Fuzzy matching between two arrays of strings. for each item in array1, selects the most similar item from array2

cosine_matching.py

### Fuzzy matching between two arrays.
### for each item in array1, selects the most similar item from array2

import re, math
from collections import Counter

WORD = re.compile(r'\w+')

def get_cosine(vec1, vec2):
    intersection = set(vec1.keys()) & set(vec2.keys())
    numerator = sum([vec1[x] * vec2[x] for x in intersection])

    sum1 = sum([vec1[x]**2 for x in vec1.keys()])
    sum2 = sum([vec2[x]**2 for x in vec2.keys()])
    denominator = math.sqrt(sum1) * math.sqrt(sum2)

    if not denominator:
        return 0.0
    else:
        return float(numerator) / denominator

def text_to_vector(text):
    words = WORD.findall(text)
    return Counter(words)


selected_columns = {}

for i, selected in enumerate(arr2):
    cosine_score = 0.0
    for to_select in arr1:
        tmp_score = get_cosine(text_to_vector(re.subn(r'([ _./\[\(\)\]]+)', ' ', to_select)[0].replace('__', ' ').strip(' ').lower()), 
                               text_to_vector(re.subn(r'([ _./\[\(\)\]]+)', ' ', selected)[0].replace('__', ' ').strip(' ').lower()))
        if  tmp_score > cosine_score:
            cosine_score = tmp_score
            selected_columns[selected] = to_select