第五章 Logistic回归

from numpy import *
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 sigmod(inX):
	return 1.0/(1+exp(-inX))

def gradAscent(dataMatIn,classLabels):
	dataMatrix = mat(dataMatIn)
	labelMat = mat(classLabels).transpose()
	m,n=shape(dataMatrix)
	alpha=0.001
	maxCycles=500
	weights=ones((n,1))
	for k in range(maxCycles):
		h=sigmod(dataMatrix*weights)
		error=(labelMat-h)
		weights=weights+alpha*dataMatrix.transpose()*error
	return weights
	
def plotBestFit(weights):
	import matplotlib.pyplot as plt
	dataMat,labelMat=loadDataSet()
	dataArr=array(dataMat)
	n=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=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()
	
def stocGradAscent1(dataMatrix,classLabels,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
			randIndex=int(random.uniform(0,len(dataIndex)))
			h=sigmod(sum(dataMatrix[randIndex]*weights))
			error=classLabels[randIndex]-h
			weights=weights+alpha*error*dataMatrix[randIndex]
			del(dataIndex[randIndex])
	return weights

alpha在每次迭代的时候会调整，虽然alpha会随着迭代次数不断减小，但永远不会减小到0