svm线性分类代码，可直接运行

#encoding=utf-8
"""
@author=wanggang
data:1.5,2020
"""
import numpy as np
import matplotlib.pyplot as plt
from sklearn import svm
x_data=np.r_[np.random.randn(20,2)-[-2,2],np.random.randn(20,2)+[2,2]]
y_data=[0]*20+[1]*20
#print(y_data)
plt.scatter(x_data[:,0],x_data[:,1],c=y_data)
plt.show()
#_________________________________
#model
model=svm.SVC(kernel='linear')
model.fit(x_data,y_data)
print(model.coef_)
print(model.intercept_)#这是截距
#获取分离平面
plt.scatter(x_data[:,0],x_data[:,1],c=y_data)
x_test=np.array([[-5],[5]])
d=-model.intercept_/model.coef_[0][1]
k=-model.coef_[0][0]/model.coef_[0][1]
y_text=d+k*x_test
plt.plot(x_test,y_text,'k')
plt.show()
#输出支持向量------------
print(model.support_vectors_)
b1=model.support_vectors_[0]
y_down=k*x_test+(b1[1]-k*b1[0])
b2=model.support_vectors_[-1]#这里是-1
y_up=k*x_test+(b2[1]-k*b2[0])
plt.scatter(x_data[:,0],x_data[:,1],c=y_data)
x_test=np.array([[-5],[5]])
d=-model.intercept_/model.coef_[0][1]
k=-model.coef_[0][0]/model.coef_[0][1]
y_text=d+k*x_test
plt.plot(x_test,y_text,'k')
plt.plot(x_test,y_down,'r--')
plt.plot(x_test,y_up,'b--')
plt.show()