Zero One Loss

zero-one-loss

Metric zero_one_loss from scikit-learn (sklearn.metrics.zero_one_loss)

When to invoke this skill

The user has predictions + ground truth and asks to evaluate with zero_one_loss, or mentions sklearn.metrics.zero_one_loss directly, or wants the standard scikit-learn implementation.

Reference signature

from sklearn.metrics import zero_one_loss

# zero_one_loss(y_true, y_pred, *, normalize=True, sample_weight=None)

Library docstring

Zero-one classification loss.

If normalize is ``True``, returns the fraction of misclassifications, else returns
the number of misclassifications. The best performance is 0.

Read more in the :ref:`User Guide <zero_one_loss>`.

Parameters
----------
y_true : 1d array-like, or label indicator array / sparse matrix
    Ground truth (correct) labels. Sparse matrix is only supported when
    labels are of :term:`multilabel` type.

y_pred : 1d array-like, or label indicator array / sparse matrix
    Predicted labels, as returned by a classifier. Sparse matrix is only
    supported when labels are of :term:`multilabel` type.

normalize : bool, default=True
    If ``False``, return the number of misclassifications.
    Otherwise, return the fraction of misclassifications.

sample_weight : array-like of shape (n_samples,), default=None
    Sample weights.

Returns
-------
loss : float
    If ``normalize == True``, returns the fraction of misclassifications, else
    returns the number of misclassifications.

See Also
--------
accuracy_score : Compute the accuracy score. By default, the function will
    return the fraction of correct predictions divided by the total number
    of predictions.
hamming_loss : Compute the average Hamming loss or Hamming distance between
    two sets of samples.
jaccard_score : Compute the Jaccard similarity coefficient score.

Notes
-----
In multilabel classification, the zero_one_loss function corresponds to
the subset zero-one loss: for each sample, the entire set of labels must be
correctly predicted, otherwise the loss for that sample is equal to one.

Examples
--------
>>> from sklearn.metrics import zero_one_loss
>>> y_pred = [1, 2, 3, 4]
>>> y_true = [2, 2, 3, 4]
>>> zero_one_loss(y_true, y_pred)
0.25
>>> zero_one_loss(y_true, y_pred, normalize=False)
1.0

In the multilabel case with binary label indicators:

>>> import numpy as np
>>> zero_one_loss(np.array([[0, 1], [1, 1]]), np.ones((2, 2)))
0.5

Quick recipe

import sklearn.metrics as _m
score = _m.zero_one_loss(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).