"""
=================================================
Novelty detection with Local Outlier Factor (LOF)
=================================================
The Local Outlier Factor (LOF) algorithm is an unsupervised anomaly detection
method which computes the local density deviation of a given data point with
respect to its neighbors. It considers as outliers the samples that have a
substantially lower density than their neighbors. This example shows how to
use LOF for novelty detection. Note that when LOF is used for novelty
detection you MUST not use predict, decision_function and score_samples on the
training set as this would lead to wrong results. You must only use these
methods on new unseen data (which are not in the training set). See
:ref:`User Guide `: for details on the difference between
outlier detection and novelty detection and how to use LOF for outlier
detection.
The number of neighbors considered, (parameter n_neighbors) is typically
set 1) greater than the minimum number of samples a cluster has to contain,
so that other samples can be local outliers relative to this cluster, and 2)
smaller than the maximum number of close by samples that can potentially be
local outliers.
In practice, such informations are generally not available, and taking
n_neighbors=20 appears to work well in general.
"""
import numpy as np
import matplotlib
import matplotlib.pyplot as plt
from sklearn.neighbors import LocalOutlierFactor
print(__doc__)
np.random.seed(42)
xx, yy = np.meshgrid(np.linspace(-5, 5, 500), np.linspace(-5, 5, 500))
# Generate normal (not abnormal) training observations
X = 0.3 * np.random.randn(100, 2)
X_train = np.r_[X + 2, X - 2]
# Generate new normal (not abnormal) observations
X = 0.3 * np.random.randn(20, 2)
X_test = np.r_[X + 2, X - 2]
# Generate some abnormal novel observations
X_outliers = np.random.uniform(low=-4, high=4, size=(20, 2))
# fit the model for novelty detection (novelty=True)
clf = LocalOutlierFactor(n_neighbors=20, novelty=True, contamination=0.1)
clf.fit(X_train)
# DO NOT use predict, decision_function and score_samples on X_train as this
# would give wrong results but only on new unseen data (not used in X_train),
# e.g. X_test, X_outliers or the meshgrid
y_pred_test = clf.predict(X_test)
y_pred_outliers = clf.predict(X_outliers)
n_error_test = y_pred_test[y_pred_test == -1].size
n_error_outliers = y_pred_outliers[y_pred_outliers == 1].size
# plot the learned frontier, the points, and the nearest vectors to the plane
Z = clf.decision_function(np.c_[xx.ravel(), yy.ravel()])
Z = Z.reshape(xx.shape)
plt.title("Novelty Detection with LOF")
plt.contourf(xx, yy, Z, levels=np.linspace(Z.min(), 0, 7), cmap=plt.cm.PuBu)
a = plt.contour(xx, yy, Z, levels=[0], linewidths=2, colors='darkred')
plt.contourf(xx, yy, Z, levels=[0, Z.max()], colors='palevioletred')
s = 40
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')
plt.axis('tight')
plt.xlim((-5, 5))
plt.ylim((-5, 5))
plt.legend([a.collections[0], b1, b2, c],
["learned frontier", "training observations",
"new regular observations", "new abnormal observations"],
loc="upper left",
prop=matplotlib.font_manager.FontProperties(size=11))
plt.xlabel(
"errors novel regular: %d/40 ; errors novel abnormal: %d/40"
% (n_error_test, n_error_outliers))
plt.show()