def test():
s = Sentiment()
r = Region(
"/Users/aaronhe/Documents/NutStore/Aaron He/FDU/Big-Data-Communication/Stereotype-Analysis-in-NetEase-News-Comments/Dict/region_dict/region.txt"
)
# 构造输入数据
text = [
["潮汕人很帅，湖北人挺会做生意的！", "上海"],
["老铁牛逼！", "重庆"],
["我觉得很好吃啊", "北京"],
]
df = pd.DataFrame(text, columns=["text", "src"])
print(df.head())
df = r.region_detect(df, on=["text"])
# dataFrame中批量添加region字段
print(
s.sentiment_detect(df,
on=["text"],
srcs=["src"],
dists=["region_1", "region_2", "region_3"]))
print(s.output_record(src="北京"))
def main():
# 数据加载
date = sys.argv[1]
path_prefix = "./new_data"
df = pd.read_pickle(
os.path.join(path_prefix, "%s_select_comments.p" % date))
# 模型加载
s = Sentiment()
df = s.sentiment_detect(df,
on=["content"],
srcs=["province"],
dists=["region_1", "region_2", "region_3"])
df_freq = s.table_record()
# 结果保存
df.to_pickle(os.path.join(path_prefix, "%s_sentiment.p" % date))
df_freq.to_pickle(os.path.join(path_prefix, "%s_senti_freq.p" % date))
print(df)
print(df_freq)
