Last active
June 30, 2021 03:40
-
-
Save punit-naik/a214a6d4719754ba1ea347022ec5d71b to your computer and use it in GitHub Desktop.
Levenshtein Distance function implemented in Clojure
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
(defn levenshtein-distance | |
"Finds the percentage of match (reversed levenshtein distance & normalised) | |
between two strings" | |
[s1 s2] | |
(let [similarity (atom 0) | |
edit-map (atom {})] | |
(doseq [i (range (count s1))] | |
(let [edit (atom (if (zero? i) 0 i))] | |
(doseq [j (range (count s2))] | |
(let [e (if (= (.charAt s1 i) (.charAt s2 j)) 0 1)] | |
(reset! edit | |
(min | |
(if (zero? j) | |
(+ i 2) | |
(inc @edit)) | |
(if (zero? i) | |
(+ j 2) | |
(inc (@edit-map (str (dec i) "," j)))) | |
(+ (cond | |
(zero? i) j | |
(zero? j) i | |
:else (@edit-map (str (dec i) "," (dec j)))) | |
(if (and (zero? i) (zero? j)) 0 e)))) | |
(swap! edit-map assoc (str i "," j) @edit) | |
(when (and (= i (dec (count s1))) (= j (dec (count s2)))) | |
(reset! edit-map nil) | |
(reset! similarity @edit)))))) | |
(double (- 100 (* 100 (/ @similarity (+ (count s1) (count s2)))))))) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment