def load_subject_weibo_data():
"""加载客观微博数据
"""
# topicname = u'外滩踩踏-微博'
# topicname = u'呼格案-微博'
# topicname = u'复旦投毒案-微博'
topicname = u'APEC-微博'
em = EventManager()
topicid = em.getEventIDByName(topicname)
event = Event(topicid)
# f = open('caitai.jl')
# f = open('huge.jl')
# f = open('fudan.jl')
f = open('apec.jl')
for line in f:
item = json.loads(line.strip())
item['text'] = item['text'].encode('utf-8')
item = subob_classifier(item)
if not item['subject']:
news = subject_weibo2news(item)
event.saveItem(news)
f.close()
def load_subject_weibo_data():
"""加载客观微博数据
"""
# topicname = u'外滩踩踏-微博'
# topicname = u'呼格案-微博'
# topicname = u'复旦投毒案-微博'
topicname = u'APEC-微博'
em = EventManager()
topicid = em.getEventIDByName(topicname)
event = Event(topicid)
# f = open('caitai.jl')
# f = open('huge.jl')
# f = open('fudan.jl')
f = open('apec.jl')
for line in f:
item = json.loads(line.strip())
item['text'] = item['text'].encode('utf-8')
item = subob_classifier(item)
if not item['subject']:
news = subject_weibo2news(item)
event.saveItem(news)
f.close()
def eventriver():
"""event river数据
"""
topic_name = request.args.get('query', default_topic) # 话题名
sort = request.args.get('sort',
'tfidf') # weight, addweight, created_at, tfidf
end_ts = request.args.get('ts', None)
during = request.args.get('during', None)
if end_ts:
end_ts = int(end_ts)
if during:
during = int(during)
start_ts = end_ts - during
topicid = em.getEventIDByName(topic_name)
event = Event(topicid)
subeventlist, dates, total_weight = event.getEventRiverData(start_ts,
end_ts,
sort=sort)
return json.dumps({
"dates": dates,
"name": topic_name,
"type": "eventRiver",
"weight": total_weight,
"eventList": subeventlist
})
def one_topic_clear(topicname_start):
topicname, start_datetime = topicname_start
em = EventManager()
topicid = em.getEventIDByName(topicname)
start_ts = datetime2ts(start_datetime)
event = Event(topicid)
event.initialize(start_ts)
def one_topic_clear(topicname_start):
topicname, start_datetime = topicname_start
em = EventManager()
topicid = em.getEventIDByName(topicname)
start_ts = datetime2ts(start_datetime)
event = Event(topicid)
event.initialize(start_ts)
def initializeNewsTopic():
"""初始化新闻话题
"""
em = EventManager()
topicname = u'外滩踩踏'
start_datetime = "2015-01-02 00:00:00"
topicid = em.getEventIDByName(topicname)
start_ts = datetime2ts(start_datetime)
event = Event(topicid)
event.initialize(start_ts)
def initializeNewsTopic():
"""初始化新闻话题
"""
em = EventManager()
topicname = u'外滩踩踏'
start_datetime = "2015-01-02 00:00:00"
topicid = em.getEventIDByName(topicname)
start_ts = datetime2ts(start_datetime)
event = Event(topicid)
event.initialize(start_ts)
def createEvent(name,begin,end,location,description,leader,img): size=6 chars=string.ascii_uppercase + string.digits unHashed = ''.join(random.choice(chars) for _ in range(size)) qr_code = pbkdf2_sha256.hash(unHashed) if(name == '' or begin == '' or end == '' or location == '' or description == '' or leader== '' or img==''): return 400 event = Event( name=name, begin=begin, end=end, location=location, desc=description, leader=leader, cancel=0, img=img, qr_code=qr_code, created= datetime.datetime.now(), link= None ) return Persister.persist_object(event)
def __make_database():
engine = create_engine(f'sqlite:///{DATABASE_NAME}', echo=False)
