chenygie / yanshi

测试

yanshi

测试

预处理数据

# 用string库中的punctuation，完成英文符号的替换。
from string import punctuation
process_dicts={i:'' for i in punctuation}
print(process_dicts)

punc_table = str.maketrans(process_dicts)
test_sentence = test_sentence.translate(punc_table)

计算英文词频

test_sentence_list = test_sentence.lower().split()

word_dict_count = {}
for word in test_sentence_list:
    word_dict_count[word] = word_dict_count.get(word, 0) + 1

word_list = []
soted_word_list = sorted(word_dict_count.items(), key=lambda x: x[1], reverse=True)
for key in soted_word_list:
    word_list.append(key[0])

word_list = word_list[:2500]
print(len(word_list))