.. note::
    :class: sphx-glr-download-link-note

    Click :ref:`here <sphx_glr_download_auto_examples_linear_model_plot_sgd_comparison.py>` to download the full example code
.. rst-class:: sphx-glr-example-title

.. _sphx_glr_auto_examples_linear_model_plot_sgd_comparison.py:


==================================
Comparing various online solvers
==================================

An example showing how different online solvers perform
on the hand-written digits dataset.




.. code-block:: python

    # Author: Rob Zinkov <rob at zinkov dot com>
    # License: BSD 3 clause

    import numpy as np
    import matplotlib.pyplot as plt
    from sklearn import datasets

    from sklearn.model_selection import train_test_split
    from sklearn.linear_model import SGDClassifier, Perceptron
    from sklearn.linear_model import PassiveAggressiveClassifier
    from sklearn.linear_model import LogisticRegression

    heldout = [0.95, 0.90, 0.75, 0.50, 0.01]
    rounds = 20
    digits = datasets.load_digits()
    X, y = digits.data, digits.target

    classifiers = [
        ("SGD", SGDClassifier(max_iter=100)),
        ("ASGD", SGDClassifier(average=True, max_iter=100)),
        ("Perceptron", Perceptron(tol=1e-3)),
        ("Passive-Aggressive I", PassiveAggressiveClassifier(loss='hinge',
                                                             C=1.0, tol=1e-4)),
        ("Passive-Aggressive II", PassiveAggressiveClassifier(loss='squared_hinge',
                                                              C=1.0, tol=1e-4)),
        ("SAG", LogisticRegression(solver='sag', tol=1e-1, C=1.e4 / X.shape[0]))
    ]

    xx = 1. - np.array(heldout)

    for name, clf in classifiers:
        print("training %s" % name)
        rng = np.random.RandomState(42)
        yy = []
        for i in heldout:
            yy_ = []
            for r in range(rounds):
                X_train, X_test, y_train, y_test = \
                    train_test_split(X, y, test_size=i, random_state=rng)
                clf.fit(X_train, y_train)
                y_pred = clf.predict(X_test)
                yy_.append(1 - np.mean(y_pred == y_test))
            yy.append(np.mean(yy_))
        plt.plot(xx, yy, label=name)

    plt.legend(loc="upper right")
    plt.xlabel("Proportion train")
    plt.ylabel("Test Error Rate")
    plt.show()

**Total running time of the script:** ( 0 minutes  0.000 seconds)


.. _sphx_glr_download_auto_examples_linear_model_plot_sgd_comparison.py:


.. only :: html

 .. container:: sphx-glr-footer
    :class: sphx-glr-footer-example



  .. container:: sphx-glr-download

     :download:`Download Python source code: plot_sgd_comparison.py <plot_sgd_comparison.py>`



  .. container:: sphx-glr-download

     :download:`Download Jupyter notebook: plot_sgd_comparison.ipynb <plot_sgd_comparison.ipynb>`


.. only:: html

 .. rst-class:: sphx-glr-signature

    `Gallery generated by Sphinx-Gallery <https://sphinx-gallery.readthedocs.io>`_
