top_percent=0.3)
for res_id, mer_id in mids:
# 将mer_id下的文本扔入res_id下的簇，remove mer_id的簇，同时重新计算各簇的特征词, 并计算文本权重, 并去重
temp_infos = event.get_subevent_infos(mer_id)
for r in temp_infos:
news = News(r["_id"], event.id)
news.update_news_subeventid(res_id)
event.remove_subevents([mer_id])
if __name__ == '__main__':
em = EventManager()
event_ids_list = []
# 获取做初始聚类的话题
initial_event_ids = em.getInitializingEventIDs()
event_ids_list.extend([(id, True) for id in initial_event_ids])
# 获取已做完初始聚类的活跃话题
active_event_ids = em.checkActive()
event_ids_list.extend([(id, False) for id in active_event_ids])
# map并行计算
pool = Pool()
pool.map(one_topic_merge, event_ids_list)
pool.close()
pool.join()
# 如果做计算时出错，更新last_modify, 并将modify_success设置为False
print '[Error]: ', e
event.setLastmodify(timestamp)
event.setModifysuccess(False)
if __name__ == '__main__':
from bson.objectid import ObjectId
# running_ids = [ObjectId("54c4df61d8b487851c2434f6"), ObjectId("54c34b3d2253270fd4dd5598"), \
# running_ids = [ObjectId("54c5105fd8b487851c2434f7"), ObjectId("54c59c19d8b487851c2434f8")]
running_ids = [ObjectId("54cb0b472253277627a8ac43")]
# running_ids = [ObjectId("54cb259e2253277bca996516")]
em = EventManager()
event_ids_list = []
# 获取做初始聚类的话题
initial_event_ids = em.getInitializingEventIDs()
event_ids_list.extend([(id, True) for id in initial_event_ids if id in running_ids])
# 获取已做完初始聚类的活跃话题
active_event_ids = em.checkActive()
event_ids_list.extend([(id, False) for id in active_event_ids if id in running_ids])
# map并行计算
pool = Pool()
pool.map(one_topic_calculation, event_ids_list)
pool.close()
pool.join()
