.. DO NOT EDIT.
.. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY.
.. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE:
.. "python/examples/generalized_linear_model.py"
.. LINE NUMBERS ARE GIVEN BELOW.

.. only:: html

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

        :ref:`Go to the end <sphx_glr_download_python_examples_generalized_linear_model.py>`
        to download the full example code.

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

.. _sphx_glr_python_examples_generalized_linear_model.py:


Demo for GLM
============

.. GENERATED FROM PYTHON SOURCE LINES 5-52

.. code-block:: Python

    import os

    import xgboost as xgb

    ##
    #  this script demonstrate how to fit generalized linear model in xgboost
    #  basically, we are using linear model, instead of tree for our boosters
    ##
    CURRENT_DIR = os.path.dirname(__file__)
    dtrain = xgb.DMatrix(
        os.path.join(CURRENT_DIR, "../data/agaricus.txt.train?format=libsvm")
    )
    dtest = xgb.DMatrix(
        os.path.join(CURRENT_DIR, "../data/agaricus.txt.test?format=libsvm")
    )
    # change booster to gblinear, so that we are fitting a linear model
    # alpha is the L1 regularizer
    # lambda is the L2 regularizer
    # you can also set lambda_bias which is L2 regularizer on the bias term
    param = {
        "objective": "binary:logistic",
        "booster": "gblinear",
        "alpha": 0.0001,
        "lambda": 1,
    }

    # normally, you do not need to set eta (step_size)
    # XGBoost uses a parallel coordinate descent algorithm (shotgun),
    # there could be affection on convergence with parallelization on certain cases
    # setting eta to be smaller value, e.g 0.5 can make the optimization more stable
    # param['eta'] = 1

    ##
    # the rest of settings are the same
    ##
    watchlist = [(dtest, "eval"), (dtrain, "train")]
    num_round = 4
    bst = xgb.train(param, dtrain, num_round, watchlist)
    preds = bst.predict(dtest)
    labels = dtest.get_label()
    print(
        "error=%f"
        % (
            sum(1 for i in range(len(preds)) if int(preds[i] > 0.5) != labels[i])
            / float(len(preds))
        )
    )


.. _sphx_glr_download_python_examples_generalized_linear_model.py:

.. only:: html

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

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

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

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

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

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

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


.. only:: html

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

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