- 训练算法:使用梯度上升找到最佳参数
- 分析数据:画出决策边界
- 随机梯度上升算法
- 原理
- 伪代码
- 程序清单:随机梯度上升算法
- 改进的随机梯度上升算法
#Logistic回归梯度上升优化算法
import numpy as np
def loadDataSet():
dataMat=[]; labelMat=[]
fr=open('testSet.txt')
for line in fr.readlines():
lineArr=line.strip().split()
dataMat.append([1.0,float(lineArr[0]),float(lineArr[1])])
labelMat.append(int(lineArr[2]))
return dataMat,labelMat
def sigmoid(inX):
return 1.0/(1+np.exp(-inX))
def gradAscent(dataMatIn,classLabels):
dataMatrix=np.mat(dataMatIn)
labelMat=np.mat(classLabels).transpose()
m,n=np.shape(dataMatrix)
alpha=0.001
maxCycles=500
weights=np.ones((n,1))
for k in range(maxCycles):
h=sigmoid(dataMatrix*weights)
error=(labelMat-h)
weights=weights+alpha*dataMatrix.transpose()*error
return weights
分析数据:画出决策边界
def plotBestFit(weights):
import matplotlib.pyplot as plt
dataMat,labelMat=loadDataSet()
dataArr=np.array(dataMat)
n=np.shape(dataArr)[0]
xcord1=[]; ycord1=[]
xcord2=[]; ycord2=[]
for i in range(n):
if(int(labelMat[i])==1):
xcord1.append(dataArr[i,1]); ycord1.append(dataArr[i,2])
else:
xcord2.append(dataArr[i,1]); ycord2.append(dataArr[i,2])
fig=plt.figure()
ax=fig.add_subplot(111)
ax.scatter(xcord1,ycord1,s=30,c='red',marker='s')
ax.scatter(xcord2,ycord2,s=30,c='green')
x=np.arange(-3.0,3.0,0.1)
y=(-weights[0]-weights[1]*x)/weights[2]
ax.plot(x,y)
plt.xlabel('X1'); plt.ylabel('X2');
plt.show()
随机梯度上升算法
原理
梯度上升算法每次更新回归系数时,要遍历整个数据集,时间复杂度较高。一种改进方法是一次只用一个样本点来更新回归系数,该方法称为随机梯度上升算法。
伪代码所有回归系数初始化为1
对数据集中每个样本:
计算该样本的梯度
使用alpha*gradient更新回归系数值
返回回归系数值
程序清单:随机梯度上升算法
def stocGradAscent0(dataMatrix,classLabels):
m,n=np.shape(dataMatrix)
alpha=0.1
weights=np.ones(n)
for i in range(m):
h=sigmoid(np.sum(dataMatrix[i]*weights))
error=classLabels[i]-h
weights=weights+alpha*error*dataMatrix[i]
return weights
该拟合直线并非最佳分类线
def stocGradAscent1(dataMatrix,classLabels,numIter=150):
m,n=np.shape(dataMatrix)
weights=np.ones(n)
for j in range(numIter):
dataIndex=np.array(range(m))
for i in range(m):
alpha=4/(1.0+i+j)+0.01
randIndex=int(np.random.uniform(0,m))
h=sigmoid(sum(dataMatrix[randIndex]*weights))
error=classLabels[randIndex]-h
weights=weights+alpha*error*dataMatrix[randIndex]
np.delete(dataIndex,randIndex)
return weights
欢迎分享,转载请注明来源:内存溢出
评论列表(0条)