Last active
June 1, 2018 16:17
-
-
Save Joopmicroop/770ab436806da9476c9ced0d0c91960e to your computer and use it in GitHub Desktop.
compare sentences / equality fitness function
This file contains 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
function calculateStringFitness(str0,str1,opt){ | |
function countMatches(a0, a1){ | |
var matches, pos0, pos1, matchObj; | |
matches = pos0 = pos1 = 0; | |
matchObj = {}; | |
a0 = a0.sort(); | |
a1 = a1.sort(); | |
function compareToSortOrder( a, b ) { | |
if(a===b) return 0; | |
return ([a,b].sort()[0]===a) ? -1 : 1; | |
} | |
do { | |
var compare = compareToSortOrder( a0[pos0], a1[pos1] ); | |
if (compare == 0) { | |
matchObj[a0[pos0]] = (matchObj[a0[pos0]]) ? matchObj[a0[pos0]]+1 : 1; | |
matches++; pos0++; pos1++; | |
} | |
else if (compare < 0) pos0++; | |
else if (compare > 0) pos1++; | |
} while ( pos0 < a0.length && pos1 < a1.length ); | |
return { | |
matchCount:matches, | |
matches:matchObj | |
} | |
} | |
function sorensenDice(str0, str1, opt){ | |
if(opt && opt.caseSensitive == false){ | |
str0 = str0.toLowerCase(); | |
str1 = str1.toLowerCase(); | |
} | |
var splitChar = (opt && opt.split == 'word') ? ' ':''; | |
var a0 = str0.split(splitChar); | |
var a1 = str1.split(splitChar); | |
var match = countMatches(a0, a1); | |
var dsc = (2.0*(match.matchCount))/(a0.length+a1.length); | |
return { | |
matchCount: match.matchCount, | |
matches: match.matches, | |
simFactor: dsc | |
}; | |
} | |
// calculate sorensenDice aka match coefficient | |
// https://en.wikipedia.org/wiki/S%C3%B8rensen%E2%80%93Dice_coefficient | |
var sd = sorensenDice(str0,str1,opt); | |
// calculate jaccardIndex from sorensenDice aka overlap coefficient | |
// https://en.wikipedia.org/wiki/Jaccard_index | |
var ji = sd.simFactor/(2-sd.simFactor); | |
return { | |
matchCount: sd.matchCount, | |
matches: sd.matches, | |
sorensenDice: sd.simFactor, | |
jaccardIndex: ji | |
}; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment