Logistic Regression 用于预测马是否生病

 # -*- coding: utf-8 -*-

 """

 Created on Tue Mar 28 21:35:25 2017

 @author: MyHome

 """

 import numpy as np

 from random import uniform

 '''定义sigmoid函数'''

 def sigmoid(inX):

     return 1.0 /(1.0 +np.exp(-inX))

 '''使用随机梯度下降更新权重，并返回最终值'''

 def StocGradientDescent(dataMatrix,classLabels,numIter = 600):

     m,n = dataMatrix.shape

     #print m,n

     weights = np.ones(n)

     for j in xrange(numIter):

         dataIndex = range(m)

         for i in xrange(m):

             alpha = 4 / (1.0+j+i) + 0.01

             randIndex = int(uniform(0,len(dataIndex)))

             h = sigmoid(sum(dataMatrix[randIndex]*weights))

             gradient = (h - classLabels[randIndex])*dataMatrix[randIndex]

             weights = weights - alpha*gradient

             del(dataIndex[randIndex])

     return weights

 '''创建分类器'''

 def classifyVector(inX,weights):

     prob = sigmoid(sum(inX*weights))

     if prob > 0.5:

         return 1.0

     else:

         return 0.0

 '''测试'''

 def Test():

     frTrain = open("horseColicTraining.txt")

     frTest = open("horseColicTest.txt")

     trainingSet = []

     trainingLabel = []

     for line in frTrain.readlines():

         currLine = line.strip().split("\t")

         lineArr = []

         for i in range(21):

             lineArr.append(float(currLine[i]))

         trainingSet.append(lineArr)

         trainingLabel.append(float(currLine[21]))

     trainWeights = StocGradientDescent(np.array(trainingSet),trainingLabel)

     errorCount = 0.0

     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(np.array(lineArr),trainWeights)) != int(currLine[21]):

             errorCount += 1

     errorRate = (float(errorCount)/numTestVec)

     print "the error rate of this test is:%f"%errorRate

     return errorRate

 '''调用Test()10次求平均值'''

 def multiTest():

     numTest = 10

     errorSum = 0.0

     for k in range(numTest):

         errorSum += Test()

     print "after %d iterations the average errror rate is:\

         %f"%(numTest,errorSum/float(numTest))

 if __name__ == "__main__":

     multiTest()