def to_article(rank, lda):
# rank 排序后的主题列表
value = np.arange(1, 0, -0.1) # 主题对应的分值 np.arange(1,0,-0.1)
tp = pickle.load(open(r"D:\citeulike\dic\all_" + lda[:-4] + ".dump", "r"))
# 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 rank:
if n in tp[m].keys():
j = rank.index(n)
# 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 = value[j] * 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
def to_article(rank,lda):
#rank 排序后的主题列表
value = np.arange(1,0,-0.1) # 主题对应的分值 np.arange(1,0,-0.1)
tp = pickle.load(open(r'D:\citeulike\dic\all_'+lda[:-4]+'.dump', 'r'))
# 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 rank:
if n in tp[m].keys():
j = rank.index(n)
# 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 = value[j] * 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
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
