53 lines
1.3 KiB
Python
53 lines
1.3 KiB
Python
"""
|
|
=================================================
|
|
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.
|
|
"""
|
|
print(__doc__)
|
|
|
|
import numpy as np
|
|
import pylab as pl
|
|
from sklearn import svm
|
|
|
|
# we create 40 separable points
|
|
rng = np.random.RandomState(0)
|
|
n_samples_1 = 1000
|
|
n_samples_2 = 100
|
|
X = np.r_[1.5 * rng.randn(n_samples_1, 2),
|
|
0.5 * rng.randn(n_samples_2, 2) + [2, 2]]
|
|
y = [0] * (n_samples_1) + [1] * (n_samples_2)
|
|
|
|
# fit the model and get the separating hyperplane
|
|
clf = svm.SVC(kernel='linear', C=1.0)
|
|
clf.fit(X, y)
|
|
|
|
w = clf.coef_[0]
|
|
a = -w[0] / w[1]
|
|
xx = np.linspace(-5, 5)
|
|
yy = a * xx - clf.intercept_[0] / w[1]
|
|
|
|
|
|
# get the separating hyperplane using weighted classes
|
|
wclf = svm.SVC(kernel='linear', class_weight={1: 10})
|
|
wclf.fit(X, y)
|
|
|
|
ww = wclf.coef_[0]
|
|
wa = -ww[0] / ww[1]
|
|
wyy = wa * xx - wclf.intercept_[0] / ww[1]
|
|
|
|
# plot separating hyperplanes and samples
|
|
h0 = pl.plot(xx, yy, 'k-', label='no weights')
|
|
h1 = pl.plot(xx, wyy, 'k--', label='with weights')
|
|
pl.scatter(X[:, 0], X[:, 1], c=y, cmap=pl.cm.Paired)
|
|
pl.legend()
|
|
|
|
pl.axis('tight')
|
|
pl.show()
|