TheAlgorithms-Python
23 строки · 625.0 Байт
1"""
2https://en.wikipedia.org/wiki/N-gram
3"""
4
5
6def create_ngram(sentence: str, ngram_size: int) -> list[str]:
7"""
8Create ngrams from a sentence
9
10>>> create_ngram("I am a sentence", 2)
11['I ', ' a', 'am', 'm ', ' a', 'a ', ' s', 'se', 'en', 'nt', 'te', 'en', 'nc', 'ce']
12>>> create_ngram("I am an NLPer", 2)
13['I ', ' a', 'am', 'm ', ' a', 'an', 'n ', ' N', 'NL', 'LP', 'Pe', 'er']
14>>> create_ngram("This is short", 50)
15[]
16"""
17return [sentence[i : i + ngram_size] for i in range(len(sentence) - ngram_size + 1)]
18
19
20if __name__ == "__main__":
21from doctest import testmod
22
23testmod()
24