metadata = MetaData()
users_table = Table(USER_TABLE_NAME, metadata,
*User.get_all_columns_with_attributes())
events_table = Table(EVENT_TABLE_NAME, metadata,
*Event.get_all_columns_with_attributes())
metadata.create_all(engine)
__fill_database()
def handle_error(eventid):
"""
"""
event = Event(eventid)
last_modify = event.getLastmodify()
event.setLastmodify(last_modify - 3600)
event.setModifysuccess(True)
def initializeWeiboTopic():
"""初始化weibo话题
"""
em = EventManager()
# topicname = u'外滩踩踏-微博'
# start_datetime = "2015-01-02 00:00:00"
# topicname = u'呼格案-微博'
# start_datetime = "2014-12-14 00:00:00"
# topicname = u'复旦投毒案-微博'
# start_datetime = "2014-12-15 00:00:00"
topicname = u'APEC-微博'
start_datetime = "2014-12-15 00:00:00"
topicid = em.getEventIDByName(topicname)
start_ts = datetime2ts(start_datetime)
event = Event(topicid)
event.initialize(start_ts)
def initializeWeiboTopic():
"""初始化weibo话题
"""
em = EventManager()
# topicname = u'外滩踩踏-微博'
# start_datetime = "2015-01-02 00:00:00"
# topicname = u'呼格案-微博'
# start_datetime = "2014-12-14 00:00:00"
# topicname = u'复旦投毒案-微博'
# start_datetime = "2014-12-15 00:00:00"
topicname = u'APEC-微博'
start_datetime = "2014-12-15 00:00:00"
topicid = em.getEventIDByName(topicname)
start_ts = datetime2ts(start_datetime)
event = Event(topicid)
event.initialize(start_ts)
def addEvent(self, title, description, project, beginDate, endDate):
if persister.checkProjectExists(project):
currentDate = datetime.datetime.now()
eventObject = Event(title=title,
description=description,
project=project,
beginDate=beginDate,
endDate=endDate,
createdAt=currentDate)
return persister.storeObject(eventObject)
return False
def one_topic_merge(eventid_initializing):
"""合并簇
input:
eventid_initializing: (eventid, initializing)
eventid: 话题ID
initializing： 是否做初始聚类
"""
eventid, initializing = eventid_initializing
# 根据话题ID初始化话题实例
event = Event(eventid)
timestamp = event.getLastmodify() + 3600 # 当前的时间戳，int, 默认为最后修改日期+3600
now_hour = int(time.strftime('%H', time.localtime(timestamp)))
subevents = event.getSubEvents()
subevent_fwords = dict()
for subevent in subevents:
subeventid = subevent["_id"]
feature = Feature(subeventid)
# 获取每个子事件最新的特征词
fwords = feature.get_newest()
subevent_fwords[subeventid] = fwords
subeventids_sort_timestamp = event.get_sorted_subeventids()
cids, mids = merge_subevents(subevent_fwords,
subeventids_sort_timestamp,
top_tfidf_para=10,
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])
def one_topic_merge(eventid_initializing):
"""合并簇
input:
eventid_initializing: (eventid, initializing)
eventid: 话题ID
initializing： 是否做初始聚类
"""
eventid, initializing = eventid_initializing
# 根据话题ID初始化话题实例
event = Event(eventid)
timestamp = event.getLastmodify() + 3600 # 当前的时间戳，int, 默认为最后修改日期+3600
now_hour = int(time.strftime('%H', time.localtime(timestamp)))
subevents = event.getSubEvents()
subevent_fwords = dict()
for subevent in subevents:
subeventid = subevent["_id"]
feature = Feature(subeventid)
# 获取每个子事件最新的特征词
fwords = feature.get_newest()
subevent_fwords[subeventid] = fwords
subeventids_sort_timestamp = event.get_sorted_subeventids()
cids, mids = merge_subevents(subevent_fwords, subeventids_sort_timestamp, top_tfidf_para=10, 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])
def one_topic_calculation(eventid_initializing):
