def test1(self):
import numpy as np
fileIndex = 1
for i in xrange(1):
# userEui = np.loadtxt(ROOT_DIRECTORY + "/userEui" + str(fileIndex) + ".txt")
userEui = np.loadtxt(ROOT_DIRECTORY + "/userEui.txt")
# wsEui = np.loadtxt(ROOT_DIRECTORY + "/wsEui" + str(fileIndex) + ".txt")
wsEui = np.loadtxt(ROOT_DIRECTORY + "/wsEui.txt")
fileIndex = fileIndex + 1
alpha = 0.4
count = 0
totalQos = 0
testArr = paper.loadTest(ROOT_DIRECTORY + '/test1.txt')
minMae = 1000
minAlpha = 10
for i in xrange(11):
eui = []
alpha = i / 10.0
totalQos = 0
for index, value in enumerate(userEui):
totalQos = totalQos + testArr[index][2]
eui.append(testArr[index][2] - alpha * value -
(1 - alpha) * wsEui[index])
eui = np.array(eui)
mae, rmse = paper.maeAndRmse(eui)
if mae < minMae:
minMae = mae
minAlpha = alpha
print "alpha:" + str(alpha) + "\t" + "MAE:" + str(
mae) + "\tRMSE:" + str(rmse) + "\tNMAE:" + str(
totalQos / len(testArr))
print "最小mae:" + str(minMae) + "\t alpha=" + str(minAlpha)
def testTp(self):
simCalMethod = paper.simPCC
sparseness = 20
fileNumbers = 10
for i in range(1, fileNumbers + 1):
#文件对象
print i,
euiFileName = 'throught/ipcc/euislopeone-%d-%d.txt' % (sparseness,
i)
pfEui = open(euiFileName, 'w')
#load data
trainFileName = r'throught/training%d-%d.txt' % (sparseness, i)
trainArrayObj = paper.createArrayObj(trainFileName)
testFileName = r'throught/test%d-%d.txt' % (sparseness, i)
testArrayObj = paper.loadTest(testFileName)
#相似度矩阵数据
wsSimFileName = 'throught/ipcc/simArrayWs-%d-%d.txt' % (sparseness,
i)
wsSimArrayObj = paper.createSimArray(trainArrayObj.T, simCalMethod)
paper.save(wsSimArrayObj, wsSimFileName)
# wsSimArrayObj = paper.load(wsSimFileName)
#计算预测准确
print calMaeAndRmse(trainArrayObj, testArrayObj, wsSimArrayObj,
pfEui)
pfEui.close()
print 'ok'
def calmaeAndNmae(euiFile, testFileName):
import paper
import numpy as np
#cal the mae
eui = np.loadtxt(euiFile)
mae = np.mean(np.abs(eui))
#cal the NMAE
testArrayObj = paper.loadTest(testFileName)
mean = np.mean(testArrayObj[:, 2])
nmae = mae/mean
return mae, nmae
def testTp(self):
sparseness = 5
fileNumbers = 2
for i in range(1, fileNumbers + 1):
p, q = loadPQTp(sparseness, i)
pfEui = 'throught/eui/euipq-%d-%d.txt' % (sparseness, i)
pf = open(pfEui, 'w')
#测试测试数据
testFileName = r'throught/test%d-%d.txt' % (sparseness, i)
testArrayObj = paper.loadTest(testFileName)
predWithPQTp(testArrayObj, pf, p, q)
pf.close()
def testTp(self):
for sparseness in [5, 10, 15, 20]:
for i in range(1, fileNumbers+1):
#文件对象
print i,
euiFileName = 'throught/weightedslopeone/euislopeone-%d-%d.txt' % (sparseness,i)
pfEui = open(euiFileName, 'w')
#load data
trainFileName = r'throught/training%d-%d.txt' % (sparseness, i)
trainArrayObj = paper.createArrayObj(trainFileName)
testFileName = r'throught/test%d-%d.txt' % (sparseness, i)
