1.训练算法:使用梯度上升找到最佳参数
梯度上升法的伪代码如下:
每个回归系数初始化为1
重复R次:
计算整个数据集的梯度
使用alpha*gradient更新回归系数的向量
返回回归系数
下面的代码是梯度上升算法的具体实现。
#Logistic回归梯度上升优化算法
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
dataArr,labelMat=loadDataSet()
def sigmoid(inX):
return 1.0/(1+exp(-inX))
def gradAscent(dataMatIn,classLabels):
dataMatrix=mat(dataMatIn) #转换为Numpy矩阵数据类型
labelMat=mat(classLabels).transpose()
m,n=shape(dataMatrix)
alpha=0.001
maxCycles=500
weights=ones((n,1))
for k in range(maxCycles):
h=sigmoid(dataMatrix*weights)
error=(labelMat-h)
weights=weights+alpha*dataMatrix.transpose()*error #矩阵相乘
return weights
2.训练算法:随机梯度上升
随机梯度上升算法可以写成如下的伪代码:
所有回归系数初始化为1
对数据集中的每个样本
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
以下是随机梯度上升算法的实现代码。
#随机梯度上升算法
def stocGradAscent(dataMatrix,classLabel):
m,n=shape(dataMatrix)
alpha=0.01
weights=ones(n)
for i in range(m):
h=sigmoid(sum(dataMatrix[i]*weights))
error=classLabel[i]-h
weights=weights+alpha*error*dataMatrix[i]
return weights
为了算法能够避免来回波动,从而收敛到某个值,收敛速度加快。
改进的具体代码如下:
#改进的梯度上升算法
def stocGradAscent1(dataMatrix,classLabel,numIter=150):
m,n=shape(dataMatrix)
weights=ones(n)
for j in range(numIter):
dataIndex=range(m)
for i in range(m):
alpha=4/(1.0+j+i)+0.01 #alpha每次迭代时需要调整
randIndex=int(random.uniform(0,len(dataIndex)))
h=sigmoid(sum(dataMatrix[randIndex]*weights))
error=classLabel[randIndex]-h #随机选取更新
weights=weights+alpha*error*dataMatrix[randIndex]
del (dataIndex[randIndex])
return weights
3.测试算法:用Logistic回归进行分类
#Logisitic回归分类函数
def classifyVector(inX,weights):
prob=sigmoid(sum(inX*weights))
if prob>0.5:return 1.0
else:return 0.0
def colisTest():
frTrain=open('horseColicTraining.txt')
frTest=open('horseColicTest.txt')
trainingSet=[];trainingLabels=[]
for line in frTrain.readlines():
currLine=line.strip().split('\t')
lineArr=[]
for i in range(21):
lineArr.append(float(currLine[i]))
trainingSet.append(lineArr)
trainingLabels.append(float(currLine[21]))
trainingWeights=stocGradAscent1(array(trainingSet),trainingLabels,500)
errorCount=0;numTestVec=0.0
for line in frTest.readlines():
numTestVec+=1.0
currLine=line.strip().split('\t')
lineArr=[]
for i in range(21):
lineArr.append(float(currLine[i]))
if int(classifyVector(array(lineArr),trainingWeights))!=int(currLine[21]):
errorCount+=1
errorRate=(float(errorCount)/numTestVec)
print "the erro rate of this test is: %f" % errorRate
return errorRate
def mutiTest():
numTsets=10;errorSum=0.0
for k in range(numTsets):
errorSum+=colisTest()
print "after %d iterations the average error rate is: %f" % (numTsets,errorSum/float(numTsets))
mutiTest()