Machine Learning in action --regression(已勘误)

最近在自学机器学习，应导师要求，先把《Machine Learning with R》动手刷了一遍，感觉R真不能算是一门计算机语言，感觉也就是一个功能复杂的计算器。所以这次就决定使用经典教材《Machine Learning in action》。因为开学得换work station ，怕到时候代码又丢了，所以就索性开个博客，把代码上传上来。

因为书上的原代码有很多错误，并且网上的许多博客的代码也是没有改正的，这次我把修正过的代码po上来

version：python3.5

talk is cheap show me the code

函数定义代码

#coding=utf-8from numpy import *import matplotlib.pyplot as pltdef loadDataSet(fileName):    fr = open(fileName)    numFeat = len(fr.readline().split('\t'))    dataMat = [] ; labelMat = []    for line in fr.readlines():        lineArr = []        curLine = line.strip().split('\t')        for i in range(numFeat - 1):            lineArr.append(float(curLine[i]))        dataMat.append(lineArr)        labelMat.append(float(curLine[-1]))    return dataMat, labelMatdef standRegres(xArr, yArr):    xMat = mat(xArr) ; yMat = mat(yArr).T    xTx = xMat.T * xMat    if linalg.det(xTx) == 0:        print("This matrix is singular, can not do inverse")    ws = xTx.I * (xMat.T * yMat)    return wsdef lwlr(testPoint, xArr, yArr, k = 1.0):    xMat = mat(xArr) ; yMat = mat(yArr).T    m = shape(xMat)[0]    weights = mat(eye((m)))    #创建权重对角矩阵    for j in range(m):        diffMat = testPoint - xMat[j, :]        weights[j, j] = exp(diffMat * diffMat.T / (-2.0 *k **2))    xTx = xMat.T * (weights * xMat)    if linalg.det(xTx) == 0.0:        print("this matrix is singular, cannot do inverse")    ws = xTx.I * (xMat.T * (weights * yMat))    return  testPoint * wsdef lwlrTest(testArr, xArr, yArr, k = 1.0):    m = shape(testArr)[0]    yHat = zeros(m)    for i in range(m):        yHat[i] = lwlr(testArr[i], xArr, yArr, k)    return  yHatdef rssError(yArr, yHatArr):    return ((yArr - yHatArr)**2).sum()def ridgeRegres(xMat, yMat, lam = 0.2):    xTx = xMat.T * xMat    denom = xTx + eye(shape(xMat)[1]) * lam    if linalg.det(denom) == 0:        print("This Matrix is singular, cannot do inverse")        return    ws = denom.I * (xMat.T * yMat)    return wsdef ridgeTest(xArr, yArr):    xMat = mat(xArr) ; yMat = mat(yArr).T    yMean = mean(yMat, 0)#对列求均值    #数据标准化    yMat = yMat -yMean    xMeans = mean(xMat, 0) #对 列 求均值    xVar = var(xMat, 0)#对列求方差    xMat = (xMat - xMeans) / xVar    numTestPts = 30    wMat = zeros((numTestPts, shape(xMat)[1]))    for i in range(numTestPts):        ws = ridgeRegres(xMat, yMat, exp(i-10))        wMat[i,:] = ws.T    return wMatdef regularize(xMat):    inMat = xMat.copy()    inMeans = mean(inMat, 0)    inVar = var(inMat, 0)    inMat = (inMat - inMeans)/inVar    return inMatdef stageWise(xArr, yArr, eps = 0.01, numIt = 100):    xMat = mat(xArr) ; yMat = mat(yArr).T    yMean = mean(yMat, 0)    yMat = yMat -yMean    xMat = regularize(xMat)    m, n = shape(xMat)    returnMat = zeros((numIt, n))    ws = zeros((n, 1)) ; wsTest = ws.copy() ; wsMax = ws.copy()    for i in range(numIt):        print("ws.T: ",ws.T)        lowestError = inf        for j in range(n):            for sign in [-1, 1]:                wsTest = ws.copy()                wsTest[j] += eps * sign                yTest = xMat * wsTest                rssE = rssError(yMat.A, yTest.A)                if rssE < lowestError :                    lowestError = rssE                    wsMax = wsTest        ws = ws.copy()        returnMat[i, :] = ws.T    return returnMat

上面代码块只是定义了主要的函数，离运行还差一点。由于书原文中，采用了使用 iPython 命令行的运行方式，但是博主比较懒，所以干脆舍弃掉原来的方式。

废话不多少，直接上代码

实验1

if __name__=="__main__":    xArr, yArr = loadDataSet('ex0.txt')    ws = standRegres(xArr,yArr)    print(ws)    xMat = mat(xArr)    yMat = mat(yArr)    yHat = xMat * ws

实验2 ：

if __name__ == "__main__":    fig = plt.figure()    ax = fig.add_subplot(111)    ax.scatter(xMat[:,1].flatten().A[0], yMat.T[:,0].flatten().A[0])    xCopy = xMat.copy()    xCopy.sort(0)    yHat = xCopy * ws    ax.plot(xCopy[:, 1], yHat)    plt.show()

实验3 ：

if __name__ == "__main__":    xArr, yArr = loadDataSet('ex0.txt')    print("actual yArr[0]:",yArr[0])    lwlr(xArr[0], xArr, yArr, 1.0)    print(lwlr(xArr[0], xArr, yArr, 1.0))

实验4 ：

if __name__ == "__main__":    xArr, yArr = loadDataSet('ex0.txt')    print(lwlrTest(xArr, xArr, yArr, 0.003  ))

实验5 ：

if __name__ == "__main__":    xArr, yArr = loadDataSet('ex0.txt')    xMat = mat(xArr)    print("xMat: ",xMat)    yMat = mat(yArr)    yHat = lwlrTest(xArr, xArr, yArr, 0.01  )    srtInd = xMat[:, 1].argsort(0) #返回的是数组值从小到大的索引值, 按列排序    print("srtInd: ",srtInd)    xSort = xMat[srtInd][:, 0, :] #从小到大 排序    print("xSort: ",xSort)    fig = plt.figure()    ax = fig.add_subplot(111)    ax.plot(xSort[:,1], yHat[srtInd])    ax.scatter(xMat[:,1].flatten().A[0], mat(yArr).T.flatten().A[0], s=2, c = 'red')    plt.show()

实验6 ：

if __name__ == "__main__":    abX, abY = loadDataSet('abalone.txt')    ridgeWeights = ridgeTest(abX, abY)    fig = plt.figure()    ax = fig.add_subplot(111)    ax.plot(ridgeWeights)    plt.show()

实验7 ：

if __name__ == "__main__":    xArr, yArr = loadDataSet('abalone.txt')    #stageWise(xArr, yArr, 0.001, 5000)    print(stageWise(xArr, yArr, 0.001,5000))

更多请戳github
https://github.com/Edgis/Machine-learning-in-action/blob/master/regression.py