Given a string of a million numbers, return all repeating 3 digit numbers

Question

I had an interview with a hedge fund company in New York a few months ago and unfortunately, I did not get the internship offer as a data/software engineer. (They also asked

Answer 1

Here is a NumPy implementation of the "consensus" O(n) algorithm: walk through all triplets and bin as you go. The binning is done by upon encountering say "385", adding one to bin[3, 8, 5] which is an O(1) operation. Bins are arranged in a 10x10x10 cube. As the binning is fully vectorized there is no loop in the code.

def setup_data(n):
    import random
    digits = "0123456789"
    return dict(text = ''.join(random.choice(digits) for i in range(n)))

def f_np(text):
    # Get the data into NumPy
    import numpy as np
    a = np.frombuffer(bytes(text, 'utf8'), dtype=np.uint8) - ord('0')
    # Rolling triplets
    a3 = np.lib.stride_tricks.as_strided(a, (3, a.size-2), 2*a.strides)

    bins = np.zeros((10, 10, 10), dtype=int)
    # Next line performs O(n) binning
    np.add.at(bins, tuple(a3), 1)
    # Filtering is left as an exercise
    return bins.ravel()

def f_py(text):
    counts = [0] * 1000
    for idx in range(len(text)-2):
        counts[int(text[idx:idx+3])] += 1
    return counts

import numpy as np
import types
from timeit import timeit
for n in (10, 1000, 1000000):
    data = setup_data(n)
    ref = f_np(**data)
    print(f'n = {n}')
    for name, func in list(globals().items()):
        if not name.startswith('f_') or not isinstance(func, types.FunctionType):
            continue
        try:
            assert np.all(ref == func(**data))
            print("{:16s}{:16.8f} ms".format(name[2:], timeit(
                'f(**data)', globals={'f':func, 'data':data}, number=10)*100))
        except:
            print("{:16s} apparently crashed".format(name[2:]))

Unsurprisingly, NumPy is a bit faster than @Daniel's pure Python solution on large data sets. Sample output:

# n = 10
# np                    0.03481400 ms
# py                    0.00669330 ms
# n = 1000
# np                    0.11215360 ms
# py                    0.34836530 ms
# n = 1000000
# np                   82.46765980 ms
# py                  360.51235450 ms