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

    Click :ref:`here <sphx_glr_download_auto_examples_plot_2_example_added_gridsearchcv.py>` to download the full example code
.. rst-class:: sphx-glr-example-title

.. _sphx_glr_auto_examples_plot_2_example_added_gridsearchcv.py:


.. _example2:

Second example: :class:`GridSearchCV` demonstration
----------------------------------------------------

This example shows how to use :class:`GridSearchCv` with **PipeGraph** to effectively fit the best model across a number of hyperparameters.
It is equivalent to use :class:`GridSearchCv` with :class:`Pipeline`. More complicated cases are shown in the following examples. In this second example we wanted to show how to fit a :class:`GridSearchCV` in a yet simple scenario.

Steps of the **PipeGraph**:

- **scaler**: a preprocessing step using a :class:`MinMaxScaler` object
- **polynomial_features**: a transformer step
- **linear_model**: the :class:`LinearRegression` object we want to fit and use for predict.

.. figure:: https://raw.githubusercontent.com/mcasl/PipeGraph/master/examples/images/Diapositiva2.png

    Figure 1. PipeGraph diagram showing the steps and their connections


Firstly, we import the necessary libraries and create some artificial data.



.. code-block:: python


    import numpy as np
    from sklearn.preprocessing import MinMaxScaler
    from sklearn.preprocessing import PolynomialFeatures
    from sklearn.linear_model import LinearRegression
    from sklearn.model_selection import GridSearchCV
    from pipegraph.base import PipeGraph

    import matplotlib.pyplot as plt

    X = 2*np.random.rand(100,1)-1
    y = 40 * X**5 + 3*X*2 +  3*X + 3*np.random.randn(100,1)

    scaler = MinMaxScaler()
    polynomial_features = PolynomialFeatures()
    linear_model = LinearRegression()







Secondly, we define the steps and a ``param_grid`` dictionary as specified by :class:`GridSearchCV`.
In this case we just want to explore a few possibilities varying the degree of the polynomials and whether to use or not an intercept at the linear model.



.. code-block:: python


    steps = [('scaler', scaler),
             ('polynomial_features', polynomial_features),
             ('linear_model', linear_model)]

    param_grid = {'polynomial_features__degree': range(1, 11),
                  'linear_model__fit_intercept': [True, False]}







Now, we use ``PipeGraphRegressor`` as estimator for :class:`GridSearchCV` and perform the ``fit`` and ``predict`` operations.



.. code-block:: python


    pgraph = PipeGraph(steps=steps)
    grid_search_regressor = GridSearchCV(estimator=pgraph, param_grid=param_grid, refit=True)
    grid_search_regressor.fit(X, y)
    y_pred = grid_search_regressor.predict(X)

    plt.scatter(X, y)
    plt.scatter(X, y_pred)
    plt.show()


    coef = grid_search_regressor.best_estimator_.get_params()['linear_model'].coef_
    degree = grid_search_regressor.best_estimator_.get_params()['polynomial_features'].degree

    print('Information about the parameters of the best estimator: \n degree: {} \n coefficients: {} '.format(degree, coef))




.. image:: /auto_examples/images/sphx_glr_plot_2_example_added_gridsearchcv_001.png
    :class: sphx-glr-single-img


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

 Out:

 .. code-block:: none

    Information about the parameters of the best estimator: 
     degree: 5 
     coefficients: [[  -44.9706866    363.27350854 -1281.17106722  2402.3058455
      -2319.31529496   925.19838541]]


This example showed how to use :class:`GridSearchCV` with :class:`PipeGraphRegressor` in a simple linear workflow.
:ref:`Next example <example3>` provides detail on how to proceed with a non linear case.


**Total running time of the script:** ( 0 minutes  0.201 seconds)


.. _sphx_glr_download_auto_examples_plot_2_example_added_gridsearchcv.py:


.. only :: html

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



  .. container:: sphx-glr-download

     :download:`Download Python source code: plot_2_example_added_gridsearchcv.py <plot_2_example_added_gridsearchcv.py>`



  .. container:: sphx-glr-download

     :download:`Download Jupyter notebook: plot_2_example_added_gridsearchcv.ipynb <plot_2_example_added_gridsearchcv.ipynb>`


.. only:: html

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

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