Last active
March 11, 2019 14:52
-
-
Save jhamberg/0de5e2cbbc60920107277d49b8873834 to your computer and use it in GitHub Desktop.
Calculate the Jaccard Distance between two strings
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
import java.util.HashMap; | |
public class JaccardDistance { | |
public static double jaccard(String a, String b) { | |
HashMap<String, Integer> map = new HashMap<>(); | |
// For each bigram in first string, add 1 | |
for(int i=0; i < a.length()-1; i++) { | |
String bigram = "" + a.charAt(i) + a.charAt(i+1); | |
map.put(bigram, map.getOrDefault(bigram, 0) + 1); | |
} | |
// For each bigram in second string, reduce 1 | |
for(int i=0; i < b.length()-1; i++) { | |
String bigram = "" + b.charAt(i) + b.charAt(i+1); | |
map.put(bigram, map.getOrDefault(bigram, 0) - 1); | |
} | |
// Calculate elements in intersection | |
int intersection = 0; | |
int missingFromA = 0; | |
for(int value : map.values()) { | |
intersection += Math.abs(value); | |
// Negative values are missing from A | |
if (value < 0) { | |
missingFromA += Math.abs(value); | |
} | |
} | |
// Calculate elements in union | |
int bigramsInA = a.length() - 1; | |
int union = bigramsInA + missingFromA; | |
return intersection/(double)union; | |
} | |
public static void main(String[] args) { | |
System.out.println(jaccard( | |
"The quick brown fox jumps over the lazy dog", | |
"The quick brown fox jumps over the hazy dog")); | |
// Result: 0.09090909090909091 | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment