Completenessscore

completenessscore

Metric CompletenessScore from torchmetrics (torchmetrics.clustering.CompletenessScore)

When to invoke this skill

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

Reference signature

from torchmetrics.clustering import CompletenessScore

# CompletenessScore(**kwargs: Any) -> None

Library docstring

Compute `Completeness Score`_.

A clustering result satisfies completeness if all the data points that are members of a given class are elements of
the same cluster. The metric is not symmetric, therefore swapping ``preds`` and ``target`` yields a different score.

This clustering metric is an extrinsic measure, because it requires ground truth clustering labels, which may not
be available in practice since clustering in generally is used for unsupervised learning.

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

- ``preds`` (:class:`~torch.Tensor`): single integer tensor with shape ``(N,)`` with predicted cluster labels
- ``target`` (:class:`~torch.Tensor`): single integer tensor with shape ``(N,)`` with ground truth cluster labels

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

- ``rand_score`` (:class:`~torch.Tensor`): A tensor with the Rand Score

Args:
    kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info.

Example:
    >>> import torch
    >>> from torchmetrics.clustering import CompletenessScore
    >>> preds = torch.tensor([2, 1, 0, 1, 0])
    >>> target = torch.tensor([0, 2, 1, 1, 0])
    >>> metric = CompletenessScore()
    >>> metric(preds, target)
    tensor(0.4744)

Quick recipe

import torchmetrics.clustering as _m
score = _m.CompletenessScore(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).