Skip to content

Instantly share code, notes, and snippets.

@tcitry
Created November 9, 2017 06:57
Show Gist options
  • Save tcitry/6a98eb03fe52e2c35ae1bcf26d9335a7 to your computer and use it in GitHub Desktop.
Save tcitry/6a98eb03fe52e2c35ae1bcf26d9335a7 to your computer and use it in GitHub Desktop.
# -*- coding:utf-8 -*-
import io
import re
class Counter:
def __init__(self, path):
"""
:param path: 文件路径
"""
self.mapping = dict()
with io.open(path, encoding="utf-8") as f:
data = f.read()
words = [s.lower() for s in re.findall("\w+", data)]
for word in words:
self.mapping[word] = self.mapping.get(word, 0) + 1
def most_common(self, n):
assert n > 0, "n should be large than 0"
return sorted(self.mapping.items(), key=lambda item: item[1], reverse=True)[:n]
if __name__ == '__main__':
most_common_5 = Counter("importthis.txt").most_common(5)
for item in most_common_5:
print(item)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment