SGD: Maximum margin separating hyperplane程序解析

 

 

1、np.ndenumerate、np.ndindex

import numpy as np

Z=np.arange(6).reshape(2,3)
Z

array([[0, 1, 2],
       [3, 4, 5]])

for index,value in np.ndenumerate(Z):
    print(index,value)

(0, 0) 0
(0, 1) 1
(0, 2) 2
(1, 0) 3
(1, 1) 4
(1, 2) 5

for index in np.ndindex(Z.shape):
    print(index,Z[index])

(0, 0) 0
(0, 1) 1
(0, 2) 2
(1, 0) 3
(1, 1) 4
(1, 2) 5

for index in np.ndindex(2,2,3):
    print(index)

 

(0, 0, 0)
(0, 0, 1)
(0, 0, 2)
(0, 1, 0)
(0, 1, 1)
(0, 1, 2)
(1, 0, 0)
(1, 0, 1)
(1, 0, 2)
(1, 1, 0)
(1, 1, 1)
(1, 1, 2)

numpy.meshgrid()——生成网格点坐标矩阵

 

坐标矩阵——横坐标矩阵X XX中的每个元素，与纵坐标矩阵Y YY中对应位置元素，共同构成一个点的完整坐标

 

contour画等高线图

以z=x^2+y^2为例

import numpy as np
import matplotlib.pyplot as plt

x=np.linspace(-10,10,100)
y=np.linspace(-10,10,100)
xx,yy=np.meshgrid(x,y)

Z=xx**2+yy**2
plt.contour(xx,yy,Z)
plt.show()

 

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


#生成一个50个样本点的数据集
X,y=make_blobs(n_samples=50,centers=2,random_state=0,cluster_std=0.6)

#训练模型
clf=SGDClassifier(loss='hinge',alpha=0.01,max_iter=200)
clf.fit(X,y)

print(clf.decision_function([[-1,-1]]))

#画决策超平面
xx=np.linspace(-1,5,10)
yy=np.linspace(-1,5,10)

X1,X2=np.meshgrid(xx,yy)

Z=np.zeros(X1.shape)

for (i,j),value in np.ndenumerate(X1):
    x1=value
    x2=X2[i,j]
    p=clf.decision_function([[x1,x2]])
    Z[i,j]=p[0]
        
levels=[-1.0,0,1.0]
plt.scatter(X[:,0],X[:,1],c=y,cmap=plt.cm.Paired,edgecolor='black')
linestyles=['dashed','solid','dashed']
plt.contour(X1,X2,Z,levels=levels,linestyles=linestyles,colors='k')

plt.axis('tight')
plt.show()

 

结果