python机器学习学习笔记（四）

支持向量机分类

1.定义训练集绘制决策空间

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

x = np.array([[1,3],[1,2],[1,1.5],[1.5,2],[2,3],[2.5,1.5],[2,1],[3,1],[3,2],[3.5,1],[3.5,3]])
y = [0]*6+[1]*5

plt.scatter(x[:,0],x[:,1],c=y,s=50,alpha=0.9)
plt.show()

2.用SVC()构造函数定义模型，调用fit()函数训练模型，用decision_function()函数绘制决策边界，并绘图

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

x = np.array([[1,3],[1,2],[1,1.5],[1.5,2],[2,3],[2.5,1.5],[2,1],[3,1],[3,2],[3.5,1],[3.5,3]])
y = [0]*6+[1]*5
svc = svm.SVC(kernel='linear').fit(x,y)
X,Y = np.mgrid[0:4:200j,0:4:200j]
Z = svc._decision_function(np.c_[X.ravel(),Y.ravel()])
Z = Z.reshape(X.shape)

plt.contourf(X,Y,Z>0,alpha=0.4)
plt.contour(X,Y,Z,colors=['k'],lineStyle=['-'],levels=[0])
plt.scatter(x[:,0],x[:,1],c=y,s=50,alpha=0.9)
plt.show()

3.至此模型训练完成，用predict()函数进行预测

a = svc.predict([[1.5,2.5]])
print(a)
#返回[0]
b = svc.predict([[2.5,1]])
print(b)
#返回[1]

4.正则化

参数C值越小，分界线两侧得数据点考虑得越多，C值越大，只考虑分界线附近得数据点（C默认值为1）

C=1时

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

x = np.array([[1,3],[1,2],[1,1.5],[1.5,2],[2,3],[2.5,1.5],[2,1],[3,1],[3,2],[3.5,1],[3.5,3]])
y = [0]*6+[1]*5
svc = svm.SVC(kernel='linear',C=1).fit(x,y)
X,Y = np.mgrid[0:4:200j,0:4:200j]
Z = svc._decision_function(np.c_[X.ravel(),Y.ravel()])
Z = Z.reshape(X.shape)

plt.contourf(X,Y,Z>0,alpha=0.4)
plt.contour(X,Y,Z,colors=['k','k','k'],linestyles=['--','-','--'],levels=[-1,0,1])
plt.scatter(svc.support_vectors_[:,0],svc.support_vectors_[:,1],s=120,facecolors='r')  #绘制参与计算间隔的数据点
plt.scatter(x[:,0],x[:,1],c=y,s=50,alpha=0.9)
plt.show()

C=0.1时

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

x = np.array([[1,3],[1,2],[1,1.5],[1.5,2],[2,3],[2.5,1.5],[2,1],[3,1],[3,2],[3.5,1],[3.5,3]])
y = [0]*6+[1]*5
svc = svm.SVC(kernel='linear',C=0.1).fit(x,y)
X,Y = np.mgrid[0:4:200j,0:4:200j]
Z = svc._decision_function(np.c_[X.ravel(),Y.ravel()])
Z = Z.reshape(X.shape)

plt.contourf(X,Y,Z>0,alpha=0.4)
plt.contour(X,Y,Z,colors=['k','k','k'],linestyles=['--','-','--'],levels=[-1,0,1])
plt.scatter(svc.support_vectors_[:,0],svc.support_vectors_[:,1],s=120,facecolors='r')  #绘制参与计算间隔的数据点
plt.scatter(x[:,0],x[:,1],c=y,s=50,alpha=0.9)
plt.show()

---

参考:

法比奥·内利. Python数据分析实战：第2版.北京：人民邮电出版社, 2019.11.