def run(self):
ltp = Ltp.get_object2()
ltp.load_dict(ALL_DICT_PATH)
analyzer = EmotionAnalysis(ltp)
topic_collection = MongoDB.get_client()[MONGO_DB]['topic']
comment_collection = MongoDB.get_client()[MONGO_DB]['comment']
topic = topic_collection.find_one({'_id': ObjectId(self.id)})
count1 = 0
for weibo_id in topic['text_id_list']:
if MONGO_DB == 'weibo':
comments = comment_collection.find({'id': weibo_id})
else:
data = MongoDB.get_client()[MONGO_DB]['mid'].find_one(
{'id': weibo_id})
if not data:
continue
comments = comment_collection.find({'mid': data['mid']})
for data in comments:
if 'score' in data and data['score']:
continue
content = data['content'].strip()
if not content:
continue
data['score'] = analyzer.sent_sentiment_score(
data['content'].strip())
comment_collection.update_one({'_id': data['_id']},
{'$set': data}, True)
count1 += 1
self.count.emit(round((count1 / topic['text_num']) * 100))
self.stop.emit(True)
def __init__(self, mainwindow):
super().__init__()
client = MongoDB.get_client()
db = client[MONGO_DB]
self.collection = db['topic']
self.weibo_collection = db['weibo']
self.setupUi(mainwindow)
self.id = None
def create_emotion_pie(self):
"""
绘制情感倾向饼图
:return:
"""
figure = plt.figure(figsize=(6, 4), dpi=80, frameon=True)
data = [0, 0, 0]
topic = self.topic_collection.find_one({'_id': ObjectId(self.id)})
# if 'score' not in topic or not topic['score']:
for weibo_id in topic['text_id_list']:
if MONGO_DB == 'weibo':
comments = self.comment_collection.find({'id': weibo_id})
else:
mid = MongoDB.get_client()[MONGO_DB]['mid'].find_one(
{'id': weibo_id})
if not mid:
continue
comments = self.comment_collection.find({'mid': mid['mid']})
for comment in comments:
if not comment['content'].strip():
continue
if 'score' not in comment or not comment['score']:
continue
score = comment['score']
if score[0] - score[1] > 2:
data[0] += 1
elif score[0] - score[1] < 0:
data[1] += 1
else:
data[2] += 1
topic['score'] = data
self.topic_collection.update_one({'_id': topic['_id']},
{'$set': topic}, True)
# else:
# data = topic['score']
try:
data[0] += data[2] * 0.3 * data[0] / (data[0] + data[1])
data[1] += data[2] * 0.3 * data[1] / (data[0] + data[1])
data[2] *= 0.7
except:
pass
labels = ['积极', '消极', '其它']
colors = ['r', 'b', 'y']
fig1 = plt.subplot(1, 1, 1)
plt.xlim(0, 4)
plt.ylim(0, 4)
fig1.pie(x=data, labels=labels, colors=colors, autopct='%.1f%%')
fig1.set_title('话题舆情倾向度')
plt.xticks(())
plt.yticks(())
return figure
def __init__(self, mainwindow):
super().__init__()
client = MongoDB.get_client()
db = client[MONGO_DB]
self.collection = db['topic']
self.weibo_collection = db['weibo']
self.ltp = Ltp.get_object()
self.area = ''
self.keys = []
self.setupUi(mainwindow)
def __init__(self, parent=None):
super().__init__(parent)
self.parent = parent
db = MongoDB.get_client()[MONGO_DB]
self.topic_collection = db['topic']
self.weibo_collection = db['weibo']
self.attention = False
self.emotion = False
self._time = False
self.ltp = Ltp.get_object()
self.setupUi()
def __init__(self, id, parent=None):
super().__init__(parent)
self.parent = parent
self.ltp = Ltp.get_object()
client = MongoDB.get_client()
db = client[MONGO_DB]
self.topic_collection = db['topic']
self.weibo_collection = db['weibo']
self.comment_collection = db['comment']
self.id = id
self.setupUi()
def __init__(self, parent, id):
super().__init__(parent)
self.id = id
client = MongoDB.get_client()
db = client[MONGO_DB]
self.topic_collection = db['topic']
self.weibo_collection = db['weibo']
self.comment_collection = db['comment']
self.horizontalLayout = QtWidgets.QHBoxLayout(self)
self.create_figure(self.create_heatline())
self.create_figure(self.create_emotion_pie())
plt.rcParams['font.sans-serif'] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
def __init__(self, parent=None):
"""
初始化
:param parent: 调用浏览器引擎的父窗口
"""
super().__init__(parent)
self.superwindow = parent
self.setupUi()
self.client = MongoDB.get_client()
self.db = MongoDB.get_client()[MONGO_DB]
self.weibo = self.db['weibo']
self.topic = self.db['topic']
self.comment = self.db['comment']
self.user = self.db['user']
self.repost = self.db['repost']
self.flag = None
self.maparea = None
self.maphtml = None
self.barhtml = None
self.wordcloudhtml = None
