Find closest string pattern

[jmair]

Using the normalized compression distance, option 1 is better in the first example and option 2 is better in the second example

from zlib import compress

def ncd(a, b):
    """Normalized compression distance between two byte strings"""
    u =len(compress(a))
    v =len(compress(b))
    u, v =min(u, v), max (u, v)
    w =len(compress(a + b))
    return float (w - u) / v 

def l2b(alist):
    return ",".join(alist).encode()

def option_distances(alist, *options):
    b = l2b(alist)
    return [(ncd(b, l2b(option)), option)
            for option in options]


if __name__ == '__main__':
    my_list = ['one', 'two', 'three' , 'four']
    option_one = ['two', 'three', 'one', 'four']
    option_two = ['four', 'three', 'two', 'one']
    
    print(my_list)
    for d, option in option_distances(my_list, option_one, option_two):
        print(d, option)
    
    my_list = "red red red blue black".split()
    option1 = "blue red".split()
    option2 = "red black".split()
    
    print(my_list)
    for d, option in option_distances(my_list, option1, option2):
        print(d, option)

Output:
['one', 'two', 'three', 'four']
0.19230769230769232 ['two', 'three', 'one', 'four']
0.3076923076923077 ['four', 'three', 'two', 'one']
['red', 'red', 'red', 'blue', 'black']
0.43478260869565216 ['blue', 'red']
0.391304347826087 ['red', 'black']

Perfect, thanks. I'll look at that. Appreciate the direction.