机器学习实战（8）：局部加强线性回归LWLR

w~=(X'WX)^(-1)*X'*Wy ; y~=X'*w~

由平方误差对w求导=0推出。

权重W高斯核函数、类似SVM的径向基函数的高斯形式，指数函数

# coding=utf-8
#Created on Jan 8, 2011
#@author: Peter

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 standRegres(xArr,yArr):
    xMat = mat(xArr); yMat = mat(yArr).T
    xTx = xMat.T*xMat
    if linalg.det(xTx) == 0.0:
        print ("This matrix is singular, cannot do inverse")
        return
    ws = xTx.I * (xMat.T*yMat)
    return ws

def lwlr(testPoint,xArr,yArr,k=1.0): #Locally Weighted Linear Regression
    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

xArr,yArr=loadDataSet(r'C:\Users\li\Downloads\machinelearninginaction\Ch08\ex0.txt')
yHat=lwlrTest(xArr, xArr, yArr, 0.01)
xMat=mat(xArr)
srtInd=xMat[:,1].argsort(0) #将数据点按序排列
xSort=xMat[srtInd][:,0,:]
import matplotlib.pyplot as plt
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()