How do I find the duplicates in a list and create another list with them?

Question

How can I find the duplicates in a Python list and create another list of the duplicates? The list only contains integers.

Answer 1

Some other tests. Of course to do...

set([x for x in l if l.count(x) > 1])

...is too costly. It's about 500 times faster (the more long array gives better results) to use the next final method:

def dups_count_dict(l):
    d = {}

    for item in l:
        if item not in d:
            d[item] = 0

        d[item] += 1

    result_d = {key: val for key, val in d.iteritems() if val > 1}

    return result_d.keys()

Only 2 loops, no very costly l.count() operations.

Here is a code to compare the methods for example. The code is below, here is the output:

dups_count: 13.368s # this is a function which uses l.count()
dups_count_dict: 0.014s # this is a final best function (of the 3 functions)
dups_count_counter: 0.024s # collections.Counter

The testing code:

import numpy as np
from time import time
from collections import Counter

class TimerCounter(object):
    def __init__(self):
        self._time_sum = 0

    def start(self):
        self.time = time()

    def stop(self):
        self._time_sum += time() - self.time

    def get_time_sum(self):
        return self._time_sum


def dups_count(l):
    return set([x for x in l if l.count(x) > 1])


def dups_count_dict(l):
    d = {}

    for item in l:
        if item not in d:
            d[item] = 0

        d[item] += 1

    result_d = {key: val for key, val in d.iteritems() if val > 1}

    return result_d.keys()


def dups_counter(l):
    counter = Counter(l)    

    result_d = {key: val for key, val in counter.iteritems() if val > 1}

    return result_d.keys()



def gen_array():
    np.random.seed(17)
    return list(np.random.randint(0, 5000, 10000))


def assert_equal_results(*results):
    primary_result = results[0]
    other_results = results[1:]

    for other_result in other_results:
        assert set(primary_result) == set(other_result) and len(primary_result) == len(other_result)


if __name__ == '__main__':
    dups_count_time = TimerCounter()
    dups_count_dict_time = TimerCounter()
    dups_count_counter = TimerCounter()

    l = gen_array()

    for i in range(3):
        dups_count_time.start()
        result1 = dups_count(l)
        dups_count_time.stop()

        dups_count_dict_time.start()
        result2 = dups_count_dict(l)
        dups_count_dict_time.stop()

        dups_count_counter.start()
        result3 = dups_counter(l)
        dups_count_counter.stop()

        assert_equal_results(result1, result2, result3)

    print 'dups_count: %.3f' % dups_count_time.get_time_sum()
    print 'dups_count_dict: %.3f' % dups_count_dict_time.get_time_sum()
    print 'dups_count_counter: %.3f' % dups_count_counter.get_time_sum()