监督学习-局部加权回归模板

from numpy import *

def loadDataSet(fileName):      #general function to parse tab -delimited floats
    numFeat = len(open(fileName).readline().split('\t')) - 1 #get number of fields 
    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 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):                      #next 2 lines create weights matrix
        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")
        return
    ws = xTx.I * (xMat.T * (weights * yMat))
    return testPoint * ws

def lwlrTest(testArr,xArr,yArr,k=1.0):  #loops over all the data points and applies lwlr to each one
    m = shape(testArr)[0]
    yHat = zeros(m)
    for i in range(m):
        yHat[i] = lwlr(testArr[i],xArr,yArr,k)
    return yHat

def lwlrTestPlot(xArr,yArr,k=1.0):  #same thing as lwlrTest except it sorts X first
    yHat = zeros(shape(yArr))       #easier for plotting
    xCopy = mat(xArr)
    xCopy.sort(0)
    for i in range(shape(xArr)[0]):
        yHat[i] = lwlr(xCopy[i],xArr,yArr,k)
    return yHat,xCopy

def rssError(yArr,yHatArr): #yArr and yHatArr both need to be arrays
    return ((yArr-yHatArr)**2).sum()

def test():
    import regression
    abx,aby=regression.loadDataSet('abalone.txt')
    y01=regression.lwlrTest(abx[0:99],abx[0:99],aby[0:99],0.1)
    y1=regression.lwlrTest(abx[0:99],abx[0:99],aby[0:99],1)
    y10=regression.lwlrTest(abx[0:99],abx[0:99],aby[0:99],10)
    a=regression.rssError(aby[0:99],y01.T)
    print(a)
    a=regression.rssError(aby[0:99],y1.T)
    print(a)
    a=regression.rssError(aby[0:99],y10.T)
    print(a)