def get_tp():
# 获取16000篇文章的每篇文章概率主题分布，保存便于调用。
topic_list = []
diction = gensim.corpora.Dictionary.load("citeulike.dict")
batch_lda = gensim.models.LdaModel.load("online_lda_100.lda")
content = open(r"D:\citeulike\dic\temp.dat", "r").readlines()
for i in content:
text_list = stopword.get_txt(i)
doc_bow = diction.doc2bow(text_list)
doc_lda = batch_lda[doc_bow]
topic_list.append(dict(doc_lda)) # 以字典的形式存储，方便获取
pickle.dump(topic_list, open(r"D:\citeulike\dic\all_onlinetopic_100.dump", "w"))
def get_tp():
# 获取16000篇文章的每篇文章概率主题分布，保存便于调用。
topic_list = []
diction = gensim.corpora.Dictionary.load('citeulike.dict')
batch_lda = gensim.models.LdaModel.load('online_lda_100.lda')
content = open(r'D:\citeulike\dic\temp.dat', 'r').readlines()
for i in content:
text_list = stopword.get_txt(i)
doc_bow = diction.doc2bow(text_list)
doc_lda = batch_lda[doc_bow]
topic_list.append(dict(doc_lda)) # 以字典的形式存储，方便获取
pickle.dump(topic_list, open(r'D:\citeulike\dic\all_onlinetopic_100.dump', 'w'))
def get_topic(texts, lda):
#获取输入文章的主题概率分布
dict_sim1 = {}
sim = pickle.load(
open(r'D:\citeulike\dic\topic_' + lda[:-4] + '.dump', 'r'))
diction = gensim.corpora.Dictionary.load('citeulike.dict')
batch_lda = gensim.models.LdaModel.load(r'D:\citeulike\dic' + '\\' + lda)
text = input_article(texts)
text_list = stopword.get_txt(text)
doc_bow = diction.doc2bow(text_list)
doc_lda = batch_lda[doc_bow]
#print doc_lda
#元组不可变，更改为列表
tp_batch = []
for yuanzu in doc_lda:
tp_batch.append(list(yuanzu))
#归一化
sum0 = 0
t = 0
for m in range(len(doc_lda)):
if tp_batch[m][1] > 0.1:
t += 1
sum0 += tp_batch[m][1]
for n in range(len(doc_lda)):
if tp_batch[n][1] > 0.1:
tp_batch[n][1] = tp_batch[n][1] / sum0
for (tp_id, rate) in tp_batch:
if rate > 0.1:
dict_sim2 = {}
wordsNum = int(round((10 - t) * rate))
#print tp_id
#print wordsNum
#从相似性矩阵中获取wordnum个最相似的主题
sim_1 = sorted(sim[tp_id], reverse=True)
sim_2 = sim_1[1:wordsNum + 1]
#print sim_2
for i in sim_2:
dict_sim2[sim[tp_id].index(i)] = i #index获取列表中对应元素的下标
if tp_id in dict_sim2.keys():
dict_sim2[tp_id] += 1.0
else:
dict_sim2[tp_id] = 1.0 #加入文章的主题，概率设为10
dict_sim1[tp_id] = dict_sim2
#最终返回字典形式，{文章主题i:{相似主题j:相似度,···},{},···}
#print dict_sim1
return dict_sim1
def get_topic(texts,lda):
#获取输入文章的主题概率分布
dict_sim1 = {}
sim = pickle.load(open(r'D:\citeulike\dic\topic_'+lda[:-4]+'.dump','r'))
diction = gensim.corpora.Dictionary.load('citeulike.dict')
batch_lda = gensim.models.LdaModel.load(r'D:\citeulike\dic'+'\\'+lda)
text = input_article(texts)
text_list = stopword.get_txt(text)
doc_bow = diction.doc2bow(text_list)
doc_lda = batch_lda[doc_bow]
#print doc_lda
#元组不可变，更改为列表
tp_batch = []
for yuanzu in doc_lda:
tp_batch.append(list(yuanzu))
#归一化
sum0 = 0
t = 0
for m in range(len(doc_lda)):
if tp_batch[m][1] > 0.1:
t += 1
sum0 += tp_batch[m][1]
for n in range(len(doc_lda)):
if tp_batch[n][1] > 0.1:
tp_batch[n][1] = tp_batch[n][1]/sum0
for (tp_id,rate) in tp_batch:
if rate >0.1:
dict_sim2 = {}
wordsNum = int(round((10-t)*rate))
#print tp_id
#print wordsNum
#从相似性矩阵中获取wordnum个最相似的主题
sim_1 = sorted(sim[tp_id],reverse=True)
