[Solved] How to efficiently compare two maps?

by


Since your files are sorted, you don’t have to store them or even parse them outside of lines. You can keep advancing in the sequence with the lesser current element:

def count_equal(a, b):
    """
    Counts the number of values that are equal in two sorted iterables.

    >>> odds = [1, 3, 5, 7, 9, 11, 13, 15]
    >>> primes = [2, 3, 5, 7, 11, 13]
    >>> count_equal(odds, primes)
    5
    """
    return _count_equal(iter(a), iter(b))


def _count_equal(a, b):
    c = 0
    x = next(a)
    y = next(b)

    try:
        while True:
            while x < y:
                x = next(a)

            while y < x:
                y = next(b)

            if x == y:
                c += 1
                x = next(a)
                y = next(b)
    except StopIteration:
        return c

You can keep track of how many lines there are in each file separately in the same read:

from __future__ import division


class CountingIterable:
    def __init__(self, iterable):
        self.iterable = iterable

    def __iter__(self):
        count = 0

        for x in self.iterable:
            yield x
            count += 1

        self.count = count


with open('file1.txt', 'r') as a, open('file2.txt', 'r') as b:
    a_counter = CountingIterable(a)
    b_counter = CountingIterable(b)

    a_iterator = iter(a_counter)
    b_iterator = iter(b_counter)

    n = count_equal(a_iterator, b_iterator)

    # consume any remaining elements to acquire count
    for _ in a_iterator: pass
    for _ in b_iterator: pass

    result = n / max(a_counter.count, b_counter.count)

1

solved How to efficiently compare two maps?