线性回归

1.线性回归原理

回归的目的就是预测数值型的目标值，回归方程就是回归系数和输入线性组合的方程，求回归系数的过程就叫回归。线性回归是输入项和系数相乘在相加，非线性回归可能认为输出是输入的相乘

求回归系数就是求出误差函数并对会回归系数求导，并让其为0，就可以求出回归系数

import numpy as np
import matplotlib.pyplot as pl

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

线性回归可能出现的一个问题就是欠拟合，此时我们可以做局部加权线性回归，我们对带预测附近的每个点赋予一个权值，然后在做回归

def lwlr(testPoint, xArr, yArr, k = 1.0):
    xMat = np.mat(xArr)
    yMat = np.mat(yArr).T
    m = np.shape(xMat)[0]
    weights = np.mat(np.eye((m)))
    for j in range(m):
        diffMat = testPoint - xMat[j,:]
        weights[j,j] = np.exp(diffMat*diffMat.T/(-2.0*k**2))
    xTx = xMat.T * (weights*xMat)
    if np.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):
    m = np.shape(testArr)[0]
    yHat = np.zeros(m)
    for i in range(m):
        yHat[i] = lwlr(testArr[i], xArr, yArr, k)
    return yHat

岭回归，当特征的数目比数据的数还多时，我们可以引入岭回归来解决问题.岭回归就是在XtX上加一个常数在乘单位矩阵，使其非奇异可求逆

def ridgeRegress(xMat, yMat, lam = 0.2):
    xTx = xMat.T * xMat
    denom = xTx + np.eye(np.shape(xMat)[1])*lam
    if np.linalg.det(denom) == 0.0:
        print 'this matrix is singular, cannot do inverse'
        return
    ws = denom.I * (xMat.T*yMat)
    return ws

def ridgeTest(xArr, yArr):
    xMat = np.mat(xArr); yMat = np.mat(yArr).T
    yMean = np.mean(yMat,0)
    yMat = yMat - yMean
    xMean = np.mean(xMat, 0)
    xVar = np.var(xMat, 0)
    xMat = (xMat - xMean) / xVar
    numTest = 30
    wMat = np.ones((numTest, np.shape(xMat)[1]))
    for i in range(30):
        ws = ridgeRegress(xMat, yMat, np.exp(i-10))
        wMat[i,:] = ws.T
    return wMat

 

前向逐步回归

def rssError(yArr, yHatArr):
    return ((yArr - yHatArr)**2).sum()

def regularize(xMat):
    inMat = xMat.copy()
    inMatMean = np.mean(inMat,0)
    inMatVar = np.var(inMat,0)
    inMat = (inMat - inMatMean)/inMatVar
    return inMat

def stageWise(xArr, yArr, eps = 0.01, numIt = 100):
    xMat = np.mat(xArr); yMat = np.mat(yArr).T
    yMean = np.mean(yMat,0)
    yMat = yMat - yMean
    xMat = regularize(xMat)
    m,n = np.shape(xMat)
    retMat = np.ones((numIt,n))
    ws = np.ones((n,1))
    wsTest = ws.copy()
    wsMax = ws.copy()
    for i in range(numIt):
        print ws.T
        lowestError = np.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 = wsMax.copy()
        retMat[i,:] = ws.T
    return retMat