"""多步计算
input:
eventid_initializing: (eventid, initializing)
eventid: 话题ID
initializing： 是否做初始聚类
"""
eventid, initializing = eventid_initializing
# 根据话题ID初始化话题实例
event = Event(eventid)
timestamp = event.getLastmodify() + 3600 # 当前的时间戳，int, 默认为最后修改日期+3600
now_hour = int(time.strftime('%H', time.localtime(timestamp)))
def step1_cal():
"""第一步计算，获取子事件特征词，新文本与特征词匹配分类
"""
print '[%s] ' % ts2datetime(int(time.time())), 'event ', eventid, ' %s start step1' % ts2datetime(timestamp)
if initializing:
# 若话题需要做初始聚类，获取话题开始时间之前的文本
results = event.getInitialInfos()
else:
# 若话题已做完初始聚类，获取话题最新一小时的文本
results = event.getInfos(timestamp - 3600, timestamp)
if now_hour == 0:
# 如果不是在做初始化，24时的时候, 一定把当天（大于或等于0时小于24时）产生的簇（非其他簇）下的文本重新做一下匹配, 同时删除这些簇
temp_subeventids = event.getTodayCreatSubeventIds()
temp_infos = event.getTodayCreatSubeventInfos()
event.remove_subevents(temp_subeventids)
results.extend(temp_infos)
print eventid, ' before classify: ', len(results)
# 获取子事件
subevents = event.getSubEvents()
labels_list = []
feature_words_list = []
for subevent in subevents:
subeventid = subevent["_id"]
feature = Feature(subeventid)
# 获取每个子事件最新的特征词
fwords = feature.get_newest()
feature_words_list.append(fwords)
labels_list.append(subeventid)
for r in results:
text = (r['title'] + r['content168']).encode('utf-8')
feature_words_inputs = []
for fwords in feature_words_list:
wcdict = dict()
for w, c in fwords.iteritems():
if isinstance(w, unicode):
w = w.encode('utf-8')
wcdict[w] = c
feature_words_inputs.append(wcdict)
# 单条文本与各子事件的特征词进行匹配，得到每条文本的簇标签
label = subevent_classifier(text, labels_list, feature_words_inputs)
if label == "other":
label = event.getOtherSubEventID()
news = News(r["_id"], event.id)
news.update_news_subeventid(label)
print '[%s] ' % ts2datetime(int(time.time())), 'event ', eventid, ' %s end step1' % ts2datetime(timestamp)
def step2_cal():
"""第二步计算，判断其他类是否需要分裂，若需要，则对其他类进行文本聚类，并做聚类评价
"""
# 聚类评价时选取TOPK_FREQ_WORD的高频词
TOPK_FREQ_WORD = 50
# 聚类评价时最小簇的大小
LEAST_SIZE = 8
# 判断其他类是否需要分裂
ifsplit = event.check_ifsplit(initializing)
print '[%s] ' % ts2datetime(int(time.time())), 'event ', eventid, ' split ', ifsplit, ' %s start step2' % ts2datetime(timestamp)
if ifsplit:
inputs, kmeans_cluster_num, reserve_num = event.getOtherSubEventInfos(initializing)
print eventid, ' after classify before split: ', len(inputs), kmeans_cluster_num, reserve_num
if len(inputs) > 2:
items = []
for r in inputs:
r["title"] = r["title"].encode("utf-8")
r["content"] = r["content168"].encode("utf-8")
items.append(r)
# kmeans聚类
kmeans_results = kmeans(items, k=kmeans_cluster_num)
# 聚类评价
if initializing or now_hour == 0:
min_tfidf = event.get_min_tfidf()
final_cluster_results, tfidf_dict = cluster_evaluation(kmeans_results, top_num=reserve_num, topk_freq=TOPK_FREQ_WORD, least_size=LEAST_SIZE, min_tfidf=min_tfidf)
else:
# 每小时聚类时，不用和已有簇的最小tfidf作比
final_cluster_results, tfidf_dict = cluster_evaluation(kmeans_results, top_num=reserve_num, topk_freq=TOPK_FREQ_WORD, least_size=LEAST_SIZE)
# 更新新闻簇标签，更新子事件表
for label, items in final_cluster_results.iteritems():
if label == "other":
label = event.getOtherSubEventID()
event.save_subevent(label, timestamp)
if label != event.getOtherSubEventID():
# 更新每类的tfidf
event.update_subevent_tfidf(label, tfidf_dict[label])
for r in items:
news = News(r["_id"], event.id)
news.update_news_subeventid(label)
else:
print 'inputs less than 2, kmeans aborted'
print '[%s] ' % ts2datetime(int(time.time())), 'event ', eventid, ' %s end step2' % ts2datetime(timestamp)
def step3_cal():
"""计算各簇的特征词、代表文本、去重, 更新簇的大小、增幅信息
"""
print '[%s] ' % ts2datetime(int(time.time())), 'event ', eventid, ' %s start step3' % ts2datetime(timestamp)
inputs = []
subevents = event.getSubEvents()
for subevent in subevents:
subeventid = subevent["_id"]
inputs.extend(event.getSubeventInfos(subeventid))
for r in inputs:
r["title"] = r["title"].encode("utf-8")
r["content"] = r["content168"].encode("utf-8")
r["label"] = r["subeventid"]
# 计算各簇的存量特征词
cluster_feature = extract_feature(inputs)
for label, fwords in cluster_feature.iteritems():
feature = Feature(label)
feature.upsert_newest(fwords)
# 计算文本权重
for r in inputs:
weight = text_weight_cal(r, cluster_feature[r['label']])
news = News(r["_id"], event.id)
news.update_news_weight(weight)
# 文本去重
items_dict = {}
for r in inputs:
try:
items_dict[r["label"]].append(r)
except KeyError:
items_dict[r["label"]] = [r]
for label, items in items_dict.iteritems():
results = duplicate(items)
for r in results:
news = News(r["_id"], event.id)
news.update_news_duplicate(r["duplicate"], r["same_from"])
# 更新簇的大小、增幅信息
before_size = event.get_subevent_size(label)
event.update_subevent_size(label, len(items))
event.update_subevent_addsize(label, len(items) - before_size)
if initializing:
# 更新事件状态由initializing变为active
event.activate()
print '[%s] ' % ts2datetime(int(time.time())), 'event ', eventid, ' %s end step3' % ts2datetime(timestamp)
def step4_cal():
""" 24 点时merge已有的簇
"""
if not initializing and now_hour == 0:
print '[%s] ' % ts2datetime(int(time.time())), 'event ', eventid, ' %s start step4' % ts2datetime(timestamp)
subevents = event.getSubEvents()
subevent_fwords = dict()
for subevent in subevents:
subeventid = subevent["_id"]
feature = Feature(subeventid)
# 获取每个子事件最新的特征词
fwords = feature.get_newest()
subevent_fwords[subeventid] = fwords
subeventids_sort_timestamp = event.get_sorted_subeventids()
cids, mids = merge_subevents(subevent_fwords, subeventids_sort_timestamp, top_tfidf_para=10, 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
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])
# 重新计算各簇的特征词, 并计算文本权重, 并去重
if len(mids):
step3_cal()
print '[%s] ' % ts2datetime(int(time.time())), 'event ', eventid, ' %s end step3' % ts2datetime(timestamp)
# 首先检测该事件最近一次修改是否成功
success = event.checkLastModify()
if success:
"""
step1_cal()
step2_cal()
step3_cal()
step4_cal()
"""
try:
# 进行多步计算
step1_cal()
step2_cal()
step3_cal()
step4_cal()
event.setLastmodify(timestamp) # 更新事件的last_modify
event.setModifysuccess(True) # 更新事件的modify_success为True
except Exception, e:
# 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)
def one_topic_calculation(eventid_initializing):
"""多步计算
input:
eventid_initializing: (eventid, initializing)
eventid: 话题ID
initializing： 是否做初始聚类
"""
eventid, initializing = eventid_initializing
# 根据话题ID初始化话题实例
event = Event(eventid)
timestamp = event.getLastmodify() + 3600 # 当前的时间戳，int, 默认为最后修改日期+3600
now_hour = int(time.strftime('%H', time.localtime(timestamp)))
def step1_cal():
"""第一步计算，获取子事件特征词，新文本与特征词匹配分类
"""
print '[%s] ' % ts2datetime(int(time.time(
