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
|
"""
=====================
SGD: Weighted samples
=====================
Plot decision function of a weighted dataset, where the size of points
is proportional to its weight.
"""
print __doc__
import numpy as np
import pylab as pl
from sklearn import linear_model
# we create 20 points
np.random.seed(0)
X = np.r_[np.random.randn(10, 2) + [1, 1], np.random.randn(10, 2)]
y = [1] * 10 + [-1] * 10
sample_weight = 100 * np.abs(np.random.randn(20))
# and assign a bigger weight to the last 10 samples
sample_weight[:10] *= 10
# plot the weighted data points
xx, yy = np.meshgrid(np.linspace(-4, 5, 500), np.linspace(-4, 5, 500))
pl.figure()
pl.scatter(X[:, 0], X[:, 1], c=y, s=sample_weight, alpha=0.9,
cmap=pl.cm.bone)
## fit the unweighted model
clf = linear_model.SGDClassifier(alpha=0.01, n_iter=100)
clf.fit(X, y)
Z = clf.decision_function(np.c_[xx.ravel(), yy.ravel()])
Z = Z.reshape(xx.shape)
no_weights = pl.contour(xx, yy, Z, levels=[0], linestyles=['solid'])
## fit the weighted model
clf = linear_model.SGDClassifier(alpha=0.01, n_iter=100)
clf.fit(X, y, sample_weight=sample_weight)
Z = clf.decision_function(np.c_[xx.ravel(), yy.ravel()])
Z = Z.reshape(xx.shape)
samples_weights = pl.contour(xx, yy, Z, levels=[0], linestyles=['dashed'])
pl.legend([no_weights.collections[0], samples_weights.collections[0]],
["no weights", "with weights"], loc="lower left")
pl.xticks(())
pl.yticks(())
pl.show()
|
