.. DO NOT EDIT.
.. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY.
.. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE:
.. "auto_examples/plot_group_lasso.py"
.. LINE NUMBERS ARE GIVEN BELOW.

.. only:: html

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

        :ref:`Go to the end <sphx_glr_download_auto_examples_plot_group_lasso.py>`
        to download the full example code.

.. rst-class:: sphx-glr-example-title

.. _sphx_glr_auto_examples_plot_group_lasso.py:


===============================================================
Run GroupLasso and GroupLasso CV for structured sparse recovery
===============================================================

The example runs the GroupLasso scikit-learn like estimators.

.. GENERATED FROM PYTHON SOURCE LINES 8-31

.. code-block:: Python


    import numpy as np
    import matplotlib.pyplot as plt

    from celer import GroupLassoCV, LassoCV
    from celer.datasets import make_correlated_data
    from celer.plot_utils import configure_plt

    print(__doc__)
    configure_plt(fontsize=16)

    # Generating X, y, and true regression coefs with 4 groups of 5 non-zero values

    n_samples, n_features = 100, 50

    w_true = np.zeros(n_features)
    w_true[:5] = 1
    w_true[10:15] = 1
    w_true[30:35] = -1
    w_true[45:] = 1
    X, y, w_true = make_correlated_data(
        n_samples, n_features, w_true=w_true, snr=5, random_state=0)





.. rst-class:: sphx-glr-script-out

 .. code-block:: none


    usetex mode requires TeX.




.. GENERATED FROM PYTHON SOURCE LINES 32-33

Get group Lasso's optimal alpha for prediction by cross validation

.. GENERATED FROM PYTHON SOURCE LINES 33-58

.. code-block:: Python


    groups = 5  # groups are contiguous and of size 5
    # irregular groups are also supported,
    group_lasso = GroupLassoCV(groups=groups)
    group_lasso.fit(X, y)

    print("Estimated regularization parameter alpha: %s" % group_lasso.alpha_)

    fig = plt.figure(figsize=(6, 3), constrained_layout=True)
    plt.semilogx(group_lasso.alphas_, group_lasso.mse_path_, ':')
    plt.semilogx(group_lasso.alphas_, group_lasso.mse_path_.mean(axis=-1), 'k',
                 label='Average across the folds', linewidth=2)
    plt.axvline(group_lasso.alpha_, linestyle='--', color='k',
                label='alpha: CV estimate')

    plt.legend()

    plt.xlabel(r'$\alpha$')
    plt.ylabel('Mean square prediction error')
    plt.show(block=False)


    lasso = LassoCV().fit(X, y)





.. image-sg:: /auto_examples/images/sphx_glr_plot_group_lasso_001.png
   :alt: plot group lasso
   :srcset: /auto_examples/images/sphx_glr_plot_group_lasso_001.png
   :class: sphx-glr-single-img


.. rst-class:: sphx-glr-script-out

 .. code-block:: none

    Estimated regularization parameter alpha: 0.2750549815570016




.. GENERATED FROM PYTHON SOURCE LINES 59-60

Show optimal regression vector for prediction, obtained by cross validation

.. GENERATED FROM PYTHON SOURCE LINES 60-74

.. code-block:: Python


    fig = plt.figure(figsize=(8, 3), constrained_layout=True)
    m, s, _ = plt.stem(np.where(w_true)[0], w_true[w_true != 0],
                       label=r"true regression coefficients")
    labels = ["LassoCV-estimated regression coefficients",
              "GroupLassoCV-estimated regression coefficients"]
    colors = [u'#ff7f0e', u'#2ca02c']

    for w, label, color in zip([lasso.coef_, group_lasso.coef_], labels, colors):
        m, s, _ = plt.stem(np.where(w)[0], w[w != 0], label=label, markerfmt='x')
        plt.setp([m, s], color=color)
    plt.xlabel("feature index")
    plt.legend(fontsize=12)
    plt.show(block=False)



.. image-sg:: /auto_examples/images/sphx_glr_plot_group_lasso_002.png
   :alt: plot group lasso
   :srcset: /auto_examples/images/sphx_glr_plot_group_lasso_002.png
   :class: sphx-glr-single-img






.. rst-class:: sphx-glr-timing

   **Total running time of the script:** (0 minutes 0.716 seconds)


.. _sphx_glr_download_auto_examples_plot_group_lasso.py:

.. only:: html

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

    .. container:: sphx-glr-download sphx-glr-download-jupyter

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

    .. container:: sphx-glr-download sphx-glr-download-python

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

    .. container:: sphx-glr-download sphx-glr-download-zip

      :download:`Download zipped: plot_group_lasso.zip <plot_group_lasso.zip>`


.. only:: html

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

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