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

    Click :ref:`here <sphx_glr_download_sphinx_gallery_auto_transparency_xmpl_transparency_lime.py>` to download the full example code or run this example in your browser via Binder
.. rst-class:: sphx-glr-example-title

.. _sphx_glr_sphinx_gallery_auto_transparency_xmpl_transparency_lime.py:


====================
Using LIME Explainer
====================

This example illustrates how to use the LIME tabular explainer to explain a
prediction.

This example shows how to use the tabular LIME implementation --
:class:`fatf.transparency.predictions.surrogate_explainers.TabularBlimeyLime`
-- to explain a prediction of a black-box probabilistic model.


.. image:: /sphinx_gallery_auto/transparency/images/sphx_glr_xmpl_transparency_lime_001.png
    :class: sphx-glr-single-img


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

 Out:

 .. code-block:: none

    {'setosa': {'*petal length (cm)* <= 1.60': 0.9307866199252784,
                '*petal width (cm)* <= 0.30': 0.04259129805843401,
                '*sepal length (cm)* <= 5.10': -0.0027663756624473936,
                '3.00 < *sepal width (cm)* <= 3.30': -0.011263216273426888},
     'versicolor': {'*petal length (cm)* <= 1.60': -0.5593822883064358,
                    '*petal width (cm)* <= 0.30': 0.07065024115814264,
                    '*sepal length (cm)* <= 5.10': 0.025538640983435418,
                    '3.00 < *sepal width (cm)* <= 3.30': 0.0663293593939103},
     'virginica': {'*petal length (cm)* <= 1.60': -0.37140433161884245,
                   '*petal width (cm)* <= 0.30': -0.11324153921657666,
                   '*sepal length (cm)* <= 5.10': -0.022772265320988014,
                   '3.00 < *sepal width (cm)* <= 3.30': -0.05506614312048342}}




|


.. code-block:: default

    # Author: Kacper Sokol <k.sokol@bristol.ac.uk>
    # License: new BSD

    from pprint import pprint

    import fatf

    import fatf.utils.data.datasets as fatf_datasets
    import fatf.utils.models as fatf_models

    import fatf.transparency.predictions.surrogate_explainers as fatf_surrogates

    import fatf.vis.lime as fatf_vis_lime

    print(__doc__)

    # Fix random seed
    fatf.setup_random_seed(42)

    # Load data
    iris_data_dict = fatf_datasets.load_iris()
    iris_X = iris_data_dict['data']
    iris_y = iris_data_dict['target']
    iris_feature_names = iris_data_dict['feature_names'].tolist()
    iris_class_names = iris_data_dict['target_names'].tolist()

    # Train a model
    clf = fatf_models.KNN()
    clf.fit(iris_X, iris_y)

    # Create a LIME explainer
    lime = fatf_surrogates.TabularBlimeyLime(
        iris_X,
        clf,
        feature_names=iris_feature_names,
        class_names=iris_class_names)

    # Choose an index of the instance to be explained
    index_to_explain = 42

    # Explain an instance
    lime_explanation = lime.explain_instance(
        iris_X[index_to_explain, :], samples_number=500)

    # Display the textual explanation
    pprint(lime_explanation)

    # Plot the explanation
    fatf_vis_lime.plot_lime(lime_explanation)


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

   **Total running time of the script:** ( 0 minutes  1.705 seconds)


.. _sphx_glr_download_sphinx_gallery_auto_transparency_xmpl_transparency_lime.py:


.. only :: html

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


  .. container:: binder-badge

    .. image:: https://mybinder.org/badge_logo.svg
      :target: https://mybinder.org/v2/gh/fat-forensics/fat-forensics-doc/master?filepath=notebooks/sphinx_gallery_auto/transparency/xmpl_transparency_lime.ipynb
      :width: 150 px


  .. container:: sphx-glr-download

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



  .. container:: sphx-glr-download

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


.. only:: html

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

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