self.graphtml = None
self.geohtml = None
self.id = None
def run(self):
ltp = Ltp.get_object()
tdt = Tdt.get_object()
model = Text2Vec.get_object()
weibo_collection = MongoDB.get_client()[MONGO_DB]['weibo']
count1 = 0
weibo_set = weibo_collection.find().sort('posted_at',
pymongo.ASCENDING)
for weibo in weibo_set:
tdt.single_pass(weibo, 'topic', ltp, model)
weibo_collection.update_one({'_id': weibo['_id']},
{'$set': weibo}, True)
count1 += 1
self.count.emit(count1)
self.stop.emit(True)
import sys
from emotion import EmotionAnalysis
sys.path.append('E:\Python\workspace\TDTSystem')
from ltp.ltp import Ltp
from setting import *
from mongo import MongoDB
if __name__ == '__main__':
ltp = Ltp(4)
ltp.load_dict(ALL_DICT_PATH)
analyzer = EmotionAnalysis(ltp)
comment = MongoDB.get_client()['weibo']['comment']
count = 0
for data in comment.find():
count += 1
print(count)
if 'score' in data and data['score']:
continue
content = data['content'].strip()
if not content:
continue
data['score'] = analyzer.sent_sentiment_score(data['content'].strip())
comment.update_one({'_id': data['_id']}, {'$set': data}, True)
def single_pass(self, weibo, topic_table, ltp=None, text2vec=None):
"""
Single-Pass聚类算法，微博weibo属于话题集topic_set某话题，则加入话题并更新话题，否则，自成一个话题加入话题库
:param ltp: Ltp类实例
:param text2vec: Text2Vec类实例
:param topic_table: str, mongoDB话题库名
:param weibo:dict, 微博数据
:return:
"""
if 'if_topic' in weibo and weibo['if_topic']:
return
if not ltp:
ltp = Ltp.get_object()
if not text2vec:
model = Text2Vec.get_object()
else:
model = text2vec
content = weibo['content']
parser = ltp.text_parser(content)
vector = model.text2dict(list(parser[0:3])) # 微博切分: [标题, 正文, hashtag]
entity = parser[3] # 命名实体
topic_collection = MongoDB.get_client()[MONGO_DB][topic_table]
topic_set = topic_collection.find()
similiratiy = [] # 存储微博与所有话题的相似度
for topic in topic_set:
# if cls > 0 and cls != topic['cls'] :
# continue
keydict = topic['keywords']
vector2 = {}
count = 0
for key, value in keydict.items():
if len(vector2) > len(vector):
break
vector2[key] = value
count += value
similar_score = model.similarity(vector2, vector) # 计算相似度
if similar_score < 0.4: # 相似度低，微博不属于话题，判断是否将话题淘汰
time_gip = (self.get_timestamp(weibo['posted_at']) -
self.get_timestamp(topic['latest_time'])) / 86400
if topic['text_num'] < 5 and time_gip > 60: # 话题微博数小于5且两个月得不到更新，淘汰
topic_collection.delete_one({'_id': topic['_id']})
else:
similiratiy.append(similar_score)
else:
similiratiy.append(similar_score)
try:
score = max(similiratiy)
except:
score = 0.0
if score >= 0.5: # 微博加入话题，更新话题
index = similiratiy.index(score)
topic = topic_collection.find_one(skip=index)
keywords = topic['keywords']
text_num = topic['text_num']
topic['text_id_list'].append(weibo['id'])
topic['text_list'].append(weibo['content'])
ltp.netag_dict_merge(topic['entity'], entity)
self.dict_combine(keywords, vector, text_num)
topic['keywords'] = dict(
sorted(keywords.items(),
key=lambda item: item[1],
reverse=True))
topic['heat'] += weibo['comment_count'] + sqrt(
weibo['forward_count'] + weibo['like_count'])
topic['text_num'] += 1
if weibo['posted_at'] < topic['start_time']:
topic['start_time'] = weibo['posted_at']
elif weibo['posted_at'] > topic['latest_time']:
topic['latest_time'] = weibo['posted_at']
topic['central_time'] = self.datetime_update(
topic['central_time'], weibo['posted_at'], text_num)
topic_collection.update_one({'_id': topic['_id']}, {'$set': topic},
True)
else: # 微博自成一新话题
one_topic = {
'entity': {},
'keywords': {},
'text_id_list': [],
'text_list': [],
'text_num': 1,
'heat': 0,
'start_time': None,
'latest_time': None,
'central_time': None,
# 'cls': cls
}
one_topic['text_id_list'].append(weibo['id'])
one_topic['text_list'].append(weibo['content'])
one_topic['entity'] = entity
one_topic['heat'] = weibo['comment_count'] + sqrt(
weibo['forward_count'] + weibo['like_count'])
one_topic['start_time'] = one_topic['latest_time'] = one_topic[
'central_time'] = weibo['posted_at']
one_topic['keywords'] = dict(
sorted(vector.items(), key=lambda item: item[1], reverse=True))
topic_collection.insert_one(one_topic)
weibo['if_topic'] = True
def __init__(self, parent=None):
super().__init__(parent)
self.db = MongoDB.get_client()[MONGO_DB]
self.parent = parent
self.setupUi()
