vhxs

import numpy as np
from random import sample


# The Jaccard distance is truly a metric: https://arxiv.org/pdf/1612.02696.pdf
def jaccard_distance(set1: set, set2: set):
    union_size = len(set1.union(set2))
    intersection_size = len(set1.intersection(set2))

    return 1 - (intersection_size / union_size)