metadata

title: accuracy_score
emoji: 🤗
colorFrom: blue
colorTo: orange
tags:
  - evaluate
  - metric
  - sklearn
description: '"Accuracy classification score."'
sdk: gradio
sdk_version: 3.12.0
app_file: app.py
pinned: false

This metric is part of the Scikit-learn integration into 🤗 Evaluate. You can find all available metrics in the Scikit-learn organization on the Hugging Face Hub.

Metric Card for `sklearn.metrics.accuracy_score`

Input Convention

To be consistent with the evaluate input conventions the scikit-learn inputs are renamed:

y_true: references
y_pred: predictions

Usage

import evaluate

metric = evaluate.load("sklearn/accuracy_score")
results = metric.compute(references=references, predictions=predictions)

Description

Accuracy classification score.

In multilabel classification, this function computes subset accuracy:
the set of labels predicted for a sample must *exactly* match the
corresponding set of labels in y_true.

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

Parameters
----------
y_true : 1d array-like, or label indicator array / sparse matrix
    Ground truth (correct) labels.

y_pred : 1d array-like, or label indicator array / sparse matrix
    Predicted labels, as returned by a classifier.

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

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

Returns
-------
score : float
    If ``normalize == True``, return the fraction of correctly
    classified samples (float), else returns the number of correctly
    classified samples (int).

    The best performance is 1 with ``normalize == True`` and the number
    of samples with ``normalize == False``.

See Also
--------
balanced_accuracy_score : Compute the balanced accuracy to deal with
    imbalanced datasets.
jaccard_score : Compute the Jaccard similarity coefficient score.
hamming_loss : Compute the average Hamming loss or Hamming distance between
    two sets of samples.
zero_one_loss : Compute the Zero-one classification loss. By default, the
    function will return the percentage of imperfectly predicted subsets.

Notes
-----
In binary classification, this function is equal to the `jaccard_score`
function.

Examples
--------
>>> from sklearn.metrics import accuracy_score
>>> y_pred = [0, 2, 1, 3]
>>> y_true = [0, 1, 2, 3]
>>> accuracy_score(y_true, y_pred)
0.5
>>> accuracy_score(y_true, y_pred, normalize=False)
2

In the multilabel case with binary label indicators:

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

Citation

@article{scikit-learn,
 title={Scikit-learn: Machine Learning in {P}ython},
 author={Pedregosa, F. and Varoquaux, G. and Gramfort, A. and Michel, V.
         and Thirion, B. and Grisel, O. and Blondel, M. and Prettenhofer, P.
         and Weiss, R. and Dubourg, V. and Vanderplas, J. and Passos, A. and
         Cournapeau, D. and Brucher, M. and Perrot, M. and Duchesnay, E.},
 journal={Journal of Machine Learning Research},
 volume={12},
 pages={2825--2830},
 year={2011}
}

Further References

Docs: https://scikit-learn.org/stable/modules/generated/sklearn.metrics.accuracy_score.html