回归算法学习笔记（一）用线性回归线找到最佳拟合直线

#coding=utf-8

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=[]
        currentLine=line.strip().split('\t')
        for i in range(numFeat):
            lineArr.append(float(currentLine[i]))
        dataMat.append(lineArr)
        labelMat.append(float(currentLine[-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

xArr,yArr=loadDataSet('ex0.txt')
ws=standRegres(xArr,yArr)
print  ws
xMat=mat(xArr)
yMat=mat(yArr)
yHat=xMat*ws
import matplotlib.pyplot as plt
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()