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

.. only:: html

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

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

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

.. _sphx_glr_examples_Builtin_logistic_regression.py:


Logistic regression
=====================
This example illustrates the use of the :class:`skwdro.linear_models.LogisticRegression` class and the influence of the radius.

.. GENERATED FROM PYTHON SOURCE LINES 7-18

.. code-block:: Python

    import numpy as np
    import matplotlib.pyplot as plt

    from sklearn.datasets import make_blobs, make_moons
    from sklearn.metrics import accuracy_score
    from sklearn.model_selection import train_test_split

    from skwdro.linear_models import LogisticRegression

    from utils.classifier_comparison import plot_classifier_comparison








.. GENERATED FROM PYTHON SOURCE LINES 19-21

Setup
~~~~~

.. GENERATED FROM PYTHON SOURCE LINES 21-49

.. code-block:: Python


    n = 200 # Total number of samples
    n_train = n // 2 # Number of training samples
    n_test = n - n_train # Number of test samples

    datasets = []

    # Moons dataset
    dataset = make_moons(n_samples=n, noise=0.1)
    Xtrain, Xtest, ytrain, ytest = train_test_split(*dataset, train_size=n_train, test_size=n_test)
    train_dataset, test_dataset = (Xtrain, ytrain), (Xtest, ytest)
    datasets.append((train_dataset, test_dataset))

    # Fix centers for blobs dataset
    _, _, centers = make_blobs(centers=2, return_centers=True) # type: ignore

    # Blobs dataset with std=2
    dataset = make_blobs(n_samples=n, centers=centers, cluster_std=2)
    Xtrain, Xtest, ytrain, ytest = train_test_split(*dataset, train_size=n_train, test_size=n_test)
    train_dataset, test_dataset = (Xtrain, ytrain), (Xtest, ytest)
    datasets.append((train_dataset, test_dataset))

    # Blobs dataset with std=4
    dataset = make_blobs(n_samples=n, centers=centers, cluster_std=4)
    Xtrain, Xtest, ytrain, ytest = train_test_split(*dataset, train_size=n_train, test_size=n_test)
    train_dataset, test_dataset = (Xtrain, ytrain), (Xtest, ytest)
    datasets.append((train_dataset, test_dataset))








.. GENERATED FROM PYTHON SOURCE LINES 50-52

WDRO classifiers
~~~~~~~~~~~~~~~~

.. GENERATED FROM PYTHON SOURCE LINES 52-58

.. code-block:: Python


    rhos = [10**i for i in range(-3, 0)]
    classifiers = []
    for rho in rhos:
        classifiers.append(LogisticRegression(rho=rho))








.. GENERATED FROM PYTHON SOURCE LINES 59-61

Make plot
~~~~~~~~~

.. GENERATED FROM PYTHON SOURCE LINES 61-65

.. code-block:: Python


    names = [f"$\\rho={rho}$" for rho in rhos]
    plot_classifier_comparison(names, classifiers, datasets)




.. image-sg:: /examples/Builtin/images/sphx_glr_logistic_regression_001.png
   :alt: Training data, Testing data, $\rho=0.001$, $\rho=0.01$, $\rho=0.1$
   :srcset: /examples/Builtin/images/sphx_glr_logistic_regression_001.png
   :class: sphx-glr-single-img


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

 .. code-block:: none

    Dataset 0, Classifier $\rho=0.001$: Test Acc. 85%, F1 83%
    Dataset 0, Classifier $\rho=0.01$: Test Acc. 85%, F1 83%
    Dataset 0, Classifier $\rho=0.1$: Test Acc. 85%, F1 83%
    Dataset 1, Classifier $\rho=0.001$: Test Acc. 93%, F1 93%
    Dataset 1, Classifier $\rho=0.01$: Test Acc. 93%, F1 93%
    Dataset 1, Classifier $\rho=0.1$: Test Acc. 93%, F1 93%
    Dataset 2, Classifier $\rho=0.001$: Test Acc. 77%, F1 78%
    Dataset 2, Classifier $\rho=0.01$: Test Acc. 77%, F1 78%
    Dataset 2, Classifier $\rho=0.1$: Test Acc. 77%, F1 78%





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

   **Total running time of the script:** (1 minutes 37.088 seconds)


.. _sphx_glr_download_examples_Builtin_logistic_regression.py:

.. only:: html

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

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

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

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

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

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

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


.. only:: html

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

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