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

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

.. _sphx_glr_auto_examples_rvm_for_regression.py:


=========================================================
RVM for regression
=========================================================
Based on https://github.com/ctgk/PRML/blob/master/notebooks/ch07_Sparse_Kernel_Machines.ipynb


.. code-block:: default

    print(__doc__)

    import matplotlib.pyplot as plt
    import numpy as np

    from sklearn_rvm import EMRVR


    def create_toy_data(n=20):
        x = np.linspace(0, 1, n)
        t = np.sin(2 * np.pi * x) + np.random.normal(scale=0.1, size=n)
        return x, t


    x_train, y_train = create_toy_data(n=50)
    x = np.linspace(0, 1, 100)

    model = EMRVR(kernel="rbf")
    model.fit(x_train[:, None], y_train)

    y, y_std = model.predict(x[:, None], return_std=True)

    plt.scatter(x_train, y_train, facecolor="none", edgecolor="g", label="training")
    plt.scatter(x[model.relevance_], y[model.relevance_], s=100, facecolor="none", edgecolor="b", label="relevance vector")
    plt.plot(x[:, None], y, color="r", label="predict mean")
    plt.fill_between(x, y - y_std, y + y_std, color="pink", alpha=0.2, label="predict std.")
    plt.legend(loc="best")
    plt.show()


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

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


.. _sphx_glr_download_auto_examples_rvm_for_regression.py:


.. only :: html

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



  .. container:: sphx-glr-download

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



  .. container:: sphx-glr-download

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


.. only:: html

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

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