利用jieba进行分词，词云图展示

import jieba
from scipy.misc import imread
from wordcloud import WordCloud,STOPWORDS,ImageColorGenerator
import matplotlib.pyplot as plt
import pandas as pd

def get_word():
    df = pd.read_csv('weixiaobao_data/wen.txt', sep='\t')
    word_list = df['MsgTitle'].tolist()
    return word_list


def get_word_list(mylist):
    word_list = [' '.join(jieba.cut(sen)) for sen in mylist]
    new_text = ' '.join(word_list)
    pic_path = 'buity.jpg'
    im_mask = imread(pic_path)

    wordcloud = WordCloud(background_color='white',
                          font_path=r'C:\Windows\Fonts\simfang.ttf',
                          mask=im_mask,
                          stopwords=STOPWORDS).generate(new_text)

    plt.imshow(wordcloud)
    plt.axis('off')
    plt.show()
    wordcloud.to_file('ciyun.jpg')


word_list = get_word()
get_word_list(word_list)

过程中常会出现的一个错误就是：

OSError: cannot open resource

这个是因为找不到你计算机上的字体而报错，需要你在字体的文件上看清字体的英文名称

选中点击右键-属性：

复制英文名称到font_path参数