def stageWise(xArr,yArr,eps=0.01,numIt=100):
xMat = mat(xArr); yMat=mat(yArr).T
yMean = mean(yMat,0) #按照行取平均，每行平均
yMat = yMat - yMean #对y进行标准化 #can also regularize ys but will get smaller coef
xMat = regression.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]: #分别计算增加或减少该特征对误差的影响
wsTest = ws.copy()
wsTest[j] += eps*sign
yTest = xMat*wsTest
rssE = rssError(yMat.A,yTest.A)
if rssE < lowestError: #如果误差error小于当前最小误差lowesterror：设置wbest等于当前的w
lowestError = rssE
wsMax = wsTest
ws = wsMax.copy()
# returnMat[i,:]=ws.T
# return returnMat
# xArr,yArr = regression.loadDataSet('abalone.txt')
# # print('逐步向前回归结果：');print(regression.stageWise(xArr,yArr,0.001,5000))
# xMat = mat(xArr)
# yMat = mat(yArr).T
# xMat = regression.regularize(xMat)
# yM = mean(yMat,0)
# yMat = yMat - yM
# weights = regression.standRegres(xMat,yMat.T)
# print('最小二乘法：'); print(weights.T)
# #OUTPUT:
# #[[ 0.0430442 -0.02274163 0.13214087 0.02075182 2.22403814 -0.99895312
# # -0.11725427 0.16622915]]
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 ws
predictList = []
for tTSize in predictTaskSizeList:
taskX = int(sqrt(tTSize))
while(tTSize % taskX != 0):
taskX -= 1
taskY = tTSize/taskX
xCheckMat = mat([myUtils.getConstantValue(), tTSize, taskX, taskY, predictHours], dtype = float)
preDictPerTask = []
for taskIdx in range(1,2):
xMat, yMat = myUtils.getXandYMatfromList(trainDataList[taskIdx], 2)
xMat = mat(xMat, dtype = float)
yMat = mat(yMat, dtype = float)
#Regularize the matrix
xMat[:, 1:], xMeans, xStd = regression.regularize(xMat[:, 1:])
xCheckMat[:, 1:] = (xCheckMat[:, 1:] - xMeans)/xStd
preDictPerComponent = []
for yIdx in range(0, 2): #caculate computing result and then communication result
yMatTmp = yMat[:, yIdx]
taskPredict = 0
for kElement in bestKList:
taskPredict = 0
#get the result for cared data
wr = regression.lwlr(xCheckMat, xMat,yMatTmp.T,kElement)
#wr = regression.standRegres(xMat,yMatTmp.T)
if (wr != None):
#print wr
taskPredict = xCheckMat * wr
fr = open("/home/yu/workspace/machine-learning-class/ex1/ex1data2.txt")
xMat = []
yMat = []
for line in fr.readlines():
tmpEle = line.split(',')
xMat.append([1, tmpEle[0], tmpEle[1]])
yMat.append([tmpEle[2]])
bestKList = [
10
] #[0.07, 0.3, 0.1, 0.7, 3, 10, 28, 40, 60, 80, 100]#[100, 80, 60, 40, 28, 10, 3, 0.7, 0.3, 0.07, 0.01]
xCheckMat = mat([1, 1650, 3], dtype=float)
xMat = mat(xMat, dtype=float)
yMat = mat(yMat, dtype=float)
#Regularize the matrix
xMat[:, 1:], xMeans, xStd = regression.regularize(xMat[:, 1:])
xCheckMat[:, 1:] = (xCheckMat[:, 1:] - xMeans) / xStd
for kElement in bestKList:
taskPredict = 0
#get the result for cared data
wr = regression.lwlr(xCheckMat, xMat, yMat.T, kElement)
#wr = regression.standRegres(xMat,yMat.T)
if (wr != None):
print wr
taskPredict = xCheckMat * wr
print taskPredict
break
import regression
from numpy import *
xArr, yArr = regression.loadDataSet('abalone.txt')
regression.stageWise(xArr, yArr, 0.01, 200)
regression.stageWise(xArr, yArr, 0.001, 5000)
xMat = mat(xArr)
yMat = mat(yArr).T
xMat = regression.regularize(xMat)
yM = mean(yMat, 0)
yMat = yMat - yM
weights = regression.standRegres(xMat, yMat.T)
print(weights.T)
print regression.rssError(abY[100:199], yHat.T.A)
ridgeWeights = regression.ridgeTest(abX, abY)
#print ridgeWeights
import matplotlib.pyplot as plt
fig = plt.figure()
ax = fig.add_subplot(111)
ax.plot(ridgeWeights)
plt.show()
xArr, yArr = regression.loadDataSet('abalone.txt')
#regression.stageWise(xArr, yArr, 0.01, 200)
#regression.stageWise(xArr, yArr, 0.001, 5000)
xMat, yMat = mat(xArr), mat(yArr).T
xMat = regression.regularize(xMat)
yM = mean(yMat, 0)
yMat = yMat - yM
weights = regression.standRegres(xMat, yMat.T)
print weights.T
weights = regression.stageWise(xArr, yArr, 0.005, 1000)
fig = plt.figure()
ax = fig.add_subplot(111)
ax.plot(weights)
plt.show()
'''
lgX, lgY = [], []
regression.setDataCollect(lgX, lgY)
print shape(lgX)