python BM25

安装
pip install rank-bm25

from rank_bm25 import BM25Okapi

corpus = [
    "Hello there good man!",
    "It is quite windy in London",
    "How is the weather today?"
]

tokenized_corpus = [doc.split(" ") for doc in corpus]

bm25 = BM25Okapi(tokenized_corpus)

query = "windy London"
tokenized_query = query.split(" ")

print(bm25.get_scores(tokenized_query))

print(bm25.get_top_n(tokenized_query, corpus, n=1))
# ['It is quite windy in London']