机器学习python局部加权线性回归

局部加权线性回归可以解决欠拟合问题，给待测点附近的每个点赋予一定的权重

通过矩阵运算的方法解出回归系数w = (X^TWX)^-1x^TWy，通过使用“核”来对附近的点赋予权重，最常用的高斯核权重如下：w（i,i）= exp(|x⁽ⁱ⁾ - x| / -2k²），对K值取不同的结果，得到的模型也不用，K越小，可能会出现过拟合，K越大，可能会出现欠拟合，这里将给出不同的K值的函数图像，这种方法加重了计算量

k=1.0出现了欠拟合，k=0.1时效果最佳，k=0.03时出现了过拟合

from numpy import *
def loadDataSet(filename):
    numFeat = len(open(filename).readline().split('\t')) - 1
    dataMat = []
    labelMat = []
    fr = open(filename)
    for line in fr.readlines():
        lineArr = []
        curLine = line.strip().split('\t')
        for i in range(numFeat):
            lineArr.append(float(curLine[i]))
        dataMat.append(lineArr)
        labelMat.append(float(curLine[-1]))
    return dataMat,labelMat
def standRegress(xArr,yArr):
    xMat = mat(xArr)
    yMat = mat(yArr).T
    xTx = xMat.T * xMat
    if linalg.det(xTx) == 0.0:
        print('error')
        return
    ws = xTx.I * (xMat.T * yMat)
    return ws
def lwlr(testPoint,xArr,yArr,k=1.0):
    xMat = mat(xArr)
    yMat = mat(yArr).T
    m = shape(xMat)[0]
    weights = mat(eye((m)))
    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("error")
        return
    ws = xTx.I * (xMat.T * (weights * yMat))
    return testPoint * ws
def 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 yHat
def rssError(yArr,yHatArr):
    return ((yArr-yHatArr)**2).sum()

xArr,yArr = loadDataSet('ex0.txt')
xMat = mat(xArr)
yMat = mat(yArr)
k = [1.0,0.01,0.003]
for i in range(3):
    yHat = lwlrTest(xArr, xArr, yArr, k[i])
    srtInd = xMat[:, 1].argsort(0)
    xSort = xMat[srtInd][:, 0, :]
    import matplotlib.pyplot as plt
    fig = plt.figure(i+1)
    ax = fig.add_subplot(111)
    ax.plot(xSort[:, 1], yHat[srtInd])
    ax.scatter(xMat[:, 1].flatten().A[0], yMat.T[:, 0].flatten().A[0], s=2, c='red')
    plt.title('k=%g' % k[i])
plt.show()