num_words = 50
print('本院系文章总数为%d，即将分为主题数%d个，关键字%d个......' %
(len(corpus), num_topics, num_words))
ldamodel = gensim.models.ldamodel.LdaModel(corpus,
num_topics=num_topics,
id2word=dictionary,
passes=50)
result = ldamodel.print_topics(num_topics=num_topics, num_words=num_words)
time2 = time.time()
print(time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(time.time())))
print('模型训练用时：', time2 - time1)
print('LDA模型训练完成。插入数据库......')
doc_lda = ldamodel[corpus]
for n in range(len(doc_lda)):
Topic = doc_lda[n]
wordTopic = [i[1] for i in result if int(Topic[0][0]) == i[0]]
d = strToMap(wordTopic[0])
t = {}
for key in DocWord[n]:
if key in d.keys():
t[key] = d[key]
topic = Topic[0][0]
prams = (institution_paper_list[n][0], "topic" + str(topic),
json.dumps(d,
ensure_ascii=False), json.dumps(t, ensure_ascii=False))
sql = 'insert into lda2 values(%s,%s,%s,%s)'
list = dbs.exe_sql(sql, prams)
print("结束")
print(time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(time.time())))
if len(a) >= 1 and name != a['name']:
find = False
for t in teacher:
if a['name'] == t['name'] and (len(
a['org']) == 0 or a['org'].find(t['school']) >= 0):
find = True
key = id + '_' + str(t['id']) + '_' + a['name']
if key in egoNet.keys():
if l['id'] not in egoNet[key]:
egoNet[key].append(l['id'])
else:
egoNet[key] = []
egoNet[key].append(l['id'])
if find == False:
key = id + '_-1_' + a['name'] + '*' + a['org']
if key in egoNet.keys():
if l['id'] not in egoNet[key]:
egoNet[key].append(l['id'])
else:
egoNet[key] = []
egoNet[key].append(l['id'])
for e in egoNet:
id = e.split('_')
try:
parm = (id[0], id[1], id[2], len(egoNet[e]))
except:
print(e)
sql = 'insert into ego_network values(null,%s,%s,%s,%s)'
dbs.exe_sql(sql, parm)