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
局部加权线性回归
(根据数据来局部调整预测)
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
缩减系数来理解数据
当特征大于样本数量,则无法再计算,因为此时矩阵为非满秩矩阵,计算逆会出现问题
岭回归
通过加入对角线为1其余为0的单位矩阵的系数倍数使得矩阵非奇异。
能够减少不重要的参数。
def ridgeRegres(xMat,yMat,lam=0.2):
xTx = xMat.T*xMat
denom = xTx + eye(shape(xMat)[1])*lam
if 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 = mat(xArr); yMat=mat(yArr).T
yMean = mean(yMat,0)
yMat = yMat - yMean #to eliminate X0 take mean off of Y
#regularize X's
xMeans = mean(xMat,0) #calc mean then subtract it off
xVar = var(xMat,0) #calc variance of Xi then divide by it
xMat = (xMat - xMeans)/xVar
numTestPts = 30
wMat = zeros((numTestPts,shape(xMat)[1]))
for i in range(numTestPts):
ws = ridgeRegres(xMat,yMat,exp(i-10))
wMat[i,:]=ws.T
return wMat
前向逐步线性回归
def stageWise(xArr,yArr,eps=0.01,numIt=100):
xMat = mat(xArr); yMat=mat(yArr).T
yMean = mean(yMat,0)
yMat = yMat - yMean #can also regularize ys but will get smaller coef
xMat = regularize(xMat)
m,n=shape(xMat)
returnMat = zeros((numIt,n)) #testing code remove
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
权衡偏差和方差
示例:预测乐高玩具套装的价格
获取数据
from time import sleep
import json
import urllib.request
def searchForSet(retX, retY, setNum, yr, numPce, origPrc):
sleep(10)
myAPIstr = 'AIzaSyD2cR2KFyx12hXu6PFU-wrWot3NXvko8vY'
searchURL = 'https://www.googleapis.com/shopping/search/v1/public/products?key=%s&country=US&q=lego+%d&alt=json' % (myAPIstr, setNum)
pg = urllib.request.urlopen(searchURL)
retDict = json.loads(pg.read())
for i in range(len(retDict['items'])):
try:
currItem = retDict['items'][i]
if currItem['product']['condition'] == 'new':
newFlag = 1
else: newFlag = 0
listOfInv = currItem['product']['inventories']
for item in listOfInv:
sellingPrice = item['price']
if sellingPrice > origPrc * 0.5:
print("%d\t%d\t%d\t%f\t%f" % (yr,numPce,newFlag,origPrc, sellingPrice))
retX.append([yr, numPce, newFlag, origPrc])
retY.append(sellingPrice)
except: print('problem with item %d' % i)
def setDataCollect(retX, retY):
searchForSet(retX, retY, 8288, 2006, 800, 49.99)
searchForSet(retX, retY, 10030, 2002, 3096, 269.99)
searchForSet(retX, retY, 10179, 2007, 5195, 499.99)
searchForSet(retX, retY, 10181, 2007, 3428, 199.99)
searchForSet(retX, retY, 10189, 2008, 5922, 299.99)
searchForSet(retX, retY, 10196, 2009, 3263, 249.99)