Last active
December 11, 2015 07:08
-
-
Save neuro-sys/4563703 to your computer and use it in GitHub Desktop.
Dice's co-efficient
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
| import java.util.*; | |
| /** | |
| * Source: http://www.codeproject.com/Articles/147230/Simple-Fuzzy-String-Similarity-in-Java | |
| * By George Stragand, 17 Jan 2011 | |
| */ | |
| public class Dice { | |
| public static List<char[]> bigram(String input) { | |
| ArrayList<char[]> bigram = new ArrayList<char[]>(); | |
| for (int i = 0; i < input.length() - 1; i++) { | |
| char[] chars = new char[2]; | |
| chars[0] = input.charAt(i); | |
| chars[1] = input.charAt(i+1); | |
| bigram.add(chars); | |
| } | |
| return bigram; | |
| } | |
| public static double dice(List<char[]> bigram1, List<char[]> bigram2) { | |
| List<char[]> copy = new ArrayList<char[]>(bigram2); | |
| int matches = 0; | |
| for (int i = bigram1.size(); --i >= 0;) { | |
| char[] bigram = bigram1.get(i); | |
| for (int j = copy.size(); --j >= 0;) { | |
| char[] toMatch = copy.get(j); | |
| if (bigram[0] == toMatch[0] && bigram[1] == toMatch[1]) { | |
| copy.remove(j); | |
| matches += 2; | |
| break; | |
| } | |
| } | |
| } | |
| return (double) matches / (bigram1.size() + bigram2.size()); | |
| } | |
| public static void main(String[] args) { | |
| String a = "Selam merhaba nasilsiniz"; | |
| String b = "Slm nbr nslsnz ii u?"; | |
| double dc = dice(bigram(a), bigram(b)); | |
| System.out.println((int) (dc*100) + "%"); | |
| } | |
| } |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment