• PYTHON 词云


     1 #!/usr/bin/env python
     2  # -*- coding:utf-8 -*-
     3 import matplotlib.pyplot as plt
     4 from wordcloud import WordCloud,STOPWORDS,ImageColorGenerator
     5 import jieba
     6 from scipy.misc import imread
     7 from os import path
     8 
     9 def word_clould(file_path,stopwords_path,font_path,save_pic_name):
    10     text_from_file_with_apath = open(file_path,encoding='utf-8').read()
    11 
    12     wordlist_after_jieba = jieba.cut(text_from_file_with_apath)
    13     stop_words = [line.strip() for line in open(stopwords_path,encoding='utf-8')]
    14     wordlist_jieba=[word for word in wordlist_after_jieba if word not in stop_words]
    15     wl_space_split = " ".join(wordlist_jieba)
    16     # 读取mask/color图片
    17     d = path.dirname(__file__)
    18     #nana_coloring = imread(path.join(d,bgpicture_path))
    19 
    20     my_wordcloud = WordCloud(#background_color="white",
    21                              width=1200,height=800,
    22                              # max_font_size=30,
    23                              #max_words=5000,
    24                              margin = 5,
    25                              #mask = nana_coloring,
    26                              random_state = 30,
    27                              #stopwords = STOPWORDS,
    28                              font_path=font_path).generate(wl_space_split)
    29 
    30     #image_colors = ImageColorGenerator(nana_coloring)
    31 
    32     # recolor wordcloud and show
    33     #my_wordcloud.recolor(color_func=image_colors)
    34     plt.imshow(my_wordcloud)
    35     plt.axis("off")
    36     plt.show()
    37 
    38     my_wordcloud.to_file(path.join(d, save_pic_name))
    39 
    40 
    41 file_path='小米6发布会.txt'
    42 stopwords_path='E:\stopwords.txt'
    43 #bgpicture_path="E:\wb.jpg"
    44 font_path='E:\SIMHEI.TTF'
    45 save_pic_name="cloudimg1.png"
    46 word_clould(file_path,stopwords_path,font_path,save_pic_name)
  • 相关阅读:
    汉罗塔问题
    有进度条圆周率计算
    turtle库笔记
    OwnCloud建立属于自己私有的云存储网盘
    HTTP 常见请求状态码
    虚拟机部署Kubernetes集群
    常用文件头(16进制)
    配置LAMP环境
    Linux系统日志
    Java的socket通信与操作系统的SocketAPI关系探究
  • 原文地址:https://www.cnblogs.com/Erick-L/p/6730768.html
Copyright © 2020-2023  润新知