Python英文文章词频统计(14份剑桥真题词频统计)

import jieba
# 以只读方式打开text（即真题库）
text = open('text.txt', 'r', encoding = 'utf-8').read()
# len(text)

#统一为小写 
text = text.lower()

# 需要剔除的词汇列表，也可以用记事本的形式，添加一个打开记事本的语句即可
# 即 stwlist = [line.strip() for line in open 'stopwords.txt',encoding='utf-8').readlines()]
# 这里使用列表
stwlist = ['the','a','of','to','end','in','you','is','that','for','on','it','as','your','...','14',
      'this','or','20','40','27','30','13','21','26','10','15','22',
      '32','31','1','2','4','5','6','7','8','9','0','10','11','12','13',
      '12','13','15','16','17','25','33','35','36','18','23','19','24',
      '38','29','34','37','000','...............................']

# 先进行分词
words = jieba.cut(text, cut_all = False, HMM = True)
#cut_all:是否采用全模式
#HMM：是否采用HMM模型

word_ = {}
for word in words:
  if (word.strip() not in stwlist):
    if len(word) > 1:
      if word != '\t':
        if word != '\r\n':
 # 计算词频
          if word in word_:
            word_[word] += 1
          else:
            word_[word] = 1

# 将结果保存为元组
word_freq = []
for word, freq in word_.items():
  word_freq.append((word, freq))

# 降序排列
word_freq.sort(key = lambda x:x[1], reverse = True)

#输出前3500个词汇
for i in range(3500):
  word, freq = word_freq[i]
  print('{0:10}{1:5}'.format(word, freq))