SVM: 不平衡分类问题的分割超平面




使用 SGDClassifier(loss="hinge") 替换 SVC(kernel="linear") 以后, 这个例子仍然可以工作。 设置 SGDClassifier 类的 loss 参数 为 hinge 将产生与带有线性核的SVC一样的行为。

比如尝试用下面的估计器实例替换 SVC:

clf = SGDClassifier(n_iter=100, alpha=0.01)

import numpy as np
import matplotlib.pyplot as plt
from sklearn import svm
from sklearn.datasets import make_blobs

# 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],
                  random_state=0, shuffle=False)

# fit the model and get the separating hyperplane
clf = svm.SVC(kernel='linear', C=1.0), y)

# fit the model and get the separating hyperplane using weighted classes
wclf = svm.SVC(kernel='linear', class_weight={1: 10}), y)

# plot the samples
plt.scatter(X[:, 0], X[:, 1], c=y,, edgecolors='k')

# plot the decision functions for both classifiers
ax = plt.gca()
xlim = ax.get_xlim()
ylim = ax.get_ylim()

# create grid to evaluate model
xx = np.linspace(xlim[0], xlim[1], 30)
yy = np.linspace(ylim[0], ylim[1], 30)
YY, XX = np.meshgrid(yy, xx)
xy = np.vstack([XX.ravel(), YY.ravel()]).T

# get the separating hyperplane
Z = clf.decision_function(xy).reshape(XX.shape)

# plot decision boundary and margins
a = ax.contour(XX, YY, Z, colors='k', levels=[0], alpha=0.5, linestyles=['-'])

# get the separating hyperplane for weighted classes
Z = wclf.decision_function(xy).reshape(XX.shape)

# plot decision boundary and margins for weighted classes
b = ax.contour(XX, YY, Z, colors='r', levels=[0], alpha=0.5, linestyles=['-'])

plt.legend([a.collections[0], b.collections[0]], ["non weighted", "weighted"],
           loc="upper right")

Total running time of the script: ( 0 minutes 0.051 seconds)

Gallery generated by Sphinx-Gallery