结巴分词，文本聚类，情感分析，词云图可视化

import re
import numpy
import jieba
import jieba.analyse                        # 提取关键内容
import jieba.posseg as pseg                 # 词性标注
from pymongo import MongoClient
from sklearn.feature_extraction.text import TfidfTransformer, CountVectorizer
from sklearn.cluster import KMeans, MiniBatchKMeans
from sklearn.metrics.pairwise import cosine_similarity
from snownlp import SnowNLP
from scipy.misc import imread
from wordcloud import WordCloud
import matplotlib.pyplot as plt

def load_file():
    '''
        加载外部词典，正则去除所有的标点符号，返回纯文本
    '''
    jieba.load_userdict("G:/anaconda/dict_lzf.txt")       # 加载外部自定义词典
    client = MongoClient('localhost', 27017)  # 链接数据库
    db = client['Taoguba']  # 匹配Taoguba表
    news = db.Taoguba.find()
    # db = client['Eastmoney']  # 匹配eastmoney表
    # news = db.Eastmoney.find()
    all_new = []
    N_new = []
    emo = []
    sum = []
    for i in news:
        new = (i["Content"])
        # new = (i["massage"])
        r = '[’！@#~￥%……&*（） ——+|}{“：”？》《，。、‘；’、】【!"#$%&\'()*+,-./:; <=>?@[\\]^_`{|}~]+'
        news1 = re.sub(r, '', new)
        news