机器学习实战第五章加注释源码

运行环境python3.7.4 64-bit

'''
Created on Oct 27, 2010
Logistic Regression Working Module
@author: Peter
'''
from numpy import *
import random

def loadDataSet():
    dataMat = [];labelMat = []        #创建数据列表和标签列表（0或1）
    fr = open('testSet.txt')
    for line in fr.readlines():          #逐行读取
        lineArr = line.strip().split()           #每行数据去回车，空格等,放入列表。
        dataMat.append([1.0, float(lineArr[0]), float(lineArr[1])])           #x0默认为1，并添加x1，x2
        labelMat.append(int(lineArr[2]))           #添加标签
    return dataMat,labelMat

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

#weight=weight+alpha*X（转置）*(labelMat-sigmoid(dataMatrix*weight))
def gradAscent(dataMatIn, classLabels):     #梯度上升算法
    dataMatrix = mat(dataMatIn)             #转换为Numpy矩阵
    labelMat = mat(classLabels).transpose() #convert to NumPy matrix
    m,n = shape(dataMatrix)                 #读取矩阵的行和列的大小，m为行数，n为列数
    alpha = 0.001                           #步长设为0.001
    maxCycles = 500                         #迭代次数
    weights = ones((n,1))                   #建立一个n行1列，元素初始都为1的矩阵
    for k in range(maxCycles):              #heavy on matrix operations
        h = sigmoid(dataMatrix*weights)     #梯度上升矢量化公式，h是理论值
        error = (labelMat - h)              #labelMat为0或1
        weights = weights + alpha * dataMatrix.transpose()* error #matrix mult
    return weights

def plotBestFit(weights):
    import matplotlib.pyplot as plt
    dataMat,labelMat=loadDataSet()          #加载数据集
    dataArr = array(dataMat)                #转换成numpy的array数组
    n = shape(dataArr)[0]                    #数据个数
    xcord1 = []; ycord1 = []                #正样本
    xcord2 = []; ycord2 = []                #负样本
    for i in range(n):
        if int(labelMat[i])== 1:            #1为正样本，0为负样本
            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)               #添加subplot
    ax.scatter(xcord1, ycord1, s=30, c='red', marker='s')   #绘制正样本
    ax.scatter(xcord2, ycord2, s=30, c='green')             #绘制负样本
    x = arange(-3.0, 3.0, 0.1)
    #假设Sigmoid函数的输入记为z，那么z=w0x0 + w1x1 + w2x2，即可将数据分割开。
    # 其中，x0为全是1的向量，x1为数据集的第一列数据，x2为数据集的第二列数据。
    # 另z=0，则0=w0 + w1x1 + w2x2。横坐标为x1，纵坐标为x2。
    #则x2=(-w0-w1*x1)/w2
    y = (-weights[0]-weights[1]*x)/weights[2]
    ax.plot(x, y)
    plt.xlabel('X1'); plt.ylabel('X2');
    plt.show()

def stocGradAscent0(dataMatrix, classLabels):
	dataMatrix=array(dataMatrix)
    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

def stocGradAscent1(dataMatrix, classLabels, numIter=150):
	dataMatrix=array(dataMatrix)
    m,n = shape(dataMatrix)
    weights = ones(n)   #initialize to all ones
    for j in range(numIter):
        dataIndex = range(m)
        for i in range(m):
            alpha = 4/(1.0+j+i)+0.0001    #alpha随着迭代次数增加而减小，但是始终大于0 ，j是迭代次数，i是样本点下标
            randIndex = int(random.uniform(0,len(dataIndex)))   #随机选取样本
            h = sigmoid(sum(dataMatrix[randIndex]*weights))
            error = classLabels[randIndex] - h
            weights = weights + alpha * error * dataMatrix[randIndex]
            del (list(dataIndex)[randIndex])       #删除已使用样本
    return weights

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')#打开训练集和测试集
    trainingSet = []; trainingLabels = []   # trainingSet 中存储训练数据集的特征，trainingLabels 存储训练数据集的样本对应的分类标签
    for line in frTrain.readlines():
        currLine = line.strip().split('\t')
        lineArr =[]
        for i in range(21):
            lineArr.append(float(currLine[i]))
            #存入训练样本特征
        trainingSet.append(lineArr)
        #存入训练样本标签
        trainingLabels.append(float(currLine[21]))
        #使用改进后的随机梯度下降算法得到回归系数
    trainWeights = stocGradAscent1(array(trainingSet), trainingLabels, 1000)

    #统计测试集预测错误样本数量和样本总数
    errorCount = 0; numTestVec = 0.0
    for line in frTest.readlines():
        numTestVec += 1.0 #循环一次，样本数加1
        currLine = line.strip().split('\t')
        lineArr =[]
        for i in range(21):
            lineArr.append(float(currLine[i]))
        # 利用分类预测函数对该样本进行预测，并与样本标签进行比较
        if int(classifyVector(array(lineArr), trainWeights))!= int(currLine[21]):
            #如果预测错误，错误数加1
            errorCount += 1
    #计算错误率
    errorRate = (float(errorCount)/numTestVec)
    print ("the error rate of this test is: %f" % errorRate)
    return errorRate

#调用colicTest()10次，并求一个错误率平均值。
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)))

if __name__ == '__main__':
    colicTest()