计算英文文章词频的两种方法

 1 speech_text='xxx'
 2 speech = speech_text.lower().split()
 3 dic = {}
 4 for word in speech:
 5     if word not in dic:
 6         dic[word]=1
 7     else:
 8         dic[word]+=1
 9 import operator
10 swd = sorted(dic.items(),key = operator.itemgetter(1),reverse=True)
11 from nltk.corpus import stopwords
12 from string import punctuation
13 stop_words = stopwords.words('English')
14 for k,v in swd:
15     if k not in stop_words:
16         print(k,v)
17 
18 ##########################
19 from collections import Counter
20 c = Counter(speech)
21 for sw in stop_words:
22     del c[sw]
23 c.most_common(10)

 

转载于:https://www.cnblogs.com/Erick-L/p/6735944.html