A much more effective algorithm for string similarity found on Stack Overflow

string_similarity.py

import wikipedia

def get_bigrams(string):
  '''
  Takes a string and returns a list of bigrams
  '''
  s = string.lower()
  return [s[i:i+2] for i in xrange(len(s) - 1)]

def string_similarity(str1, str2):
  '''
  Perform bigram comparison between two strings
  and return a percentage match in decimal form

  source: http://stackoverflow.com/a/6859596/170005
  '''
  pairs1 = get_bigrams(str1)
  pairs2 = get_bigrams(str2)
  union  = len(pairs1) + len(pairs2)
  hit_count = 0
  for x in pairs1:
    for y in pairs2:
      if x == y:
          hit_count += 1
          break
  return (2.0 * hit_count) / union

def closest_wiki_result(film):
    closest_match = 0
    max_score = 0
    search_results = wiki.search(film)
    print "Search results : "
    for ind, result in enumerate(search_results):
        print "\t", result
        score = string_similarity(film, result)
        if score > max_score:
            max_score = score
            closest_match = ind

    print '\nClosest match for ', film, ' is :', search_results[closest_match]

# add the word ' film' to the movie name
# even if the original name has it

film = 'Jurassic World (2015) film'
closest_wiki_result(film)

### Expected output

# Search results : 
# 	Jurassic Park
# 	Jurassic
# 	Jurassic Park (film)
# 	Jurassic Park III
# 	Jurassic World
# 	Jurassic World: Original Motion Picture Soundtrack
# 	The Lost World: Jurassic Park
# 	The Lost World: Jurassic Park (Sega game)
# 	List of Jurassic Park video games
# 	Lego Jurassic World
# 
# Closest match for  Jurassic World (2015) film  is : Jurassic World

👍