Logistic回归的使用

Logistic回归的使用和缺失值的处理

从疝气病预测病马的死亡率

数据集：

测试方法：

实现细节：

缺失值的处理：

weight = weight + alpha * error * dataMatrix[randIndex]

#coding=utf-8
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 sigmoid(inX):
return 1.0/(1+exp(-inX))

def stocGradAscent1(dataMatrix, classLabels, numIter=150):
m,n = shape(dataMatrix)

#alpha = 0.001
weight = 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 = sigmoid(sum(dataMatrix[randIndex]*weight))
error = classLabels[randIndex] - h
weight = weight + alpha * error * dataMatrix[randIndex]
del(dataIndex[randIndex])
return weight

def classifyVector(inX, weights):
prob = sigmoid(sum(inX*weights))
if prob > 0.5: return 1.0
else: return 0.0

def colicTest():
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]))
trainWeights = stocGradAscent1(array(trainingSet), trainingLabels, 1000)
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), trainWeights))!= int(currLine[21]):
errorCount += 1
errorRate = (float(errorCount)/numTestVec)
print "the error rate of this test is: %f" % errorRate
return errorRate

def multiTest():
numTests = 10; errorSum=0.0
for k in range(numTests):
errorSum += colicTest()
print "after %d iterations the average error rate is: %f" % (numTests, errorSum/float(numTests))

def main():
multiTest()

if __name__ == '__main__':
main()

机器学习笔记索引