profile_select_random_element.py

"""Measure relative performance of answers to [1].

    [1] http://stackoverflow.com/questions/1456617
"""
import linecache
import random
from timeit import default_timer


WORDS_FILENAME = "/etc/dictionaries-common/words"


def measure(func):
    measure.func_to_measure.append(func)
    return func
measure.func_to_measure = []


@measure
def dcrosta():
    words = [line.strip() for line in open(WORDS_FILENAME)]
    return random.choice(words)


@measure
def dcrosta_no_strip():
    words = [line for line in open(WORDS_FILENAME)]
    return random.choice(words)


def select_random_line(filename):
    selection = None
    count = 0
    for line in file(filename, "r"):
        if random.randint(0, count) == 0:
            selection = line.strip()
            count = count + 1
    return selection


@measure
def mark_ransom():
    return select_random_line(WORDS_FILENAME)


def select_random_line_no_strip(filename):
    selection = None
    count = 0
    for line in file(filename, "r"):
        if random.randint(0, count) == 0:
            selection = line
            count = count + 1
    return selection


@measure
def mark_ransom_no_strip():
    return select_random_line_no_strip(WORDS_FILENAME)


def choose_from(iterable):
    """Choose a random element from a finite `iterable`.

    If `iterable` is a sequence then use `random.choice()` for efficiency.

    Return tuple (random element, total number of elements)
    """
    selection, i = None, None
    for i, item in enumerate(iterable):
        if random.randint(0, i) == 0:
            selection = item

    return selection, (i+1 if i is not None else 0)


@measure
def mark_ransom_choose_from():
    return choose_from(open(WORDS_FILENAME))


@measure
def nadia():
    global total_num_lines
    total_num_lines = sum(1 for _ in open(WORDS_FILENAME))

    line_number = random.randint(0, total_num_lines)
    return linecache.getline(WORDS_FILENAME, line_number)


@measure
def nadia_known_num_lines():
    line_number = random.randint(0, total_num_lines)
    return linecache.getline(WORDS_FILENAME, line_number)


@measure
def jfs():
    return random.choice(list(open(WORDS_FILENAME)))


def timef(func, number=1000, timer=default_timer):
    """Return number of seconds it takes to execute `func()`."""
    start = timer()
    for _ in range(number):
        func()
    return (timer() - start) / number


def main():
    # measure time
    times = dict((f.__name__, timef(f, number=10))
                 for f in measure.func_to_measure)

    # print from fastest to slowest
    maxname_len = max(map(len, times))
    last = None
    for name in sorted(times, key=times.__getitem__):
        print "%s %4.2g seconds %.2f" % (name.ljust(maxname_len), times[name],
                                         last and times[name] / last or 1)
        last = times[name]


if __name__ == "__main__":
    main()

# nadia_known_num_lines   9.6e-06 seconds 1.00
# nadia                   0.056 seconds 5843.51
# jfs                     0.062 seconds 1.10
# dcrosta_no_strip        0.091 seconds 1.48
# dcrosta                 0.13 seconds 1.41
# mark_ransom_no_strip    0.66 seconds 5.10
# mark_ransom_choose_from 0.67 seconds 1.02
# mark_ransom             0.69 seconds 1.04