You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
48 lines
1.3 KiB
48 lines
1.3 KiB
9 months ago
|
import re
|
||
|
from collections import Counter
|
||
|
|
||
|
# 清洗文本,移除标点符号并转换为小写
|
||
|
def clean_text(text):
|
||
|
return re.sub(r'[^\w\s]', '', text).lower()
|
||
|
|
||
|
# 统计词频
|
||
|
def count_frequencies(text):
|
||
|
return Counter(word for word in clean_text(text).split())
|
||
|
|
||
|
# 交互式提示用户输入文件路径和前n个单词的数量
|
||
|
def interactive_mode():
|
||
9 months ago
|
file_path = input("请输入文件路径 >> ")
|
||
9 months ago
|
try:
|
||
9 months ago
|
n = int(input("请输入你想要输出的前n个最常见单词的数量 >> "))
|
||
9 months ago
|
if n <= 0:
|
||
|
raise ValueError("数量必须大于0。")
|
||
|
except ValueError as e:
|
||
|
print(f"输入错误:{e}")
|
||
|
return
|
||
|
|
||
|
try:
|
||
|
# 打开文件并读取内容
|
||
|
with open(file_path, 'r', encoding='utf-8') as file:
|
||
|
text = file.read()
|
||
|
|
||
|
# 统计词频
|
||
|
frequencies = count_frequencies(text)
|
||
|
|
||
|
# 获取前n个最常见的单词
|
||
|
most_common = frequencies.most_common(n)
|
||
|
|
||
|
# 输出结果
|
||
|
for word, freq in most_common:
|
||
|
print(f"{word}: {freq}")
|
||
|
except FileNotFoundError:
|
||
|
print(f"文件未找到: {file_path}")
|
||
|
except Exception as e:
|
||
|
print(f"发生错误: {e}")
|
||
|
|
||
|
# 主函数
|
||
|
def main():
|
||
|
print("欢迎使用词频统计工具。")
|
||
|
interactive_mode()
|
||
|
|
||
|
if __name__ == "__main__":
|
||
|
main()
|