Created
September 6, 2012 14:25
-
-
Save MichaelAstreiko/3656824 to your computer and use it in GitHub Desktop.
Find Algorithm for similarities
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
/** | |
* Made test of three word comparison algorithms: | |
* JaroWinkler, SmithWatermanGotoh and Soundex | |
* | |
* Based on test result Soundex is chosen to be used in venue title merging algorithm | |
* It is more usable, so that I can say if similarity > 0.98 then is same word | |
*/ | |
void testMergeAlgorithms() { | |
def cafeName1 = "Antonio Cafe" | |
def cafeName2 = "Antonio's Cafe" | |
def cafeName3 = "Antonio Kafe" | |
def cafeName4 = "Antonio hotel" | |
def cafeName5 = "Mary Coffee" | |
def algorithm = new JaroWinkler() | |
assertTrue algorithm.getSimilarity(cafeName1, cafeName2) == 0.9809524f | |
assertTrue algorithm.getSimilarity(cafeName1, cafeName3) == 0.9777778f | |
assertTrue algorithm.getSimilarity(cafeName3, cafeName2) == 0.96031743f | |
assertTrue algorithm.getSimilarity(cafeName1, cafeName4) == 0.92564106f | |
assertTrue algorithm.getSimilarity(cafeName1, cafeName5) == 0.55707073f | |
algorithm = new SmithWatermanGotoh() | |
assertTrue algorithm.getSimilarity(cafeName1, cafeName2) == 0.9f | |
assertTrue algorithm.getSimilarity(cafeName1, cafeName3) == 0.8666667f | |
assertTrue algorithm.getSimilarity(cafeName3, cafeName2) == 0.76666665f | |
assertTrue algorithm.getSimilarity(cafeName1, cafeName4) == 0.7f | |
assertTrue algorithm.getSimilarity(cafeName1, cafeName5) == 0.3272727f | |
algorithm = new Soundex() | |
assertTrue algorithm.getSimilarity(cafeName1, cafeName2) == 1.0f | |
assertTrue algorithm.getSimilarity(cafeName1, cafeName3) == 1.0f | |
assertTrue algorithm.getSimilarity(cafeName3, cafeName2) == 1.0f | |
assertTrue algorithm.getSimilarity(cafeName1, cafeName4) == 0.9444444f | |
assertTrue algorithm.getSimilarity(cafeName1, cafeName5) == 0.5555556f | |
assertTrue algorithm.getSimilarity(cafeName2, cafeName5) == 0.5555556f | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment