如何批量处理评论信息情感分析,并且在时间轴上可视化呈现?

    1. import pandas as pd
    2. from snownlp import SnowNLP
    3. def get_sentiment_cn(text):
    4. s = SnowNLP(text)
    5. return s.sentiments
    6. df = pd.read_excel("../dataset/restaurant-comments.xlsx")
    7. #from dateutil import parser
    8. #df["date"] = df.date.apply(parser.parse)
    9. df["sentiment"] = df.comments.apply(get_sentiment_cn)
    10. %pylab inline
    11. from ggplot import *
    12. ggplot(aes(x="date", y="sentiment"), data=df) + geom_point() \
    13. + geom_line(color = 'blue') + scale_x_date(labels = date_format("%Y-%m-%d"))

    运行结果如下:

    舆情时间序列可视化 - 图1

    修改文件:/usr/local/lib/python3.5/dist-packages/ggplot/stats/smoothers.py

    把 pandas.lib 改为 pandas,如下所示:

    1. from pandas.lib import Timestamp -> from pandas import Timestamp