.. DO NOT EDIT.
.. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY.
.. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE:
.. "auto_examples/Calibration/IsotonicRegression.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_Calibration_IsotonicRegression.py>`
        to download the full example code.

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

.. _sphx_glr_auto_examples_Calibration_IsotonicRegression.py:


Isotonic regression
=======================

This script showcases the use of IsotonicRegression for predicting monotonic relationships.

.. GENERATED FROM PYTHON SOURCE LINES 7-39



.. image-sg:: /auto_examples/Calibration/images/sphx_glr_IsotonicRegression_001.png
   :alt: IsotonicRegression
   :srcset: /auto_examples/Calibration/images/sphx_glr_IsotonicRegression_001.png
   :class: sphx-glr-single-img


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

 .. code-block:: none

    tensor([1.3007, 1.1584, 1.1584, 1.0047, 1.3007, 1.2268, 1.6313, 1.1178, 1.1126,
            1.3007, 1.5274, 1.0047, 1.1584, 0.9212, 1.9415, 1.1178, 1.5274, 0.8849,
            1.0805, 1.1584])
    [1.30070541 1.1584315  1.1584315  1.00466986 1.30070541 1.22684785
     1.63132361 1.11777065 1.11262473 1.30070541 1.52742959 1.00466986
     1.1584315  0.92119819        nan 1.11777065 1.52742959        nan
     1.08046234 1.1584315 ]






|

.. code-block:: Python

    import torch
    import matplotlib.pyplot as plt
    from sklearn.isotonic import IsotonicRegression as sk_isotonic

    from DLL.Data.Preprocessing import data_split
    from DLL.MachineLearning.SupervisedLearning.Calibration import IsotonicRegression


    torch.manual_seed(0)
    X = torch.linspace(0, 1, 100)
    y = X ** 2 + 1 + 0.1 * torch.randn_like(X)
    Xtrain, ytrain, _, _, Xtest, ytest = data_split(X, y, train_split=0.8, validation_split=0)

    increasing = True
    if not increasing: ytrain, ytest = -ytrain, -ytest

    model = IsotonicRegression()
    model.fit(Xtrain, ytrain, increasing=increasing)
    ypred = model.predict(Xtest)
    print(ypred)

    model = sk_isotonic(increasing=increasing)
    model.fit(Xtrain, ytrain)
    sk_ypred = model.predict(Xtest)
    print(sk_ypred)

    plt.scatter(Xtrain, ytrain, label="Train", alpha=0.5)
    plt.scatter(Xtest, ytest, label="Test", alpha=0.5)
    plt.scatter(Xtest, ypred, label="Pred", alpha=0.5)
    plt.scatter(Xtest, sk_ypred, label="SKlearn pred", alpha=0.5)
    plt.legend()
    plt.show()


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

   **Total running time of the script:** (0 minutes 2.088 seconds)


.. _sphx_glr_download_auto_examples_Calibration_IsotonicRegression.py:

.. only:: html

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

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

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

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

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

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

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


.. only:: html

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

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