def process_statics():
file_path_list = topic_sta1.getAllFile(weibofilefolder)
topic_sta1.topic_followers(file_path_list)
def get_result_dic_2():
output_dic = {}
file_path_list = topic_sta1.getAllFile(weibofilefolder)
output_dic = topic_sta1.city_keyword_emotion(file_path_list)
return output_dic
def process_statics():
file_path_list = topic_sta1.getAllFile(weibofilefolder)
topic_sta1.topic_location(file_path_list)
def store_data():
file_path_list = topic_sta1.getAllFile(weibofilefolder)
topic_sta1.collect_city_file(file_path_list)
'好工作','平等,机会','白手起家','成为,富人','个体,自由','安享晚年','收入,足够','个人努力',
'祖国强大','中国经济,持续发展','父辈,更好']
emotion = [-1,0,1,2,3,4]
for current_emotion in emotion:
for current_keyword in keywords_folder_list:
current_folder = output_file_1 + str(current_emotion) + '/' + current_keyword
if (not os.path.exists(current_folder)):
os.makedirs(current_folder)
if __name__ == '__main__':
# 不带情感
# store_data()
# 带时间_情感
# make_dirs()
#
file_path_list = topic_sta1.getAllFile(weibofilefolder)
# for i in file_path_list:
# t = threading.Thread(target=collect_time_emotion_city_file, args=(i,))
# t.start()
pool = multiprocessing.Pool(processes=8)
for i in file_path_list:
pool.apply_async(topic_sta1.multi_collect_time_emotion_city_file_nospam,(i,))
pool.close()
pool.join()
#统计各keyword 和城市的微博语料数
# topic_sta1.calc_city_doc()
def get_data():
file_path_list = topic_sta1.getAllFile(topic_sta1.weibofilefolder)
# 输出结果
topic_sta1.keyword_emotion_time(file_path_list)
def get_result_dic(filefolder):
file_path_list = topic_sta1.getAllFile(filefolder)
result_dic = topic_sta1.keyword_coOccurrence(file_path_list)
print(result_dic)