Multiclasscohenkappa

multiclasscohenkappa

Metric MulticlassCohenKappa from torchmetrics (torchmetrics.classification.MulticlassCohenKappa)

When to invoke this skill

The user has predictions + ground truth and asks to evaluate with MulticlassCohenKappa, or mentions torchmetrics.classification.MulticlassCohenKappa directly, or wants the standard torchmetrics implementation.

Reference signature

from torchmetrics.classification import MulticlassCohenKappa

# MulticlassCohenKappa(num_classes: int, ignore_index: Optional[int] = None, weights: Optional[Literal['linear', 'quadratic', 'none']] = None, validate_args: bool = True, **kwargs: Any) -> None

Library docstring

Calculate `Cohen's kappa score`_ that measures inter-annotator agreement for multiclass tasks.

.. math::
    \kappa = (p_o - p_e) / (1 - p_e)

where :math:`p_o` is the empirical probability of agreement and :math:`p_e` is
the expected agreement when both annotators assign labels randomly. Note that
:math:`p_e` is estimated using a per-annotator empirical prior over the
class labels.

As input to ``forward`` and ``update`` the metric accepts the following input:

- ``preds`` (:class:`~torch.Tensor`): Either an int tensor of shape ``(N, ...)` or float tensor of shape
  ``(N, C, ..)``. If preds is a floating point we apply ``torch.argmax`` along the ``C`` dimension to automatically
  convert probabilities/logits into an int tensor.
- ``target`` (:class:`~torch.Tensor`): An int tensor of shape ``(N, ...)``.

.. tip::
   Additional dimension ``...`` will be flattened into the batch dimension.

As output to ``forward`` and ``compute`` the metric returns the following output:

- ``mcck`` (:class:`~torch.Tensor`): A tensor containing cohen kappa score

Args:
    num_classes: Integer specifying the number of classes
    ignore_index:
        Specifies a target value that is ignored and does not contribute to the metric calculation
    weights: Weighting type to calculate the score. Choose from:

        - ``None`` or ``'none'``: no weighting
        - ``'linear'``: linear weighting
        - ``'quadratic'``: quadratic weighting

    validate_args: bool indicating if input arguments and tensors should be validated for correctness.
        Set to ``False`` for faster computations.
    kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info.

Example (pred is integer tensor):
    >>> from torch import tensor
    >>> from torchmetrics.classification import MulticlassCohenKappa
    >>> target = tensor([2, 1, 0, 0])
    >>> preds = tensor([2, 1, 0, 1])
    >>> metric = MulticlassCohenKappa(num_classes=3)
    >>> metric(preds, target)
    tensor(0.6364)

Example (pred is float tensor):
    >>> from torchmetrics.classification import MulticlassCohenKappa
    >>> target = tensor([2, 1, 0, 0])
    >>> preds = tensor([[0.16, 0.26, 0.58],
    ...               

Quick recipe

import torchmetrics.classification as _m
score = _m.MulticlassCohenKappa(y_true, y_pred)

Don'ts

• Don't reimplement when the library version handles edge cases (NaN, ties, empty inputs) better than a hand-rolled formula.
• Always check the library version's argument order — sklearn is (y_true, y_pred) while torchmetrics is (preds, target).