))), 'event ', eventid, ' %s start step1' % ts2datetime(timestamp)
if initializing:
# 若话题需要做初始聚类，获取话题开始时间之前的文本
results = event.getInitialInfos()
else:
# 若话题已做完初始聚类，获取话题最新一小时的文本
results = event.getInfos(timestamp - 3600, timestamp)
if now_hour == 0:
# 如果不是在做初始化，24时的时候, 一定把当天（大于或等于0时小于24时）产生的簇（非其他簇）下的文本重新做一下匹配, 同时删除这些簇
temp_subeventids = event.getTodayCreatSubeventIds()
temp_infos = event.getTodayCreatSubeventInfos()
event.remove_subevents(temp_subeventids)
results.extend(temp_infos)
print eventid, ' before classify: ', len(results)
# 获取子事件
subevents = event.getSubEvents()
labels_list = []
feature_words_list = []
for subevent in subevents:
subeventid = subevent["_id"]
feature = Feature(subeventid)
# 获取每个子事件最新的特征词
fwords = feature.get_newest()
feature_words_list.append(fwords)
labels_list.append(subeventid)
for r in results:
text = (r['title'] + r['content168']).encode('utf-8')
feature_words_inputs = []
for fwords in feature_words_list:
wcdict = dict()
for w, c in fwords.iteritems():
if isinstance(w, unicode):
w = w.encode('utf-8')
wcdict[w] = c
feature_words_inputs.append(wcdict)
# 单条文本与各子事件的特征词进行匹配，得到每条文本的簇标签
label = subevent_classifier(text, labels_list,
feature_words_inputs)
if label == "other":
label = event.getOtherSubEventID()
news = News(r["_id"], event.id)
news.update_news_subeventid(label)
print '[%s] ' % ts2datetime(int(time.time(
))), 'event ', eventid, ' %s end step1' % ts2datetime(timestamp)
def step2_cal():
"""第二步计算，判断其他类是否需要分裂，若需要，则对其他类进行文本聚类，并做聚类评价
"""
# 聚类评价时选取TOPK_FREQ_WORD的高频词
TOPK_FREQ_WORD = 50
# 聚类评价时最小簇的大小
LEAST_SIZE = 8
# 判断其他类是否需要分裂
ifsplit = event.check_ifsplit(initializing)
print '[%s] ' % ts2datetime(
int(time.time())
), 'event ', eventid, ' split ', ifsplit, ' %s start step2' % ts2datetime(
timestamp)
if ifsplit:
inputs, kmeans_cluster_num, reserve_num = event.getOtherSubEventInfos(
initializing)
print eventid, ' after classify before split: ', len(
inputs), kmeans_cluster_num, reserve_num
if len(inputs) > 2:
items = []
for r in inputs:
r["title"] = r["title"].encode("utf-8")
r["content"] = r["content168"].encode("utf-8")
items.append(r)
# kmeans聚类
kmeans_results = kmeans(items, k=kmeans_cluster_num)
# 聚类评价
if initializing or now_hour == 0:
min_tfidf = event.get_min_tfidf()
final_cluster_results, tfidf_dict = cluster_evaluation(
kmeans_results,
top_num=reserve_num,
topk_freq=TOPK_FREQ_WORD,
least_size=LEAST_SIZE,
min_tfidf=min_tfidf)
else:
# 每小时聚类时，不用和已有簇的最小tfidf作比
final_cluster_results, tfidf_dict = cluster_evaluation(
kmeans_results,
top_num=reserve_num,
topk_freq=TOPK_FREQ_WORD,
least_size=LEAST_SIZE)
# 更新新闻簇标签，更新子事件表
for label, items in final_cluster_results.iteritems():
if label == "other":
label = event.getOtherSubEventID()
event.save_subevent(label, timestamp)
if label != event.getOtherSubEventID():
# 更新每类的tfidf
event.update_subevent_tfidf(label, tfidf_dict[label])
for r in items:
news = News(r["_id"], event.id)
news.update_news_subeventid(label)
else:
print 'inputs less than 2, kmeans aborted'
print '[%s] ' % ts2datetime(int(time.time(
))), 'event ', eventid, ' %s end step2' % ts2datetime(timestamp)
def step3_cal():
"""计算各簇的特征词、代表文本、去重, 更新簇的大小、增幅信息
"""
print '[%s] ' % ts2datetime(int(time.time(
))), 'event ', eventid, ' %s start step3' % ts2datetime(timestamp)
inputs = []
subevents = event.getSubEvents()
for subevent in subevents:
