Python version of this: https://gist.github.com/jsuchal/54e26cc6601bf737b94d

minhasher.py

import random

class MinHasher(object):
    def __init__(self, n, universe_size, seed=None):
        if seed != None: random.seed(seed) 
        self.hash_functions = [self._create_random_hash_function(universe_size) for i in range(n)]

    def _create_random_hash_function(self, universe_size):
        a = random.randint(0, universe_size)
        b = random.randint(0, universe_size)
        return lambda x: (a * x + b) % universe_size

    def generate_signature(self, s):
        return [self.calculate_minhash(func, s) for func in self.hash_functions]

    def calculate_minhash(self, hash_function, s):
        minhash = float("inf") 
        for item in s:
            value = hash_function(item)
            if value < minhash:
                minhash = value
        return int(minhash)

def jaccard(s1, s2):
    x = set(s1)
    y = set(s2)
    return float(len(x & y)) / len(x | y)

def similarity(s1, s2):
    matches = 0
    for i, h in enumerate(s1):
        if h == s2[i]:
            matches += 1
    return matches / float(len(s1))

if __name__ == '__main__':
    minhasher = MinHasher(10, 12549826247007890, 1234567)

    u1 = range(1,10000)
    u2 = range(5001,20000)

    s1 = minhasher.generate_signature(u1)
    s2 = minhasher.generate_signature(u2)

    print 'J(u1, u2) = %s' % jaccard(u1, u2)
    print 'sim(u1, u2) = %s' % similarity(s1, s2)

    print s1
    print s2