Shortcuts

Pearson’s Contingency Coefficient

Module Interface

class torchmetrics.PearsonsContingencyCoefficient(num_classes, nan_strategy='replace', nan_replace_value=0.0, **kwargs)[source]

Compute Pearson’s Contingency Coefficient statistic measuring the association between two categorical (nominal) data series.

Pearson = \sqrt{\frac{\chi^2 / n}{1 + \chi^2 / n}}

where

\chi^2 = \sum_{i,j} \ frac{\left(n_{ij} - \frac{n_{i.} n_{.j}}{n}\right)^2}{\frac{n_{i.} n_{.j}}{n}}

where n_{ij} denotes the number of times the values (A_i, B_j) are observed with A_i, B_j represent frequencies of values in preds and target, respectively.

Pearson’s Contingency Coefficient is a symmetric coefficient, i.e. Pearson(preds, target) = Pearson(target, preds).

The output values lies in [0, 1] with 1 meaning the perfect association.

Parameters
  • num_classes (int) – Integer specifing the number of classes

  • nan_strategy (Literal[‘replace’, ‘drop’]) – Indication of whether to replace or drop NaN values

  • nan_replace_value (Union[int, float, None]) – Value to replace NaN``s when ``nan_strategy = 'replace'

  • kwargs (Any) – Additional keyword arguments, see Advanced metric settings for more info.

Returns

Pearson’s Contingency Coefficient statistic

Raises
  • ValueError – If nan_strategy is not one of ‘replace’ and ‘drop’

  • ValueError – If nan_strategy is equal to ‘replace’ and nan_replace_value is not an int or float

Example

>>> from torchmetrics import PearsonsContingencyCoefficient
>>> _ = torch.manual_seed(42)
>>> preds = torch.randint(0, 4, (100,))
>>> target = torch.round(preds + torch.randn(100)).clamp(0, 4)
>>> pearsons_contingency_coefficient = PearsonsContingencyCoefficient(num_classes=5)
>>> pearsons_contingency_coefficient(preds, target)
tensor(0.6948)

Initializes internal Module state, shared by both nn.Module and ScriptModule.

compute()[source]

Computer Pearson’s Contingency Coefficient statistic.

Return type

Tensor

update(preds, target)[source]

Update state with predictions and targets.

Parameters
  • preds (Tensor) –

    1D or 2D tensor of categorical (nominal) data:

    • 1D shape: (batch_size,)

    • 2D shape: (batch_size, num_classes)

  • target (Tensor) –

    1D or 2D tensor of categorical (nominal) data:

    • 1D shape: (batch_size,)

    • 2D shape: (batch_size, num_classes)

Return type

None

Functional Interface

torchmetrics.functional.pearsons_contingency_coefficient(preds, target, nan_strategy='replace', nan_replace_value=0.0)[source]

Compute Pearson’s Contingency Coefficient measuring the association between two categorical (nominal) data series.

Pearson = \sqrt{\frac{\chi^2 / n}{1 + \chi^2 / n}}

where

\chi^2 = \sum_{i,j} \ frac{\left(n_{ij} - \frac{n_{i.} n_{.j}}{n}\right)^2}{\frac{n_{i.} n_{.j}}{n}}

where n_{ij} denotes the number of times the values (A_i, B_j) are observed with A_i, B_j represent frequencies of values in preds and target, respectively.

Pearson’s Contingency Coefficient is a symmetric coefficient, i.e. Pearson(preds, target) = Pearson(target, preds).

The output values lies in [0, 1] with 1 meaning the perfect association.

Parameters
  • preds (Tensor) –

    1D or 2D tensor of categorical (nominal) data:

    • 1D shape: (batch_size,)

    • 2D shape: (batch_size, num_classes)

  • target (Tensor) –

    1D or 2D tensor of categorical (nominal) data:

    • 1D shape: (batch_size,)

    • 2D shape: (batch_size, num_classes)

  • nan_strategy (Literal[‘replace’, ‘drop’]) – Indication of whether to replace or drop NaN values

  • nan_replace_value (Union[int, float, None]) – Value to replace NaN``s when ``nan_strategy = 'replace'

Return type

Tensor

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)

pearsons_contingency_coefficient_matrix

torchmetrics.functional.nominal.pearsons_contingency_coefficient_matrix(matrix, nan_strategy='replace', nan_replace_value=0.0)[source]

Compute 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.

Parameters
  • matrix (Tensor) –

    A tensor of categorical (nominal) data, where:

    • rows represent a number of data points

    • columns represent a number of categorical (nominal) features

  • nan_strategy (Literal[‘replace’, ‘drop’]) – Indication of whether to replace or drop NaN values

  • nan_replace_value (Union[int, float, None]) – Value to replace NaN``s when ``nan_strategy = 'replace'

Return type

Tensor

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]])