把词频排名前5的单词和出现频次保存到一个文本文件中,并将文件名统一格式为“姓名.txt”
'''假设有一段文本保存在text.txt文件中,对其进行分词后统计词频排名前5的单词和出现频次'''
import jieba
# 读取文本内容
with open('text.txt', 'r', encoding='utf-8') as f:
text = f.read()
# 分词
words = list(jieba.cut(text))
# 统计词频
word_freq = {}
for word in words:
if word in word_freq:
word_freq[word] += 1
else:
word_freq[word] = 1
# 排序并取前5个
top_words = sorted(word_freq.items(), key=lambda x: x[1], reverse=True)[:5]
# 保存到文件
filename = '姓名.txt'
with open(filename, 'w', encoding='utf-8') as f:
for word, freq in top_words:
f.write(f'{word}\t{freq}\n')