.. DO NOT EDIT.
.. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY.
.. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE:
.. "auto_examples/linear_model/plot_sgdocsvm_vs_ocsvm.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_linear_model_plot_sgdocsvm_vs_ocsvm.py>`
to download the full example code or to run this example in your browser via JupyterLite or Binder
.. rst-class:: sphx-glr-example-title
.. _sphx_glr_auto_examples_linear_model_plot_sgdocsvm_vs_ocsvm.py:
====================================================================
One-Class SVM versus One-Class SVM using Stochastic Gradient Descent
====================================================================
This example shows how to approximate the solution of
:class:`sklearn.svm.OneClassSVM` in the case of an RBF kernel with
:class:`sklearn.linear_model.SGDOneClassSVM`, a Stochastic Gradient Descent
(SGD) version of the One-Class SVM. A kernel approximation is first used in
order to apply :class:`sklearn.linear_model.SGDOneClassSVM` which implements a
linear One-Class SVM using SGD.
Note that :class:`sklearn.linear_model.SGDOneClassSVM` scales linearly with
the number of samples whereas the complexity of a kernelized
:class:`sklearn.svm.OneClassSVM` is at best quadratic with respect to the
number of samples. It is not the purpose of this example to illustrate the
benefits of such an approximation in terms of computation time but rather to
show that we obtain similar results on a toy dataset.
.. GENERATED FROM PYTHON SOURCE LINES 23-78
.. code-block:: Python
import matplotlib
import matplotlib.lines as mlines
import matplotlib.pyplot as plt
import numpy as np
from sklearn.kernel_approximation import Nystroem
from sklearn.linear_model import SGDOneClassSVM
from sklearn.pipeline import make_pipeline
from sklearn.svm import OneClassSVM
font = {"weight": "normal", "size": 15}
matplotlib.rc("font", **font)
random_state = 42
rng = np.random.RandomState(random_state)
# Generate train data
X = 0.3 * rng.randn(500, 2)
X_train = np.r_[X + 2, X - 2]
# Generate some regular novel observations
X = 0.3 * rng.randn(20, 2)
X_test = np.r_[X + 2, X - 2]
# Generate some abnormal novel observations
X_outliers = rng.uniform(low=-4, high=4, size=(20, 2))
# OCSVM hyperparameters
nu = 0.05
gamma = 2.0
# Fit the One-Class SVM
clf = OneClassSVM(gamma=gamma, kernel="rbf", nu=nu)
clf.fit(X_train)
y_pred_train = clf.predict(X_train)
y_pred_test = clf.predict(X_test)
y_pred_outliers = clf.predict(X_outliers)
n_error_train = y_pred_train[y_pred_train == -1].size
n_error_test = y_pred_test[y_pred_test == -1].size
n_error_outliers = y_pred_outliers[y_pred_outliers == 1].size
# Fit the One-Class SVM using a kernel approximation and SGD
transform = Nystroem(gamma=gamma, random_state=random_state)
clf_sgd = SGDOneClassSVM(
nu=nu, shuffle=True, fit_intercept=True, random_state=random_state, tol=1e-4
)
pipe_sgd = make_pipeline(transform, clf_sgd)
pipe_sgd.fit(X_train)
y_pred_train_sgd = pipe_sgd.predict(X_train)
y_pred_test_sgd = pipe_sgd.predict(X_test)
y_pred_outliers_sgd = pipe_sgd.predict(X_outliers)
n_error_train_sgd = y_pred_train_sgd[y_pred_train_sgd == -1].size
n_error_test_sgd = y_pred_test_sgd[y_pred_test_sgd == -1].size
n_error_outliers_sgd = y_pred_outliers_sgd[y_pred_outliers_sgd == 1].size
.. GENERATED FROM PYTHON SOURCE LINES 79-139
.. code-block:: Python
from sklearn.inspection import DecisionBoundaryDisplay
_, ax = plt.subplots(figsize=(9, 6))
xx, yy = np.meshgrid(np.linspace(-4.5, 4.5, 50), np.linspace(-4.5, 4.5, 50))
X = np.concatenate([xx.ravel().reshape(-1, 1), yy.ravel().reshape(-1, 1)], axis=1)
DecisionBoundaryDisplay.from_estimator(
clf,
X,
response_method="decision_function",
plot_method="contourf",
ax=ax,
cmap="PuBu",
)
DecisionBoundaryDisplay.from_estimator(
clf,
X,
response_method="decision_function",
plot_method="contour",
ax=ax,
linewidths=2,
colors="darkred",
levels=[0],
)
DecisionBoundaryDisplay.from_estimator(
clf,
X,
response_method="decision_function",