subeventid = subevent["_id"]
inputs.extend(event.getSubeventInfos(subeventid))
for r in inputs:
r["title"] = r["title"].encode("utf-8")
r["content"] = r["content168"].encode("utf-8")
r["label"] = r["subeventid"]
# 计算各簇的存量特征词
cluster_feature = extract_feature(inputs)
for label, fwords in cluster_feature.iteritems():
feature = Feature(label)
feature.upsert_newest(fwords)
# 计算文本权重
for r in inputs:
weight = text_weight_cal(r, cluster_feature[r['label']])
news = News(r["_id"], event.id)
news.update_news_weight(weight)
# 文本去重
items_dict = {}
for r in inputs:
try:
items_dict[r["label"]].append(r)
except KeyError:
items_dict[r["label"]] = [r]
for label, items in items_dict.iteritems():
results = duplicate(items)
for r in results:
news = News(r["_id"], event.id)
news.update_news_duplicate(r["duplicate"], r["same_from"])
# 更新簇的大小、增幅信息
before_size = event.get_subevent_size(label)
event.update_subevent_size(label, len(items))
event.update_subevent_addsize(label, len(items) - before_size)
if initializing:
# 更新事件状态由initializing变为active
event.activate()
print '[%s] ' % ts2datetime(int(time.time(
))), 'event ', eventid, ' %s end step3' % ts2datetime(timestamp)
def step4_cal():
""" 24 点时merge已有的簇
"""
if not initializing and now_hour == 0:
print '[%s] ' % ts2datetime(int(time.time(
))), 'event ', eventid, ' %s start step4' % ts2datetime(timestamp)
subevents = event.getSubEvents()
subevent_fwords = dict()
for subevent in subevents:
subeventid = subevent["_id"]
feature = Feature(subeventid)
# 获取每个子事件最新的特征词
fwords = feature.get_newest()
subevent_fwords[subeventid] = fwords
subeventids_sort_timestamp = event.get_sorted_subeventids()
cids, mids = merge_subevents(subevent_fwords,
subeventids_sort_timestamp,
top_tfidf_para=10,
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
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])
# 重新计算各簇的特征词, 并计算文本权重, 并去重
if len(mids):
step3_cal()
print '[%s] ' % ts2datetime(int(time.time(
))), 'event ', eventid, ' %s end step3' % ts2datetime(timestamp)
# 首先检测该事件最近一次修改是否成功
success = event.checkLastModify()
if success:
"""
step1_cal()
step2_cal()
step3_cal()
step4_cal()
"""
try:
# 进行多步计算
step1_cal()
step2_cal()
step3_cal()
step4_cal()
event.setLastmodify(timestamp) # 更新事件的last_modify
event.setModifysuccess(True) # 更新事件的modify_success为True
except Exception, e:
# 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)
def test_subevent_classifier():
labels_list = []
feature_words_inputs = []
subevents = event.getSubEvents()
for subevent in subevents:
subeventid = subevent["_id"]
if subeventid != "575612b6-a26f-4df9-a2de-01c85cae56a2":
labels_list.append(subeventid)
feature = Feature(subeventid)
feature_words = feature.get_newest()
new_feature_words = dict()
for k, v in feature_words.iteritems():
new_feature_words[k.encode('utf-8')] = v
feature_words_inputs.append(new_feature_words)
news_id = "http://news.xinhuanet.com/comments/2014-11/03/c_1113084515.htm"
news = News(news_id, event.id)
ns = news.get_news_info()
text = ns['title'].encode('utf-8') + ns['content168'].encode('utf-8')
label = subevent_classifier(text, labels_list, feature_words_inputs)
print label
if __name__ == '__main__':
from bson.objectid import ObjectId
eventid = ObjectId("54916b0d955230e752f2a94e")
event = Event(eventid)
test_subevent_classifier()
