.. DO NOT EDIT.
.. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY.
.. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE:
.. "auto_examples/plot_classifier_user_1.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_classifier_user_1.py>`
        to download the full example code

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

.. _sphx_glr_auto_examples_plot_classifier_user_1.py:


===========================================================================
DL8.5 classifier : user specific error function based on supports per class
===========================================================================
PyDL8.5 allows users to write their own error function for classification tasks. 
This class shows how to write an error function that operates on supports per class.
For data that is not supervised, other supervised learning task, the DL85 predictor 
class should be used; check the plot_classifier_user_2.py and plot_cluster_user.py
examples.

.. GENERATED FROM PYTHON SOURCE LINES 11-46




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

 .. code-block:: none

    ##########################################################################################
    #      DL8.5 classifier : user specific error function based on supports per class       #
    ##########################################################################################
    Model building...
    Model built. Duration of building = 0.1119
    Confusion Matrix below
    [[  9  25]
     [  0 129]]
    Accuracy DL8.5 on training set = 0.8243
    Accuracy DL8.5 on test set = 0.8466






|

.. code-block:: default

    import numpy as np
    from sklearn.metrics import confusion_matrix
    from sklearn.model_selection import train_test_split
    from sklearn.metrics import accuracy_score
    import time
    from pydl85 import DL85Classifier

    dataset = np.genfromtxt("../datasets/anneal.txt", delimiter=' ')
    X, y = dataset[:, 1:], dataset[:, 0]
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)


    print("##########################################################################################\n"
          "#      DL8.5 classifier : user specific error function based on supports per class       #\n"
          "##########################################################################################")


    # return the error and the majority class
    def error(sup_iter):
        supports = list(sup_iter)
        maxindex = np.argmax(supports)
        return sum(supports) - supports[maxindex], maxindex


    clf = DL85Classifier(max_depth=2, fast_error_function=error, time_limit=600)
    start = time.perf_counter()
    print("Model building...")
    clf.fit(X_train, y_train)
    duration = time.perf_counter() - start
    print("Model built. Duration of building =", round(duration, 4))
    y_pred = clf.predict(X_test)
    print("Confusion Matrix below")
    print(confusion_matrix(y_test, y_pred))
    print("Accuracy DL8.5 on training set =", round(clf.accuracy_, 4))
    print("Accuracy DL8.5 on test set =", round(accuracy_score(y_test, y_pred), 4))


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

   **Total running time of the script:** ( 0 minutes  0.155 seconds)


.. _sphx_glr_download_auto_examples_plot_classifier_user_1.py:

.. only:: html

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




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

      :download:`Download Python source code: plot_classifier_user_1.py <plot_classifier_user_1.py>`

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

      :download:`Download Jupyter notebook: plot_classifier_user_1.ipynb <plot_classifier_user_1.ipynb>`


.. only:: html

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

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