forked from p46318075/CodePattern
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.
10 lines
245 B
10 lines
245 B
9 months ago
|
import re
|
||
|
|
from collections import Counter
|
||
|
|
|
||
|
|
class WordFrequencyModel:
|
||
|
|
def get_top_n_words(self, text, top_n=10):
|
||
|
|
words = re.findall(r'\b\w+\b', text)
|
||
|
|
word_counts = Counter(words)
|
||
|
|
return word_counts.most_common(top_n)
|
||
|
|
|