testArrayObj = paper.loadTest(testFileName)
#计算预测准确
print calMaeAndRmse(trainArrayObj, testArrayObj, pfEui)
pfEui.close()
print 'ok'
def testRt(self):
sparseness = 5
fileNumbers = 10
for i in range(1, fileNumbers + 1):
#文件对象
print i,
euiFileName = 'rt/userMean/euislopeone-%d-%d.txt' % (sparseness, i)
pfEui = open(euiFileName, 'w')
#load data
trainFileName = r'rt/sparseness%d/training%d.txt' % (sparseness, i)
trainArrayObj = paper.createArrayObj(trainFileName)
testFileName = r'rt/sparseness%d/test%d.txt' % (sparseness, i)
testArrayObj = paper.loadTest(testFileName)
#计算预测准确
print calMaeAndRmse(trainArrayObj, testArrayObj, pfEui)
pfEui.close()
print 'ok'
def testRt(self):
for sparseness in [5, 10, 15, 20]:
for i in range(1, fileNumbers + 1):
#文件对象
print i,
euiFileName = 'rt/mf/euislopeone-%d-%d.txt' % (sparseness, i)
pfEui = open(euiFileName, 'w')
#load data
trainFileName = r'rt/sparseness%d/training%d.txt' % (
sparseness, i)
trainArrayObj = paper.createArrayObj(trainFileName)
testFileName = r'rt/sparseness%d/test%d.txt' % (sparseness, i)
testArrayObj = paper.loadTest(testFileName)
#计算预测准确
p, q = learningAddIndicateFunctionlfm(trainArrayObj)
maeAndRmseRt(p, q, testArrayObj, pfEui)
pfEui.close()
print 'ok'
def testTp(self):
for sparseness in [5, 10, 15, 20]:
for i in range(1, fileNumbers + 1):
#文件对象
print i,
euiFileName = 'throught/mf/euislopeone-%d-%d.txt' % (
sparseness, i)
pfEui = open(euiFileName, 'w')
#load data
trainFileName = r'throught/training%d-%d.txt' % (sparseness, i)
trainArrayObj = paper.createArrayObj(trainFileName)
testFileName = r'throught/test%d-%d.txt' % (sparseness, i)
testArrayObj = paper.loadTest(testFileName)
#计算预测准确
trainArrayObj[trainArrayObj != NoneValue] = (
trainArrayObj[trainArrayObj != NoneValue] -
44.034) / 107.439
p, q = learningAddIndicateFunctionlfm(trainArrayObj)
maeAndRmseTp(p, q, testArrayObj, pfEui)
pfEui.close()
print 'ok'
def test1(self):
import numpy as np
trainingArr = createArrayObj(ROOT_DIRECTORY + '/training1.txt', 339,
5825)
simUserArr = np.loadtxt(ROOT_DIRECTORY + "/simUserArr.txt")
simWsArr = np.loadtxt(ROOT_DIRECTORY + "/simWsArr.txt")
webServerMapping = np.loadtxt(ROOT_DIRECTORY + "/webServerMapping.txt",
dtype=str,
delimiter="\t")
maxSimUser = np.argsort(simUserArr, axis=1)[:, 0 - 10:]
testArr = paper.loadTest(ROOT_DIRECTORY + '/test1.txt')
#标签
pui = np.loadtxt(ROOT_DIRECTORY + "/label.txt")
#标签－概率
probability = np.loadtxt(ROOT_DIRECTORY + "/probability.txt")
# 取出相似度最高的k个用户
k_user = 10
k_ws = 10
result = []
fileIndex = 1
for i in xrange(1):
k_user = 10 + i * 10
for j in xrange(1):
k_ws = 50 + j * 10
simUser = np.argsort(simUserArr, axis=1)[:, 0 - k_user:]
simWs = np.argsort(simWsArr, axis=1)[:, 0 - k_ws:]
eui = []
# 用户－服务
for index, value in enumerate(testArr):
uId = value[0]
wsId = value[1]
