1. 问题描述
根据299个训练样本，进行Logistic回归，预测67个测试样本中的疝气病马是否死亡。值得注意的是，特征中有30%的值是缺失的。
2. 数据准备
训练数据在horseColicTraining文件中，有299个样本。测试数据在horseColicTest文件中，有67个样本。每一行为一个样本，每一列为一个特征。
3. 模型原理
logistic回归是一种广义线性回归（generalized linear model），因此与多重线性回归分析有很多相同之处。它们的模型形式基本上相同，都具有 w‘x+b，其中w和b是待求参数，其区别在于他们的因变量不同，多重线性回归直接将w‘x+b作为因变量，即y =w‘x+b，而logistic回归则通过函数L将w‘x+b对应一个隐状态p，p =L(w‘x+b),然后根据p 与1-p的大小决定因变量的值。如果L是logistic函数，就是logistic回归，如果L是多项式函数就是多项式回归。
4. 算法实现
4.1. 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
def sigmoid(inX):
return 1.0/(1+exp(-inX))
def gradAscent(dataMatIn, classLabels):
dataMatrix = mat(dataMatIn) #convert to NumPy matrix
labelMat = mat(classLabels).transpose() #convert to NumPy matrix
m,n = shape(dataMatrix)
alpha = 0.001
maxCycles = 500
weights = ones((n,1))
for k in range(maxCycles): #heavy on matrix operations
h = sigmoid(dataMatrix*weights) #matrix mult
error = (labelMat - h) #vector subtraction
weights = weights + alpha * dataMatrix.transpose()* error #matrix mult
return weights
4.2. 画出数据集和Logistics回归最佳拟合直线的函数
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()
4.3. 随机梯度上升算法
def stocGradAscent0(dataMatrix, classLabels):
m,n = shape(dataMatrix)
alpha = 0.01
weights = ones(n) #initialize to all ones
for i in range(m):
h = sigmoid(sum(dataMatrix[i]*weights))
error = classLabels[i] - h
weights = weights + alpha * error * dataMatrix[i]
return weights
4.4改进的随机梯度上升算法
def stocGradAscent1(dataMatrix, classLabels, numIter=150):
m,n = shape(dataMatrix)
weights = ones(n) #initialize to all ones
for j in range(numIter):
dataIndex = list(range(m))
for i in range(m):
alpha = 4/(1.0+j+i)+0.0001 #apha decreases with iteration, does not
randIndex = int(random.uniform(0,len(dataIndex)))#go to 0 because of the constant
h = sigmoid(sum(dataMatrix[randIndex]*weights))
error = classLabels[randIndex] - h
weights = weights + alpha * error * dataMatrix[randIndex]
del(dataIndex[randIndex])
return weights
4.5.数据预测
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)))
5. 测试方法及结果
经过测试，平均错误率在32%左右。在有着30%数据缺失的情况下，这个效果并不差。
6. 总结
本文采用书上的相应算法、引入回归分析法，通过拟合来预测疝气病马的死亡率。但由于数据集内容有限及缺失数据过多，有一定的错误率。针对这一情况，应获取无缺失的数据集进行训练。