代码注释：机器学习实战第5章 Logistic回归

写在开头的话：在学习《机器学习实战》的过程中发现书中很多代码并没有注释，这对新入门的同学是一个挑战，特此贴出我对代码做出的注释，仅供参考，欢迎指正。

1、随机梯度上升

#coding:gbk
from numpy import *

#功能：导入数据集
#输入：无
#输出：数据矩阵，标签向量
def loadDataSet():
    dataMat = []#数据矩阵
    labelMat = []#标签向量
    fr = open('testSet.txt')
    for line in fr.readlines():
        lineArr = line.strip().split()#strip()表示删除空白符，split()表示分割
        dataMat.append([1.0, float(lineArr[0]), float(lineArr[1])])#1.0表示x0
        labelMat.append(int(lineArr[2]))
    return dataMat, labelMat

#功能：计算x的Sigmoid函数
#输入：x
#输出：x的Sigmoid函数
def sigmoid(inX):
    return 1.0 / (1 + exp(-inX))

#功能：Logistic回归梯度上升优化算法
#输入：无
#输出：优化后的权重向量
def gradAscent():
    dataMatIn, classLabels = loadDataSet()#得数据矩阵，标签向量
    dataMatrix = mat(dataMatIn)#将列表转换成m*n矩阵
    labelMat = mat(classLabels).transpose()#将1*m标签向量转换成m*1矩阵
    m, n = shape(dataMatrix)#得dataMatrix的行数、列数
    alpha = 0.001#步长
    maxCycles = 500#最大迭代数量
    weights = ones((n,1))#n*1权重矩阵
    for k in range(maxCycles):
        h = sigmoid(dataMatrix * weights)
        error = (labelMat - h)
        weights = weights + alpha * dataMatrix.transpose() * error#数学推导，f = x * w so w = xT * f
    return weights

#功能：画出决策边界
#输入：无
#输出：无
def plotBestFit():
    weights = stocGradAscent1()#得优化后的权重向量
    #weights = weights.getA()#主窗口输入help(numpy.matrix.getA)，将matrix转换为array
    import matplotlib.pyplot as plt
    dataMat, labelMat = loadDataSet()#得数据矩阵，标签向量
    dataArr = array(dataMat)#将dataMat转换为array
    n = shape(dataArr)[0]#得dataArr行数
    xcord1 = []
    ycord1 = []
    xcord2 = []
    ycord2 = []
    for i in range(n):
        if int(labelMat[i]) == 1:#标签为1
            xcord1.append(dataArr[i, 1])
            ycord1.append(dataArr[i, 2])
        else:#标签为0
            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')#red square红方块
    ax.scatter(xcord2, ycord2, s = 30, c='green')#绿圆点
    x = arange(-3.0, 3.0, 0.1)#在[-3.0,3.0]区间里以0.1的步长取数，得列表
    y = (-weights[0] - weights[1] * x) / weights[2]#直线方程：weights[0] + weights[1] * x + weights[2] * 2 = 0
    ax.plot(x, y)
    plt.xlabel('X1')
    plt.ylabel('X2')
    plt.show()

#功能：随机梯度上升
#输入：无
#输出：优化后的权重向量
def stocGradAscent0():
    dataArr, classLabels = loadDataSet()  # 得数据矩阵，标签向量
    dataMatrix = array(dataArr)  # 将列表转换成m*n矩阵
    m, n = shape(dataMatrix)#得dataMatrix的行数、列数
    alpha = 0.01#步长
    weights = ones(n)#n阶权重向量
    for i in range(m):
        h = sigmoid(sum(dataMatrix[i] * weights))
        error = classLabels[i] - h
        weights = weights + alpha * error *dataMatrix[i]
    return weights

2、改进的随机梯度上升

#功能：改进的随机梯度上升
#输入：无
#输出：优化后的权重向量
def stocGradAscent1(dataMatrix, classLabels, numIter = 150):
    m, n = shape(dataMatrix)  # 得dataMatrix的行数、列数
    weights = ones(n)  # n阶权重向量
    for j in range(numIter):#n次迭代
        dataIndex = range(m)
        for i in range(m):
            alpha = 4 / (1.0 + j + i) + 0.01#使得步长随着迭代的进行而逐渐减小
            randIndex = int(random.uniform(0, len(dataIndex)))#随机取第randIndex行的dataMatrix
            h = sigmoid(sum(dataMatrix[randIndex] * weights))
            error = classLabels[randIndex] - h
            weights = weights + alpha * error * dataMatrix[randIndex]
            del(dataIndex[randIndex])#删除第randIndex行，不参与迭代
    return weights

3、从疝气病症预测病马的死亡率

#功能：预测类别标签
#输入：特征向量，回归系数
#输出：预测的类别标签
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')#strip()表示删除空白符，split()表示分割
        lineArr = []
        for i in range(21):
            lineArr.append(float(currLine[i]))#将这个属性放入lineArr
        trainingSet.append(lineArr)#属性集
        trainingLabels.append(float(currLine[21]))#标签集
    trainWeights = stocGradAscent1(array(trainingSet), trainingLabels, 500)
    errorCount = 0
    numTestVec = 0.0
    for line in frTest.readlines():
        numTestVec += 1.0
        currLine = line.strip().split('\t')#strip()表示删除空白符，split()表示分割
        lineArr = []
        for i in range(21):
            lineArr.append(float(currLine[i]))#将这个属性放入lineArr
        if int(classifyVector(array(lineArr), trainWeights)) != int(currLine[21]):#预测标签和验证标签不一致
            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 "the %d test: " % k
    print "after %d iterations the average error rate is: %f" % (numTests, errorSum / float(numTests))