label = pui[index]
fenzi = 0
fenmu = 0
# 相似用户－相似度
for i, otherUId in enumerate(simUser[uId]):
#pow(simUserArr[uId][otherUId], 3)
#simUserArr[uId][otherUId]
if trainingArr[otherUId][wsId] != NoneValue and int(
trainingArr[otherUId][wsId]) in label:
fenzi += simUserArr[uId][otherUId] * trainingArr[
otherUId][wsId] * probability[otherUId][
np.argwhere(label == int(
trainingArr[otherUId][wsId]))[0, 0]]
fenmu += simUserArr[uId][otherUId] * probability[
otherUId][np.argwhere(label == int(
trainingArr[otherUId][wsId]))[0, 0]]
if fenmu != 0:
predictValue = fenzi / fenmu
r = predictValue - value[2]
if r < 0:
r = 0 - r
eui.append(r)
else:
total = 0
count = 0
for i, otherUId in enumerate(maxSimUser[uId]):
for m, n in enumerate(simWs[wsId]):
# if webServerMapping[wsId][2] != webServerMapping[n][2] and webServerMapping[wsId][4] != webServerMapping[n][4]:
# continue;
#maxSimUser[uId][0]
if trainingArr[otherUId][n] != NoneValue:
count = count + 1
total += trainingArr[otherUId][n]
if count != 0:
avg = total / count
if avg < 0:
avg = 0 - avg
eui.append(avg)
print len(eui)
eui = np.array(eui)
mae, rmse = paper.maeAndRmse(eui)
result.append("相似用户数:" + str(k_user) + "\t相似服务数:" + str(k_ws) +
"\t" + "MAE:" + str(mae) + "\tRMSE:" + str(rmse))
print "相似用户数:" + str(k_user) + "\t相似服务数:" + str(
k_ws) + "\t" + "MAE:" + str(mae) + "\tRMSE:" + str(rmse)
# np.savetxt(ROOT_DIRECTORY + "/result.txt", result, fmt='%s', delimiter="\t")
np.savetxt(ROOT_DIRECTORY + "/userEui.txt",
eui,
fmt='%s',
delimiter="\t")
# np.savetxt(ROOT_DIRECTORY + "/userEui" + str(fileIndex) + ".txt", eui, fmt='%s', delimiter="\t")
fileIndex = fileIndex + 1
def loadDataSet(trainFile, testFile):
import paper
trainArray = paper.createArrayObj(trainFile)
testObj = paper.loadTest(testFile)
return trainArray, testObj
def loadData(*dataFile):
import paper
train = paper.loadTest(dataFile[0])
test = paper.loadTest(dataFile[1])
return train, test
if __name__ == '__main__':
simCalMethod = paper.simPCC
fileNumbers = 10
for sparseness in [5, 10, 15, 20]:
#文件对象
for i in range(1, fileNumbers + 1):
print i,
# euiFileName = 'rt/upcc/euislopeone-%d-%d.txt' % (sparseness,i)
euiFileName = 'throught/upcc/euislopeone-%d-%d.txt' % (sparseness,
i)
pfEui = open(euiFileName, 'w')
#load data
# trainFileName = r'rt/sparseness%d/training%d.txt' % (sparseness, i)
# testFileName = r'rt/sparseness%d/test%d.txt' % (sparseness, i)
#throught
trainFileName = r'throught/training%d-%d.txt' % (sparseness, i)
testFileName = r'throught/test%d-%d.txt' % (sparseness, i)
trainArrayObj = paper.createArrayObj(trainFileName)
testArrayObj = paper.loadTest(testFileName)
#相似度矩阵数据
# userSimFileName = 'rt/upcc/simArrayUser-%s-%d.txt' % (sparseness,i)
userSimFileName = 'throught/upcc/simArrayUser-%s-%d.txt' % (
sparseness, i)
