在Python语言中将列表从文本拆分成nGrams

pip install nltk

import nltk

def split_to_ngrams(text, n):
    tokens = nltk.word_tokenize(text)  # 将文本分割成单词
    ngrams = nltk.ngrams(tokens, n)  # 将单词列表拆分成nGrams
    return list(ngrams)

text = "This is an example sentence."
n = 2  # 拆分成2Grams

ngrams = split_to_ngrams(text, n)
print(ngrams)

[('This', 'is'), ('is', 'an'), ('an', 'example'), ('example', 'sentence'), ('sentence', '.')]