[("MLGuy42", "andrew@gmail.com", "123-4567"),
("CS229DungeonMaster", "123-4567", "ml@stanford.edu"),
("Doomguy", "john@oculus.com", "carmack@gmail.com"),
("andrew26", "andrew@gmail.com", "mlguy@gmail.com")]

[[0, 1, 3], [2]]

def find_duplicates(user_info):
    results = list()
    seen = dict()
    for i, user in enumerate(user_info):
        first_seen = True
        key_info = None
        for info in user:
            if info in seen:
                first_seen = False
                key_info = info
                break
        if first_seen:
            results.append([i])
            pos = len(results) - 1
        else:
            index = seen[key_info]
            results[index].append(i)
            pos = index
        for info in user:
            seen[info] = pos
    return results

def find_duplicates(user_info):
    results = list()
    seen = dict()
    for i, user in enumerate(user_info):
        for info in user:
            if info in seen:
                index = seen[info]
                results[index].append(i)
                pos = index
                break
        else:
            results.append([i])
            pos = len(results) - 1
        for info in user:
            seen[info] = pos
    return results

from random import randrange
from timeit import timeit
MAXVALUE = 1000

for a in range(5): #I wanted to make sure I checked 5 to make sure I don't get a outlier data set that effects my ability to use timeit reasonably.
    user_info = [[randrange(MAXVALUE) for i in range(3)] for _ in range(1000)]
    print(timeit(lambda: find_duplicates(user_info), number=10000))