userSimArrayObj = paper.createSimArray(trainArrayObj, simCalMethod)
paper.save(userSimArrayObj, userSimFileName)
# userSimArrayObj = paper.load(userSimFileName)
#计算预测准确
mae, rmse = calMaeAndRmse()
print mae, rmse
pfEui.close()
print 'ok'
return pui
import math
import numpy as np
import paper
if __name__ == '__main__':
NoneValue = 111111.0
userNum = 339
wsNum = 5825
for sparseness in [5]:
for num in range(1, 2):
#文件对象
#load train and test
trainFile = r'rt/sparseness%d/training%d.txt' % (sparseness, num)
trainArrayObj = paper.createArrayObj(trainFile)
testFile = r'rt/sparseness%d/test%d.txt' % (sparseness, num)
testArrayObj = paper.loadTest(testFile)
#load train info and test info
trainFileInfo = r'data/sparseness%d/training%d.txt' % (sparseness,
num)
trainInfoObj = paper.loadTest(trainFileInfo)
testFileInfo = r'data/sparseness%d/test%d.txt' % (sparseness, num)
testInfoObj = paper.loadTest(testFileInfo)
#classify result
yClassify = classify(trainInfoObj, testInfoObj)
mae, rmse = calMaeAndRmse(trainArrayObj, testArrayObj, yClassify)
print
print mae, rmse
print 'ok'
def test1(self):
import numpy as np
trainingArr = createArrayObj(ROOT_DIRECTORY + '/training1.txt', 339,
5825)
simArr = createSimArray(trainingArr, paper.simMinkowskiDist, 2)
webServerMapping = np.loadtxt(ROOT_DIRECTORY + "/webServerMapping.txt",
dtype=str,
delimiter="\t")
# 取出相似度最高的k个用户
k = 10
simUser = np.argsort(simArr, axis=1)[:, 0 - k:]
testArr = paper.loadTest(ROOT_DIRECTORY + '/test1.txt')
pui = np.loadtxt(ROOT_DIRECTORY + "/label.txt")
probability = np.loadtxt(ROOT_DIRECTORY + "/probability.txt")
eui = []
# 用户－服务
for index, value in enumerate(testArr):
uId = value[0]
wsId = value[1]
label = pui[index]
fenzi = 0
fenmu = 0
# 相似用户－相似度
for i, otherUId in enumerate(simUser[uId]):
if trainingArr[otherUId][wsId] != NoneValue and int(
trainingArr[otherUId][wsId]) in label:
fenzi += simArr[uId][otherUId] * trainingArr[otherUId][
wsId] * probability[otherUId][np.argwhere(
label == int(trainingArr[otherUId][wsId]))[0, 0]]
fenmu += simArr[uId][otherUId] * probability[otherUId][
np.argwhere(
label == int(trainingArr[otherUId][wsId]))[0, 0]]
if fenmu != 0:
predictValue = fenzi / fenmu
eui.append(predictValue - value[2])
# else:
# if webServerMapping[wsId - 1][2] != 'not found':
# ii = 2
# else:
# ii = 4
# score = [ ]
# for g, h in enumerate(webServerMapping):
# if h[ii] == webServerMapping[wsId - 1][ii]:
# # 取出和i同个as的其他服务
# score.append(int(h[0]))
# total = 0
# count = 0
# for i, otherUId in enumerate(simUser[uId]):
# for m, n in enumerate(score):
# if trainingArr[otherUId][n] != NoneValue:
# count = count + 1
# total += trainingArr[otherUId][n]
# if count != 0:
# avg = total / count;
# eui.append(avg)
print len(eui)
eui = np.array(eui)
mae, rmse = paper.maeAndRmse(eui)
print "MAE:" + str(mae) + "\tRMSE:" + str(rmse)