.. DO NOT EDIT. .. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY. .. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE: .. "auto_examples/model_selection/plot_permutation_tests_for_classification.py" .. LINE NUMBERS ARE GIVEN BELOW. .. only:: html .. note:: :class: sphx-glr-download-link-note :ref:`Go to the end ` to download the full example code or to run this example in your browser via JupyterLite or Binder .. rst-class:: sphx-glr-example-title .. _sphx_glr_auto_examples_model_selection_plot_permutation_tests_for_classification.py: ================================================================= Test with permutations the significance of a classification score ================================================================= This example demonstrates the use of :func:`~sklearn.model_selection.permutation_test_score` to evaluate the significance of a cross-validated score using permutations. .. GENERATED FROM PYTHON SOURCE LINES 11-16 .. code-block:: Python # Authors: Alexandre Gramfort # Lucy Liu # License: BSD 3 clause .. GENERATED FROM PYTHON SOURCE LINES 17-22 Dataset ------- We will use the :ref:`iris_dataset`, which consists of measurements taken from 3 types of irises. .. GENERATED FROM PYTHON SOURCE LINES 22-29 .. code-block:: Python from sklearn.datasets import load_iris iris = load_iris() X = iris.data y = iris.target .. GENERATED FROM PYTHON SOURCE LINES 30-32 We will also generate some random feature data (i.e., 20 features), uncorrelated with the class labels in the iris dataset. .. GENERATED FROM PYTHON SOURCE LINES 32-40 .. code-block:: Python import numpy as np n_uncorrelated_features = 20 rng = np.random.RandomState(seed=0) # Use same number of samples as in iris and 20 features X_rand = rng.normal(size=(X.shape[0], n_uncorrelated_features)) .. GENERATED FROM PYTHON SOURCE LINES 41-60 Permutation test score ---------------------- Next, we calculate the :func:`~sklearn.model_selection.permutation_test_score` using the original iris dataset, which strongly predict the labels and the randomly generated features and iris labels, which should have no dependency between features and labels. We use the :class:`~sklearn.svm.SVC` classifier and :ref:`accuracy_score` to evaluate the model at each round. :func:`~sklearn.model_selection.permutation_test_score` generates a null distribution by calculating the accuracy of the classifier on 1000 different permutations of the dataset, where features remain the same but labels undergo different permutations. This is the distribution for the null hypothesis which states there is no dependency between the features and labels. An empirical p-value is then calculated as the percentage of permutations for which the score obtained is greater that the score obtained using the original data. .. GENERATED FROM PYTHON SOURCE LINES 60-75 .. code-block:: Python from sklearn.model_selection import StratifiedKFold, permutation_test_score from sklearn.svm import SVC clf = SVC(kernel="linear", random_state=7) cv = StratifiedKFold(2, shuffle=True, random_state=0) score_iris, perm_scores_iris, pvalue_iris = permutation_test_score( clf, X, y, scoring="accuracy", cv=cv, n_permutations=1000 ) score_rand, perm_scores_rand, pvalue_rand = permutation_test_score( clf, X_rand, y, scoring="accuracy", cv=cv, n_permutations=1000 ) .. GENERATED FROM PYTHON SOURCE LINES 76-87 Original data ^^^^^^^^^^^^^ Below we plot a histogram of the permutation scores (the null distribution). The red line indicates the score obtained by the classifier on the original data. The score is much better than those obtained by using permuted data and the p-value is thus very low. This indicates that there is a low likelihood that this good score would be obtained by chance alone. It provides evidence that the iris dataset contains real dependency between features and labels and the classifier was able to utilize this to obtain good results. .. GENERATED FROM PYTHON SOURCE LINES 87-99 .. code-block:: Python import matplotlib.pyplot as plt fig, ax = plt.subplots() ax.hist(perm_scores_iris, bins=20, density=True) ax.axvline(score_iris, ls="--", color="r") score_label = f"Score on original\ndata: {score_iris:.2f}\n(p-value: {pvalue_iris:.3f})" ax.text(0.7, 10, score_label, fontsize=12) ax.set_xlabel("Accuracy score") _ = ax.set_ylabel("Probability density") .. image-sg:: /auto_examples/model_selection/images/sphx_glr_plot_permutation_tests_for_classification_001.png :alt: plot permutation tests for classification :srcset: /auto_examples/model_selection/images/sphx_glr_plot_permutation_tests_for_classification_001.png :class: sphx-glr-single-img .. GENERATED FROM PYTHON SOURCE LINES 100-109 Random data ^^^^^^^^^^^ Below we plot the null distribution for the randomized data. The permutation scores are similar to those obtained using the original iris dataset because the permutation always destroys any feature label dependency present. The score obtained on the original randomized data in this case though, is very poor. This results in a large p-value, confirming that there was no feature label dependency in the original data. .. GENERATED FROM PYTHON SOURCE LINES 109-121 .. code-block:: Python fig, ax = plt.subplots() ax.hist(perm_scores_rand, bins=20, density=True) ax.set_xlim(0.13) ax.axvline(score_rand, ls="--", color="r") score_label = f"Score on original\ndata: {score_rand:.2f}\n(p-value: {pvalue_rand:.3f})" ax.text(0.14, 7.5, score_label, fontsize=12) ax.set_xlabel("Accuracy score") ax.set_ylabel("Probability density") plt.show() .. image-sg:: /auto_examples/model_selection/images/sphx_glr_plot_permutation_tests_for_classification_002.png :alt: plot permutation tests for classification :srcset: /auto_examples/model_selection/images/sphx_glr_plot_permutation_tests_for_classification_002.png :class: sphx-glr-single-img .. GENERATED FROM PYTHON SOURCE LINES 122-138 Another possible reason for obtaining a high p-value is that the classifier was not able to use the structure in the data. In this case, the p-value would only be low for classifiers that are able to utilize the dependency present. In our case above, where the data is random, all classifiers would have a high p-value as there is no structure present in the data. Finally, note that this test has been shown to produce low p-values even if there is only weak structure in the data [1]_. .. topic:: References: .. [1] Ojala and Garriga. `Permutation Tests for Studying Classifier Performance `_. The Journal of Machine Learning Research (2010) vol. 11 .. rst-class:: sphx-glr-timing **Total running time of the script:** (0 minutes 11.248 seconds) .. _sphx_glr_download_auto_examples_model_selection_plot_permutation_tests_for_classification.py: .. only:: html .. container:: sphx-glr-footer sphx-glr-footer-example .. container:: binder-badge .. image:: images/binder_badge_logo.svg :target: https://mybinder.org/v2/gh/scikit-learn/scikit-learn/1.4.X?urlpath=lab/tree/notebooks/auto_examples/model_selection/plot_permutation_tests_for_classification.ipynb :alt: Launch binder :width: 150 px .. container:: lite-badge .. image:: images/jupyterlite_badge_logo.svg :target: ../../lite/lab/?path=auto_examples/model_selection/plot_permutation_tests_for_classification.ipynb :alt: Launch JupyterLite :width: 150 px .. container:: sphx-glr-download sphx-glr-download-jupyter :download:`Download Jupyter notebook: plot_permutation_tests_for_classification.ipynb ` .. container:: sphx-glr-download sphx-glr-download-python :download:`Download Python source code: plot_permutation_tests_for_classification.py ` .. include:: plot_permutation_tests_for_classification.recommendations .. only:: html .. rst-class:: sphx-glr-signature `Gallery generated by Sphinx-Gallery `_