fork download
copy 
  1. #-*- coding:utf-8 -*-
  2.  
  3. """ A basic lexicographic Similarity algorithm ...part1
  4.     @author: WhiZTiM (Timothy Onogu)
  5. 	@copyright: (c) January, 2013
  6. 	@NOTE: This algorithm is developed as it is, with the hope
  7. 		that it will be useful and I will not be responsible
  8. 		for any failures if any arises...
  9. 	@contact: whiztim@whiztim.com
  10. """
  11.  
  12. def split_on_delimeters(string, delimeter=":;. \"!,$()-_+=~'`"):
  13. 	"""splits string upon the occurence of any character in delimeter"""	
  14. 	rtn = []
  15. 	placeHolder = ""
  16. 	for x in string:
  17. 		if(not x in delimeter):			#if current iter is not a delimeter
  18. 			placeHolder = placeHolder + x
  19. 			continue
  20. 		if(placeHolder != ""):			#Not allowed to append empty string
  21. 			rtn.append(placeHolder)
  22. 			placeHolder = ""
  23. 			continue
  24. 	if(placeHolder != ""):				#Add the last item that is not catered for in the "for-loop"
  25. 		rtn.append(placeHolder)
  26. 	return rtn
  27.  
  28. def returnbigrams(string):
  29. 	"""This function returns bigrams"""
  30. 	return [string[n:n+2] for n in range(len(string) - 1)]
  31.  
  32. def word_similarity(word1, word2, case_sensitive=False):
  33. 	"""This function, returns in percentage, how similar the string 'word1' is to 'word2'
  34. 	   >..>case_sensitive for considering cases"""
  35. 	if(not case_sensitive):
  36. 		word1 = word1.lower()
  37. 		word2 = word2.lower()
  38. 	pairs_word1 = returnbigrams(word1)
  39. 	pairs_word2 = returnbigrams(word2)
  40. 	t = len(pairs_word1) + len(pairs_word2)
  41.  
  42. 	sb = 0
  43. 	for x in pairs_word1:
  44. 		for y in pairs_word2:
  45. 			if(x == y): 			#bigrams match
  46. 				sb += 2.0		#add (1+1=2).. since its found in both.
  47. 				pairs_word2.remove(y)	#we do not need it again
  48. 				break			#break inner loop
  49.  
  50. 	similarity = (sb / t * 100.0)
  51. 	return similarity
  52.  
  53. sent1= "Getting higher on rank oh"
  54. sent2= "Getting on higher rank"
  55.  
  56. list1 =  split_on_delimeters(sent1)
  57. list2 =  split_on_delimeters(sent2)
  58. list1_ratios=[]
  59.  
  60. if len(list1) > len(list2):
  61.     for x in list1:
  62.         list2_ratios=[]
  63.         for y in list2:
  64.             list2_ratios.append(word_similarity(x,y))
  65.         list1_ratios.append(max(list2_ratios))
  66.     print list1_ratios
  67. else:
  68.     for x in list2:
  69.         list2_ratios=[]
  70.         for y in list1:
  71.             list2_ratios.append(word_similarity(x,y))
  72.         list1_ratios.append(max(list2_ratios))
  73.     print list1_ratios
  74.  
  75.  
  76.  
Success #stdin #stdout 0.09s 10824KB
comments (?)
stdin
copy 
Standard input is empty
stdout
copy 
[100.0, 100.0, 100.0, 100.0, 0.0]
https://ideone.com/rn9J1H
language:
Python (cpython 2.7.16)
created:
11 years ago
visibility:
public

Share or Embed source code

Discover > Sphere Engine API

The brand new service which powers Ideone!

Discover > IDE Widget

Widget for compiling and running the source code in a web browser!