plot_method="contourf",
ax=ax,
colors="palevioletred",
levels=[0, clf.decision_function(X).max()],
)
s = 20
b1 = plt.scatter(X_train[:, 0], X_train[:, 1], c="white", s=s, edgecolors="k")
b2 = plt.scatter(X_test[:, 0], X_test[:, 1], c="blueviolet", s=s, edgecolors="k")
c = plt.scatter(X_outliers[:, 0], X_outliers[:, 1], c="gold", s=s, edgecolors="k")
ax.set(
title="One-Class SVM",
xlim=(-4.5, 4.5),
ylim=(-4.5, 4.5),
xlabel=(
f"error train: {n_error_train}/{X_train.shape[0]}; "
f"errors novel regular: {n_error_test}/{X_test.shape[0]}; "
f"errors novel abnormal: {n_error_outliers}/{X_outliers.shape[0]}"
),
)
_ = ax.legend(
[mlines.Line2D([], [], color="darkred", label="learned frontier"), b1, b2, c],
[
"learned frontier",
"training observations",
"new regular observations",
"new abnormal observations",
],
loc="upper left",
)
.. image-sg:: /auto_examples/linear_model/images/sphx_glr_plot_sgdocsvm_vs_ocsvm_001.png
:alt: One-Class SVM
:srcset: /auto_examples/linear_model/images/sphx_glr_plot_sgdocsvm_vs_ocsvm_001.png
:class: sphx-glr-single-img
.. GENERATED FROM PYTHON SOURCE LINES 140-198
.. code-block:: Python
_, ax = plt.subplots(figsize=(9, 6))
xx, yy = np.meshgrid(np.linspace(-4.5, 4.5, 50), np.linspace(-4.5, 4.5, 50))
X = np.concatenate([xx.ravel().reshape(-1, 1), yy.ravel().reshape(-1, 1)], axis=1)
DecisionBoundaryDisplay.from_estimator(
pipe_sgd,
X,
response_method="decision_function",
plot_method="contourf",
ax=ax,
cmap="PuBu",
)
DecisionBoundaryDisplay.from_estimator(
pipe_sgd,
X,
response_method="decision_function",
plot_method="contour",
ax=ax,
linewidths=2,
colors="darkred",
levels=[0],
)
DecisionBoundaryDisplay.from_estimator(
pipe_sgd,
X,
response_method="decision_function",
plot_method="contourf",
ax=ax,
colors="palevioletred",
levels=[0, pipe_sgd.decision_function(X).max()],
)
s = 20
b1 = plt.scatter(X_train[:, 0], X_train[:, 1], c="white", s=s, edgecolors="k")
b2 = plt.scatter(X_test[:, 0], X_test[:, 1], c="blueviolet", s=s, edgecolors="k")
c = plt.scatter(X_outliers[:, 0], X_outliers[:, 1], c="gold", s=s, edgecolors="k")
ax.set(
title="Online One-Class SVM",
xlim=(-4.5, 4.5),
ylim=(-4.5, 4.5),
xlabel=(
f"error train: {n_error_train_sgd}/{X_train.shape[0]}; "
f"errors novel regular: {n_error_test_sgd}/{X_test.shape[0]}; "
f"errors novel abnormal: {n_error_outliers_sgd}/{X_outliers.shape[0]}"
),
)
ax.legend(
[mlines.Line2D([], [], color="darkred", label="learned frontier"), b1, b2, c],
[
"learned frontier",
"training observations",
"new regular observations",
"new abnormal observations",
],
loc="upper left",
)
plt.show()
.. image-sg:: /auto_examples/linear_model/images/sphx_glr_plot_sgdocsvm_vs_ocsvm_002.png
:alt: Online One-Class SVM
:srcset: /auto_examples/linear_model/images/sphx_glr_plot_sgdocsvm_vs_ocsvm_002.png
:class: sphx-glr-single-img
.. rst-class:: sphx-glr-timing
**Total running time of the script:** (0 minutes 0.394 seconds)
.. _sphx_glr_download_auto_examples_linear_model_plot_sgdocsvm_vs_ocsvm.py:
.. only:: html
.. container:: sphx-glr-footer sphx-glr-footer-example
.. container:: binder-badge
.. image:: images/binder_badge_logo.svg
:target: https://mybinder.org/v2/gh/scikit-learn/scikit-learn/1.4.X?urlpath=lab/tree/notebooks/auto_examples/linear_model/plot_sgdocsvm_vs_ocsvm.ipynb
:alt: Launch binder
:width: 150 px
.. container:: lite-badge
.. image:: images/jupyterlite_badge_logo.svg
:target: ../../lite/lab/?path=auto_examples/linear_model/plot_sgdocsvm_vs_ocsvm.ipynb
:alt: Launch JupyterLite
:width: 150 px
.. container:: sphx-glr-download sphx-glr-download-jupyter
:download:`Download Jupyter notebook: plot_sgdocsvm_vs_ocsvm.ipynb <plot_sgdocsvm_vs_ocsvm.ipynb>`
.. container:: sphx-glr-download sphx-glr-download-python
:download:`Download Python source code: plot_sgdocsvm_vs_ocsvm.py <plot_sgdocsvm_vs_ocsvm.py>`
.. include:: plot_sgdocsvm_vs_ocsvm.recommendations
.. only:: html
.. rst-class:: sphx-glr-signature
`Gallery generated by Sphinx-Gallery <https://sphinx-gallery.github.io>`_