_correctedcols_correctedtschuprows_t_value n_rows_tensor n_cols_tensorrrr_tschuprows_t_compute9s"     "  r6TcCs:t||tt||g}t|||||}t||S)a7Compute `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 torchmetrics.functional import tschuprows_t >>> _ = torch.manual_seed(42) >>> preds = torch.randint(0, 4, (100,)) >>> target = torch.round(preds + torch.randn(100)).clamp(0, 4) >>> tschuprows_t(preds, target) tensor(0.4930) )r lenr%catuniquerr6)rrrrrrrrrr tschuprows_tXs 2 r:matrixc Cst|||jd}tj|||jd}tt|dD]7\}}|dd|f|dd|f}} tt || g } t || | ||} t | ||||f<|||f<q|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 torchmetrics.functional.nominal import tschuprows_t_matrix >>> _ = torch.manual_seed(42) >>> matrix = torch.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 combinationsranger7r8r9rr6) r;rrr num_variablestschuprows_t_matrix_valueijxyrrrrrtschuprows_t_matrixs # "rF)r r)Tr r)r=typingrrr%rtyping_extensionsr7torchmetrics.functional.classification.confusion_matrixr%torchmetrics.functional.nominal.utilsrrr r r r intr(rboolr6r:rFrrrrsj      " :