词云分析之英文

Posted 2021-01-29 pandaboy1123

from pyecharts import WordCloud
import jieba
import re
import nltk


with open(r‘F:算法othersmerry.txt‘, ‘r‘, encoding=‘utf-8‘) as f:
    text = f.readlines()
    word_list = []
    word_dic = {}
    for line in text:
        if re.findall(‘([a-zA-Z])‘, line.strip()):
            result = "".join(i for i in line.strip() if ord(i) < 256)
            from nltk.tokenize import WordPunctTokenizer
            words = WordPunctTokenizer().tokenize(result)
            for w in words:
                if 97 <= ord(w.lower()[0]) <= 122:
                    word_list.append(w)
    # print(word_list)
    set_word_list = list(set(word_list))
    for set_word in set_word_list:
        word_dic[set_word] = word_list.count(set_word)
    # print(word_dic)
name = []
value = []
for k,v in word_dic.items():
    name.append(k)
    value.append(int(v)*100)
wordcloud = WordCloud(width=1300, height=620)
wordcloud.add("", name, value, word_size_range=[20, 100],shape=‘pentagon‘)
wordcloud.render(‘test.html‘)