Search code examples
similarityjaro-winkler

Jaro Similarity

For finding Jaro similarity I found the matching charecters as follows

matching charecters in string 1 :  AABABCAAAC   
matching charecters in string 2 :  ABAACBAAAC

what is the value of t(0.5*transpositions)? (source: wikipedia)

Solution

  • Transpositions in this context are all those characters that don't match the same position on strings

    from wikipedia

    m = 10
t = 4/2 = 2
|S1| = 10
|S2| = 10
d = 1/3 * (10/10 + 10/10 + (10-2)/10) = 0.933

    these transposition are [A/B, B/A, B/C, C/B] so t is calculed with |[A/B, B/A, B/C, C/B]| / 2.