def test():
to_run = [40, 60, 80, 100]
for i in to_run:
start_time = time.time()
method = Greedy(i, datapre.Features(),
datapre.CategoriesDistribution(), 0.1555)
# profiles = method.SearchWithoutConstraints()
# profiles = method.SearchWithConstraints()
profiles = method.SearchWithReplace()
# print len(profiles)
end_time = time.time()
# 将结果写入文件
with open("%dGB_results" % i, "wb") as f:
f.write("cost %f s" % (end_time - start_time))
f.write("\n")
f.write("Attribute Representativeness is:")
f.write(str(method.AttributeRepresentative(profiles)))
f.write("\n")
for profile in profiles:
f.write(profile + "\t")
# test()
def ProfileDomainDistribution(profiles):
features = datapre.Features()
categories = [
'Politics', 'Religion', 'Military', 'Education', 'Economy',
'Technology', 'Agriculture', 'Sports', 'Entertainment'
]
number = [0 for i in range(len(categories))]
for profile in profiles:
for i in range(len(categories)):
if features[profile][5] == categories[i]:
number[i] += 1
return number
def test():
method = Classifier(datapre.Features())
train_set,test_set = method.Split()
print "数据集分割完成"
print "训练集和测试集数量为:%d,%d" % (len(train_set),len(test_set))
# 三个方法分别在train_set中寻找100个代表性人物,用代表性人物来分类test_set
epsilons = [0.1560,0.1556,0.1555]
# 将PageRank提取出来的100个用户也来做个分类
# PageRank_method = pr.PageRank(40,train_set,datapre.GetUserCategory())
# # 获得出入度矩阵
# uMatrix = PageRank_method.GetUserMatrix()
# #
# # 转移矩阵
# fMatrix = mat([(1 - 0.85) / len(train_set.keys()) for i in range(len(train_set.keys()))]).T
# # 初始矩阵
# initPRMatrix = mat([1 for i in range(len(train_set.keys()))]).T
# # result为影响力分数结果
# PRMatrix = PageRank_method.PageRank(uMatrix,fMatrix,0.85,initPRMatrix,0.01,120)
# user_ids = train_set.keys()
# uPR = {}
# for i,id in zip(range(len(user_ids)),user_ids):
# uPR[id] = PRMatrix[i]
# # 对uPR排序
# uPR = sorted(uPR.items(),key = lambda dic:dic[1],reverse=True)
# profiles = [u[0] for u in uPR[:100]]
# print "PageRank的分类准确性为%.3f" % method.Classify(profiles,test_set)
# return
# epsilons = [0.1556,0.1555]
# epsilons = [0.1560]
# init.InitialMatrix(train_set)
number = [40,60,80,100]
print "开始抽取代表性用户"
for epsilon in epsilons:
with open("%.4f" % epsilon,"wb") as f:
for k in number:
profiles1 = greedy.Greedy(k,train_set,datapre.CategoriesDistribution(),epsilon).SearchWithReplace()
print "GB方法计算完成"
profiles2 = kmediods.KMedoids(k,train_set,datapre.CategoriesDistribution(),epsilon).Search()
print "kmedoids方法计算完成"
profiles3 = sa.SAalgo(k,train_set,datapre.CategoriesDistribution(),epsilon,0.3,10,0.9).Search()
print "sa方法计算完成"
accuracy1 = method.Classify(profiles1,test_set)
f.write("方法:GB; 典型阈值:%f; 代表性子集数量:%d; 准确率:%.3f \n" % (epsilon,k,accuracy1))
accuracy2 = method.Classify(profiles2,test_set)
f.write("方法:kmedoids; 典型阈值:%f; 代表性子集数量:%d; 准确率:%.3f \n" % (epsilon,k,accuracy2))
accuracy3 = method.Classify(profiles3,test_set)
f.write("方法:SA; 典型阈值:%f; 代表性子集数量:%d; 准确率:%.3f \n" % (epsilon,k,accuracy3))
print "方法:GB; 典型阈值:%f; 代表性子集数量:%d; 准确率:%.3f \n" % (epsilon,k,accuracy1)
print "方法:kmedoids; 典型阈值:%f; 代表性子集数量:%d; 准确率:%.3f \n" % (epsilon,k,accuracy2)
print "方法:SA; 典型阈值:%f; 代表性子集数量:%d; 准确率:%.3f \n" % (epsilon,k,accuracy3)
def test():
features = datapre.Features()
to_run = [40, 60, 80, 100]
for i in to_run:
start_time = time.time()
method = KMedoids(i, datapre.Features(),
datapre.CategoriesDistribution(), 0.1555)
profiles = method.Search()
end_time = time.time()
print metric.AttributeRepresentative(features, profiles)
print profiles
print "cost %f s" % (end_time - start_time)
with open("%dclustering_result" % i, "wb") as f:
f.write("cost %f s" % (end_time - start_time))
f.write("\n")
f.write("Attribute Representativeness is:")
f.write(str(metric.AttributeRepresentative(features, profiles)))
f.write("\n")
for profile in profiles:
f.write(profile + "\t")
# test()
def Run():
features = datapre.Features()
epsilons = [0.1560, 0.1556, 0.1555]
number = [40, 60, 80, 100]
for epsilon in epsilons:
for n in number:
start_time = time.time()
profile1 = greedy.Greedy(n, features,
datapre.CategoriesDistribution(),
epsilon).SearchWithReplace()
end_time = time.time()
with open("GB%d_%.4f" % (n, epsilon), "wb") as f:
f.write("cost %f s" % (end_time - start_time))
f.write("Attribute Representativeness is:")
f.write(str(metric.AttributeRepresentative(features,
profile1)))
f.write("\n")
for profile in profile1:
f.write(profile + "\t")
start_time = time.time()
profile2 = kmedoids.KMedoids(n, features,
datapre.CategoriesDistribution(),
epsilon).Search()
end_time = time.time()
with open("kmedoids%d_%.4f" % (n, epsilon), "wb") as f:
f.write("cost %f s" % (end_time - start_time))
f.write("Attribute Representativeness is:")
f.write(str(metric.AttributeRepresentative(features,
profile2)))
f.write("\n")
for profile in profile2:
f.write(profile + "\t")
start_time = time.time()
profile3 = sa.SAalgo(n, features, datapre.CategoriesDistribution(),
epsilon, 0.3, 10, 0.9).Search()
end_time = time.time()
with open("sa%d_%.4f" % (n, epsilon), "wb") as f:
f.write("cost %f s" % (end_time - start_time))
f.write("Attribute Representativeness is:")
f.write(str(metric.AttributeRepresentative(features,
profile3)))
f.write("\n")
for profile in profile3:
f.write(profile + "\t")