sim_2 = sim_1[1:wordsNum+1]
#print sim_2
for i in sim_2:
dict_sim2[sim[tp_id].index(i)] = i #index获取列表中对应元素的下标
if tp_id in dict_sim2.keys():
dict_sim2[tp_id] += 1.0
else:
dict_sim2[tp_id] = 1.0 #加入文章的主题，概率设为10
dict_sim1[tp_id] = dict_sim2
#最终返回字典形式，{文章主题i:{相似主题j:相似度,···},{},···}
#print dict_sim1
return dict_sim1
def word(page):
#计算推荐的文章page在给定主题topics下的单词概率和
topic_rate_new = 0
content_list = stopword.get_txt(txt[page])
doc_bow = diction.doc2bow(content_list)
doc_lda = batch_lda[doc_bow]
for j in range(len(doc_lda)):
dic = {}
word_rate = 0
tp_id = doc_lda[j][0]
if tp_id in topics:
word_list = batch_lda.show_topic(tp_id, 500000)
dic = dict(word_list) # 将showtopic的[(a,b),(),()]形式转换成字典
for w in list(set(content_list)):
# print dic[w]
word_rate += dic[w] # 计算总的主题下单词概率
# 乘以该主题的概率并除以文章内单词总个数，防止有些文章词很多，值也就很大
topic_rate = doc_lda[j][1] * word_rate / len(set(content_list))
topic_rate_new += topic_rate
#print topic_rate_new
return topic_rate_new
'''
def word(page):
#计算推荐的文章page在给定主题topics下的单词概率和
topic_rate_new = 0
content_list = stopword.get_txt(txt[page])
doc_bow = diction.doc2bow(content_list)
doc_lda = batch_lda[doc_bow]
for j in range(len(doc_lda)):
dic = {}
word_rate = 0
tp_id = doc_lda[j][0]
if tp_id in topics:
word_list = batch_lda.show_topic(tp_id, 500000)
dic = dict(word_list) # 将showtopic的[(a,b),(),()]形式转换成字典
for w in list(set(content_list)):
# print dic[w]
word_rate += dic[w] # 计算总的主题下单词概率
# 乘以该主题的概率并除以文章内单词总个数，防止有些文章词很多，值也就很大
topic_rate = doc_lda[j][1] * word_rate / len(set(content_list))
topic_rate_new += topic_rate
#print topic_rate_new
return topic_rate_new
'''
def get_tp(nom):
text_list = stopword.get_txt(content[nom])
doc_bow = diction.doc2bow(text_list)
doc_lda = batch_lda[doc_bow]
tp_batch = []
for yuanzu in doc_lda:
tp_batch.append(list(yuanzu))
#归一化
dict_sim1 = {}
sum0 = 0
t = 0
for m in range(len(doc_lda)):
if tp_batch[m][1] > 0.1:
t += 1
sum0 += tp_batch[m][1]
for n in range(len(doc_lda)):
if tp_batch[n][1] > 0.1:
tp_batch[n][1] = tp_batch[n][1]/sum0
for (tp_id,rate) in tp_batch:
if rate >0.1:
dict_sim2 = {}
wordsNum = int(round((10-t)*rate))
#print tp_id
#print wordsNum
#从相似性矩阵中获取wordnum个最相似的主题
sim_1 = sorted(sim[tp_id],reverse=True)
sim_2 = sim_1[1:wordsNum+1]
#print sim_2
for i in sim_2:
dict_sim2[sim[tp_id].index(i)] = i #index获取列表中对应元素的下标
'''
if tp_id in dict_sim2.keys():
dict_sim2[tp_id] += 1.0
else:
dict_sim2[tp_id] = 1.0 #加入文章的主题，概率设为1
'''
dict_sim1[tp_id] = dict_sim2
tp_list = []
for i in dict_sim1.values():
for j in i.keys():
tp_list.append(j)
tp_list2 = list(set(tp_list))
tp = pickle.load(open(r'D:\citeulike\dic\all_online_lda_100.dump', 'r'))
#def to_article(rank):
# 遍历每篇文章，通过排序后主题计算与该主题最相关的文章
rank_list = []
for m in range(len(tp)):
rate2 = 0
t = 0
nov_rate = rank_topic.seen('1', m) # 乘以新奇性
for n in tp_list2:
if n in tp[m].keys():
# 计算排序主题与主题概率的乘积，方便选取最相似的文章
rate = tp[m][n]
t = t + 1
else:
rate = 0
rate2 += rate
if t != 0:
# 乘以文章新奇性概率，除以文章中主题出现在rank中的个数，防止主题过多，结果越大
sum_rate = rate2 * nov_rate / t
else:
sum_rate = rate2 * nov_rate
rank_list.append(sum_rate) # 按文章顺序排列的相似性值
return rank_list