def jaccard_similarity(aset: AssociationSet, s1: str, s2: str) -> float:
"""
Calculate jaccard index of inferred associations of two subjects
|ancs(s1) /\ ancs(s2)|
---
|ancs(s1) \/ ancs(s2)|
"""
a1 = aset.inferred_types(s1)
a2 = aset.inferred_types(s2)
num_union = len(a1.union(a2))
if num_union == 0:
return 0.0
return len(a1.intersection(a2)) / num_union
def jaccard_similarity(aset: AssociationSet, s1: str, s2: str) -> Tuple[float, list]:
"""
Calculate jaccard index of inferred associations of two subjects
|ancs(s1) /\ ancs(s2)|
---
|ancs(s1) \/ ancs(s2)|
"""
a1 = aset.inferred_types(s1)
a2 = aset.inferred_types(s2)
num_union = len(a1.union(a2))
if num_union == 0:
return 0.0, list()
shared_terms = a1.intersection(a2)
# Note: we need to convert the shared_terms set to a list
# to avoid later JSON serialization problems
return len(shared_terms) / num_union, list(shared_terms)