How to use the datasketch.minhash.MinHash function in datasketch

from it and then creates a MinHash object from every
        remaining character in the domain.

        If a domain starts with www., it will be stripped of the
        domain before the Minhash is calculated.

        Args:
          domain: string with a full domain, eg. www.google.com

        Returns:
            A minhash (instance of datasketch.minhash.MinHash)
        """
        domain_items = domain.split('.')
        domain_part = '.'.join(domain_items[:-1])

        minhash = MinHash(similarity.DEFAULT_PERMUTATIONS)
        for char in domain_part:
            minhash.update(char.encode('utf8'))

        return minhash

def eg1():
    m1 = MinHash(num_perm=128)
    m2 = MinHash(num_perm=128)
    m3 = MinHash(num_perm=128)
    for d in set1:
        m1.update(d.encode('utf8'))
    for d in set2:
        m2.update(d.encode('utf8'))
    for d in set3:
        m3.update(d.encode('utf8'))

    # Create LSH index
    lsh = MinHashLSH(threshold=0.5, num_perm=128)
    lsh.insert("m2", m2)
    lsh.insert("m3", m3)
    result = lsh.query(m1)
    print("Approximate neighbours with Jaccard similarity > 0.5", result)

def _run_minhash(A, B, data, seed, bs, num_perm):
    (a_start, a_end), (b_start, b_end) = A, B
    hasher = pyhash.murmur3_32()
    m1 = MinHash(num_perm=num_perm, hashobj=Hash)
    m2 = MinHash(num_perm=num_perm, hashobj=Hash)
    for i in xrange(a_start, a_end):
        m1.update(hasher(data[i], seed=seed))
    for i in xrange(b_start, b_end):
        m2.update(hasher(data[i], seed=seed))
    return [m1.jaccard(m2)] + \
            [_b_bit_minhash_jaccard(m1, m2, b) for b in bs]

def _run_minhash(A, B, data, seed, p):
    (a_start, a_end), (b_start, b_end) = A, B
    hasher = pyhash.murmur3_32()
    m1 = MinHash(num_perm=2**p, hashobj=Hash)
    m2 = MinHash(num_perm=2**p, hashobj=Hash)
    for i in xrange(a_start, a_end):
        m1.update(hasher(data[i], seed=seed))
    for i in xrange(b_start, b_end):
        m2.update(hasher(data[i], seed=seed))
    return _minhash_inclusion(m1, m2)

def _run_minhash(A, B, data, seed, p):
    (a_start, a_end), (b_start, b_end) = A, B
    hasher = pyhash.murmur3_32()
    m1 = MinHash(num_perm=2**p, hashobj=Hash)
    m2 = MinHash(num_perm=2**p, hashobj=Hash)
    for i in xrange(a_start, a_end):
        m1.update(hasher(data[i], seed=seed))
    for i in xrange(b_start, b_end):
        m2.update(hasher(data[i], seed=seed))
    return _minhash_inclusion(m1, m2)

def _run_acc(size, seed, num_perm):
    m = MinHash(num_perm=num_perm)
    s = set()
    random.seed(seed)
    for i in range(size):
        v = int_bytes(random.randint(1, size))
        m.update(v)
        s.add(v)
    return (m, s)

def eg1():
    m1 = MinHash(num_perm=128)
    m2 = MinHash(num_perm=128)
    m3 = MinHash(num_perm=128)
    for d in set1:
        m1.update(d.encode('utf8'))
    for d in set2:
        m2.update(d.encode('utf8'))
    for d in set3:
        m3.update(d.encode('utf8'))

    # Create LSH index
    lsh = MinHashLSH(threshold=0.5, num_perm=128)
    lsh.insert("m2", m2)
    lsh.insert("m3", m3)
    result = lsh.query(m1)
    print("Approximate neighbours with Jaccard similarity > 0.5", result)

def eg1():
    m1 = MinHash()
    m2 = MinHash()
    for d in data1:
        m1.update(d.encode('utf8'))
    for d in data2:
        m2.update(d.encode('utf8'))
    print("Estimated Jaccard for data1 and data2 is", m1.jaccard(m2))

    s1 = set(data1)
    s2 = set(data2)
    actual_jaccard = float(len(s1.intersection(s2))) /\
            float(len(s1.union(s2)))
    print("Actual Jaccard for data1 and data2 is", actual_jaccard)

def _run_minhash(data, seed, p):
    hasher = pyhash.murmur3_32()
    m = MinHash(num_perm=2**p, hashobj=Hash)
    for d in data:
        m.update(hasher(d, seed=seed))
    return m.count()