西瓜书《机器学习》课后编程题答案——3.3

3.3编程实现对率回归，并给出西瓜数据集3.0α上的结果

本文在参考《机器学习实战》的基础上，利用Python3编写了代码，完成了题目3.3，主要由这几部分组成：

加载数据

def loadDataSet():      #general function to parse tab -delimited floats
    numFeat = len(open('3.0alpha.txt').readline().split('\t')) #get number of fields
    dataMat = []; labelMat = []
    fr = open('3.0alpha.txt')
    for line in fr.readlines():
        lineArr =[]
        curLine = line.strip().split('\t')
        lineArr.append(float(1.0))
        for i in range(numFeat-1):
            lineArr.append(float(curLine[i]))
        dataMat.append(lineArr)
        labelMat.append(float(curLine[-1]))
    return dataMat,labelMat

Sigmoid 函数

def sigmoid(inX):
    return 1.0/(1+exp(-inX))

低度下降计算权重

def gradAscent(dataMatIn, classLabels):
    dataMatrix = mat(dataMatIn)             #convert to NumPy matrix 进行线性代数必要操作
    labelMat = mat(classLabels).transpose() #convert to NumPy matrix 转置
    m,n = shape(dataMatrix)
    alpha = 0.001
    maxCycles = 1000
    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

分类

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

到此就实现了所有的功能，为了更好的使用各部分函数，对上述几个函数进行整合成一个函数。

完整程序

def colicTest():
    frTest = open('3.0alpha.txt') # 数据较少 用原来的数据计算训练误差 也可以将数据进行分割成训练集和测试集
    trainingSet, trainingLabels = loadDataSet()
    trainWeights = gradAscent(array(trainingSet), trainingLabels)
    errorCount = 0; numTestVec = 0.0
    numFeat = len(frTest.readline().split('\t'))
    for line in frTest.readlines():
        numTestVec += 1.0
        currLine = line.strip().split('\t')
        lineArr =[]
        lineArr.append(float(1.0))
        for i in range(numFeat - 1):
            lineArr.append(float(currLine[i]))
        if int(classifyVector(array(lineArr), trainWeights))!= int(currLine[-1]):
            errorCount += 1
    errorRate = (float(errorCount)/numTestVec)
    print("the error rate of this test is: %f" % errorRate)
    return errorRate

画出分类后的点

def plot2D():
    import matplotlib
    import matplotlib.pyplot as plt
    dataMat, labelMat = loadDataSet()
    dataArr = array(dataMat)
    weights = gradAscent(dataMat, labelMat)
    n = len(labelMat)
    xcord0 = [];ycord0 = []
    xcord1 = [];ycord1 = []
    for i in range(n):
        if labelMat[i] == 0:
            xcord0.append(dataMat[i][1]);ycord0.append(dataMat[i][2])
        else:
            xcord1.append(dataMat[i][1]);ycord1.append(dataMat[i][2])
    fig = plt.figure()
    ax = fig.add_subplot(111)
    type0 = ax.scatter(xcord0, ycord0, s=30, c='red', marker='s')
    type1 = ax.scatter(xcord1, ycord1, s=30, c='green')
    x = arange(0, 1.0, 0.05)
    y = (-weights[0] - weights[1] * x) / weights[2]
    type3 = ax.plot(x, y.transpose())
    plt.xlabel('Density')
    plt.ylabel('Sugar_content')
    plt.show()

到此就完成了整个题目，并且对程序稍加修改就可以应用到别的场合中。
最后得到错误率为：

the error rate of this test is: 0.312500
0.3125

完整的代码和数据集下载地址 [链接].(https://download.csdn.net/download/yanying1113/10807706).