【python】词频统计

我们在网购时，一般都会参考物品的评价。物品的评价一般是按好评、中评和差评来进行分类的。评论如果是文字浏览，还不够直观，若能增加评词的图形化展示，将更利于消费者选购。

import re
import jieba
import wordcloud
import numpy as np
from PIL import Image
import matplotlib.pyplot as plt

with open('d:/bookComments.txt','r') as fp:
    bookComments=fp.read()

r='[。，.！？&!;?*:\()（）《》]+'
Comments_data=re.sub(r,'',bookComments)

Comments=Comments_data.split('\n')
print("一共有{}条书评;".format(len(Comments)))

CommentsTuple=tuple(Comments)

with open('d:/bookCommentsNew.txt','w') as fp:
    for item in CommentsTuple:
        fp.write(item+'\n')

for item in CommentsTuple:
    aset=set(item)

rule = lambda x:len(set(x))/20>0.6
result = filter(rule,CommentsTuple)

with open('d:/bookCommentsNew.txt','w') as fp:
    for item in result:
        fp.write(item+'\n')

Comments_list_exact = jieba.cut(bookComments,cut_all=False)
d=dict()
for key in Comments_list_exact:
    d[key]= d.get(key,0)+1

print(d)

mask = np.array(Image.open('d:/png/beijing.png'))
wc=wordcloud.WordCloud(
    font_path='C:/Windows/Fonts/simhei.ttf',
    width=500,height=400,
    mask=mask,
    max_words=200,
    max_font_size=100,
    background_color='white',
    font_step=3,
    random_state=True,
    prefer_horizontal=0.9)

wc.generate_from_frequencies(d)

image_colors=wordcloud.ImageColorGenerator(mask)

wc.recolor(color_func=image_colors)

plt.imshow(wc)
plt.axis('off')
plt.show()

jieba下载方式：

①首先先下载清华园

 ②在pycharm左上角找到File，选择settings

③选择“+”选择需要下载的插件