import pandas as pd
import numpy as np
import re
from collections import Counter
with open ("/home/baba/txt/1.txt",'r',encoding='gbk') as f:
words=f.read().lower()
rule=re.compile(r'\w+')
words=re.findall(rule,words)
counter_words=Counter(words)
common_words=counter_words.most_common(10)
print(common_words)
[('the', 7845), ('i', 7255), ('and', 6625), ('to', 5226), ('a', 4468), ('of', 4366), ('you', 2993), ('in', 2767), ('was', 2525), ('it', 2413)]
