利用500W条微博语料对评论进行情感分析

mysql - u root -p xxx <weibo500w.sql

去重复内容：
    delete from 表名 where id not in (select minid from (select min(id) as minid from 表名 group by 字段) b);
去值为NULL：
    delete from 表名 where 字段名=NULL
去值为""空值
　　delete from 表名 where 字段名=''

import re
from snownlp import sentiment
import numpy as np
import pymysql
from snownlp import SnowNLP
import matplotlib.pyplot as plt
from snownlp import sentiment
from snownlp.sentiment import Sentiment
conn = pymysql.connect(host='数据库IP', user='用户名', password='密码', charset="utf8",use_unicode=False)  # 连接服务器
with conn:
    cur = conn.cursor()
    cur.execute("SELECT * FROM test.weibo WHERE weiboId < '%d'" % 6000000)
    rows = cur.fetchall()
comment = []
for row in rows:
    row = list(row)
    comment.append(row[18])
def train_model(texts):
    for li in texts:
        comm = li.decode('utf-8')
        text = re.sub(r'(?:回复)?(?://)?@[\w\u2E80-\u9FFF]+:?|\[\w+\]', ',',comm)
        socre = SnowNLP(text)
        if socre.sentiments > 0.8:
            with open('pos.txt', mode='a', encoding='utf-8') as g:
                g.writelines(comm +"\n")
        elif socre.sentiments < 0.3:
            with open('neg.txt', mode='a', encoding='utf-8') as f:
                f.writelines(comm + "\n")
        else:
            pass

train_model(comment)
sentiment.train('neg.txt', 'pos.txt')
sentiment.save('sentiment.marshal')

{
    "comments": [
        {
            "created_at": "Wed Jun 01 00:50:25 +0800 2011",
            "id": 12438492184,
            "text": "love your work.......",
            "source": "<a href="http://weibo.com" rel="nofollow">新浪微博</a>",
            "mid": "202110601896455629",
            "user": {
                "id": 1404376560,
                "screen_name": "zaku",
                "name": "zaku",
                "province": "11",
                "city": "5",
                "location": "北京 朝阳区",
                "description": "人生五十年，乃如梦如幻；有生斯有死，壮士复何憾。",
                "url": "http://blog.sina.com.cn/zaku",
                "profile_image_url": "http://tp1.sinaimg.cn/1404376560/50/0/1",
                "domain": "zaku",
                "gender": "m",
                "followers_count": 1204,
                "friends_count": 447,
                "statuses_count": 2908,
                "favourites_count": 0,
                "created_at": "Fri Aug 28 00:00:00 +0800 2009",
                "following": false,
                "allow_all_act_msg": false,
                "remark": "",
                "geo_enabled": true,
                "verified": false,
                "allow_all_comment": true,
                "avatar_large": "http://tp1.sinaimg.cn/1404376560/180/0/1",
                "verified_reason": "",
                "follow_me": false,
                "online_status": 0,
                "bi_followers_count": 215
            },
            }
        },
        ...
    ],
    "previous_cursor": 0,
    "next_cursor": 0,
    "total_number": 7
}

import codecs
import re
import numpy as np
import pymysql
from snownlp import SnowNLP
import matplotlib.pyplot as plt
from snownlp import sentiment
from snownlp.sentiment import Sentiment

comment = []
with open('文件路径', mode='r', encoding='utf-8') as f:
    rows = f.readlines()
    for row in rows:
        if row not in comment:
            comment.append(row.strip('\n'))
def snowanalysis(self):
    sentimentslist = []
    for li in self:
        #text = re.sub(r'(?:回复)?(?://)?@[\w\u2E80-\u9FFF]+:?|\[\w+\]', ',',li)
        print(li)
        s = SnowNLP(li)
        print(s.sentiments)
        sentimentslist.append(s.sentiments)
    plt.hist(sentimentslist, bins=np.arange(0, 1, 0.01))
    plt.show()
snowanalysis(comment)

import pickle
from os import path
import jieba
import matplotlib.pyplot as plt
from wordcloud import WordCloud, STOPWORDS, ImageColorGenerator
def make_worldcloud(file_path):
    text_from_file_with_apath = open(file_path,'r',encoding='UTF-8').read()
    wordlist_after_jieba = jieba.cut(text_from_file_with_apath, cut_all=False)
    wl_space_split = " ".join(wordlist_after_jieba)
    print(wl_space_split)
    backgroud_Image = plt.imread('图片路径')
    print('加载图片成功！')
    '''设置词云样式'''
    stopwords = STOPWORDS.copy()
    stopwords.add("哈哈") #可以加多个屏蔽词
    wc = WordCloud(
        width=1024,
        height=768,
        background_color='white',# 设置背景颜色
        mask=backgroud_Image,# 设置背景图片
        font_path='E:\simsun.ttf',  # 设置中文字体，若是有中文的话，这句代码必须添加，不然会出现方框，不出现汉字
        max_words=600, # 设置最大现实的字数
        stopwords=stopwords,# 设置停用词
        max_font_size=400,# 设置字体最大值
        random_state=50,# 设置有多少种随机生成状态，即有多少种配色方案
    )
    wc.generate_from_text(wl_space_split)#开始加载文本
    img_colors = ImageColorGenerator(backgroud_Image)
    wc.recolor(color_func=img_colors)#字体颜色为背景图片的颜色
    plt.imshow(wc)# 显示词云图
    plt.axis('off')# 是否显示x轴、y轴下标
    plt.show()#显示
    # 获得模块所在的路径的
    d = path.dirname(__file__)
    # os.path.join()：  将多个路径组合后返回
    wc.to_file(path.join(d, "h11.jpg"))
    print('生成词云成功!')

make_worldcloud('文本路径')