[机器学习]前向逐步回归

前向逐步回归算法可以得到与lasso差不多的效果，但更加简单。它属于一种贪心算法，即每一步都尽可能的减少误差。

数据如下：

图片

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

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 regularize(xMat):#regularize by columns
    inMat = xMat.copy()
    inMeans = mean(inMat,0)   #calc mean then subtract it off
    inVar = var(inMat,0)      #calc variance of Xi then divide by it
    inMat = (inMat - inMeans)/inVar
    return inMat

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


def main():
    xArr,yArr = loadDataSet('abalone.txt')
    stageWise(xArr,yArr,0.001,5000)
if __name__ == '__main__':
    main()

看一下结果：

图片一