《机器学习实战》笔记——逻辑回归

书上没有给具体的逻辑回归的课程，就直接上了代码，这很不好！

可以参考ng的课程，或者看这篇博文：http://blog.csdn.net/wlmnzf/article/details/72855610?utm_source=itdadao

过程还是比较浅显易懂的，就没怎么备注了。

  1 # _*_ coding:utf-8 _*_
  2
  3 from numpy import *
  4 def loadDataSet():
  5     dataMat = []
  6     labelMat = []
  7     fr = open(‘testSet.txt‘)
  8     for line in fr.readlines():
  9         lineArr = line.strip().split()
 10         dataMat.append([1.0, float(lineArr[0]), float(lineArr[1])])
 11         labelMat.append(int(lineArr[2]))
 12     return dataMat, labelMat
 13
 14 def sigmoid(inX):
 15     return 1.0/(1 + exp(-inX))
 16
 17 def gradAscent(dataMatIn, classLabels):
 18     dataMatrix =  mat(dataMatIn)
 19     labelMat = mat(classLabels).transpose()
 20     m,n = shape(dataMatrix)
 21     alpha = 0.001
 22     maxCycles = 500
 23     weights = ones((n,1))
 24     for k in range(maxCycles):
 25         h = sigmoid(dataMatrix*weights)
 26         error = (labelMat - h)  # 是数  这里没给出推导过程，推导过程上文有链接
 27         weights = weights + alpha * dataMatrix.transpose() * error
 28     return weights
 29
 30 # 5-3 随机梯度上升算法
 31 def stocGradAscent0(dataMatrix, classLabels):
 32     m,n = shape(dataMatrix)
 33     alpha = 0.01
 34     weights = ones(n)
 35     for i in range(m):
 36         h = sigmoid(sum(dataMatrix[i]*weights))
 37         error = classLabels[i] - h  # 是向量
 38         weights = weights + alpha * error * dataMatrix[i]
 39     return weights
 40
 41 # 5-4 改进的随机梯度上升算法
 42 def stocGradAscent1(dataMatrix, classLabels, numIter=150):
 43     m,n = shape(dataMatrix)
 44
 45     weights = ones(n)
 46     for j in range(numIter):
 47         dataIndex = range(m)
 48         for i in range(m):
 49             alpha = 4/(1.0+j+i) + 0.01
 50             randIndex = int(random.uniform(0, len(dataIndex)))
 51             h = sigmoid(sum(dataMatrix[randIndex]*weights))
 52             error = classLabels[randIndex] - h  # 是向量
 53             weights = weights + alpha * error * dataMatrix[randIndex]
 54             del(dataIndex[randIndex])
 55     return weights
 56
 57
 58 def plotBestFit(weights):
 59     import matplotlib.pyplot as plt
 60     # weights = wei.getA()    # 把matrix变为array
 61     dataMat, labelMat = loadDataSet()
 62     dataArr = array(dataMat)
 63     n = shape(dataArr)[0]
 64     xcord1 = []
 65     ycord1 = []
 66     xcord2 = []
 67     ycord2 = []
 68     for i in range(n):
 69         if int(labelMat[i])==1:
 70             xcord1.append(dataArr[i,1])
 71             ycord1.append(dataArr[i,2])
 72         else:
 73             xcord2.append(dataArr[i,1])
 74             ycord2.append(dataArr[i,2])
 75     fig = plt.figure()
 76     ax = fig.add_subplot(111)
 77     ax.scatter(xcord1, ycord1, c=‘red‘, s=30, marker=‘s‘)   # marker中s代表square
 78     ax.scatter(xcord2, ycord2, c=‘green‘, s=30)
 79     x = arange(-3, 3, 0.1)
 80     y = (-weights[0] - weights[1] * x) / weights[2]
 81     ax.plot(x, y)
 82     plt.xlabel(‘X1‘)
 83     plt.ylabel(‘X2‘)
 84     plt.show()
 85
 86 def classifyVector(inX, weights):
 87     prob = sigmoid(sum(inX * weights))
 88     if prob > 0.5: return 1.0
 89     else: return 0.0
 90
 91 def colicTest():
 92     frTrain = open(‘horseColicTraining.txt‘)
 93     frTest = open(‘horseColicTest.txt‘)
 94     trainingSet = []
 95     trainingLabels = []
 96     for line in frTrain.readlines():
 97         currLine = line.strip().split(‘\t‘)
 98         lineArr = []
 99         for i in range(21):
100             lineArr.append(float(currLine[i]))
101         trainingSet.append(lineArr)
102         trainingLabels.append(float(currLine[21]))
103     trainWeights = stocGradAscent1(array(trainingSet), trainingLabels, 500)
104     errorCount = 0
105     numTestVec = 0.0
106     for line in frTest.readlines():
107         numTestVec += 1.0
108         currLine = line.strip().split(‘\t‘)
109         lineArr = []
110         for i in range(21):
111             lineArr.append(float(currLine[i]))
112         if int(classifyVector(array(lineArr), trainWeights)) != int(currLine[21]):
113             int(currLine[21])
114             errorCount += 1
115         errorRate = (float(errorCount)/numTestVec)
116         print "the error rate of this test is: %f" % errorRate
117         return errorRate
118
119 def multiTest():
120     numTests = 10
121     errorSum = 0.0
122     for k in range(numTests):
123         errorSum += colicTest()
124     print "after %d iterations the average error rate is: %f" % (numTests, errorSum/float(numTests))
125
126 multiTest()