1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
|
"""
=================================================
SVM: Separating hyperplane for unbalanced classes
=================================================
Find the optimal separating hyperplane using an SVC for classes that
are unbalanced.
We first find the separating plane with a plain SVC and then plot
(dashed) the separating hyperplane with automatically correction for
unbalanced classes.
.. currentmodule:: sklearn.linear_model
.. note::
This example will also work by replacing ``SVC(kernel="linear")``
with ``SGDClassifier(loss="hinge")``. Setting the ``loss`` parameter
of the :class:`SGDClassifier` equal to ``hinge`` will yield behaviour
such as that of a SVC with a linear kernel.
For example try instead of the ``SVC``::
clf = SGDClassifier(n_iter=100, alpha=0.01)
"""
import matplotlib.pyplot as plt
from sklearn import svm
from sklearn.datasets import make_blobs
from sklearn.inspection import DecisionBoundaryDisplay
# we create two clusters of random points
n_samples_1 = 1000
n_samples_2 = 100
centers = [[0.0, 0.0], [2.0, 2.0]]
clusters_std = [1.5, 0.5]
X, y = make_blobs(
n_samples=[n_samples_1, n_samples_2],
centers=centers,
cluster_std=clusters_std,
random_state=0,
shuffle=False,
)
# fit the model and get the separating hyperplane
clf = svm.SVC(kernel="linear", C=1.0)
clf.fit(X, y)
# fit the model and get the separating hyperplane using weighted classes
wclf = svm.SVC(kernel="linear", class_weight={1: 10})
wclf.fit(X, y)
# plot the samples
plt.scatter(X[:, 0], X[:, 1], c=y, cmap=plt.cm.Paired, edgecolors="k")
# plot the decision functions for both classifiers
ax = plt.gca()
disp = DecisionBoundaryDisplay.from_estimator(
clf,
X,
plot_method="contour",
colors="k",
levels=[0],
alpha=0.5,
linestyles=["-"],
ax=ax,
)
# plot decision boundary and margins for weighted classes
wdisp = DecisionBoundaryDisplay.from_estimator(
wclf,
X,
plot_method="contour",
colors="r",
levels=[0],
alpha=0.5,
linestyles=["-"],
ax=ax,
)
plt.legend(
[disp.surface_.collections[0], wdisp.surface_.collections[0]],
["non weighted", "weighted"],
loc="upper right",
)
plt.show()
|
