From c607a864c4748bb86c6752eb374232ac122bfd2f Mon Sep 17 00:00:00 2001 From: Guangnan Zhu Date: Wed, 9 Jul 2025 15:16:10 +1000 Subject: [PATCH] similarity_function_revise --- coordination_network_toolkit/similarity.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/coordination_network_toolkit/similarity.py b/coordination_network_toolkit/similarity.py index d34b849..91b9d7f 100644 --- a/coordination_network_toolkit/similarity.py +++ b/coordination_network_toolkit/similarity.py @@ -48,6 +48,8 @@ def tokenize(text: str, tokenizer: Pattern = word_tokenizer) -> str: def similarity(tokens_1, tokens_2): set_1 = set(tokens_1.split()) set_2 = set(tokens_2.split()) + if len(set_1 | set_2) == 0: + return 0 return len(set_1 & set_2) / len(set_1 | set_2)