Created
April 22, 2012 20:41
-
-
Save dmikis/2466750 to your computer and use it in GitHub Desktop.
Jaccard Coefficients
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
(defconstant +main-set-length+ 1000) | |
(defconstant +subset-length+ 129) | |
(defconstant +subsets-quantity+ 1000) | |
(defun create-first-set () | |
(let ((*set* (make-array +main-set-length+ :fill-pointer 0))) | |
(dotimes (i +main-set-length+) | |
(vector-push (random 1000) *set*)) | |
(return-from create-first-set *set*))) | |
(defun get-subset (set) | |
(let ((*subset* (make-array +subset-length+ :fill-pointer 0))) | |
(dotimes (i +subset-length+) | |
(vector-push (elt set (random +main-set-length+)) *subset*)) | |
(return-from get-subset *subset*))) | |
(defun get-subsets (set) | |
(let ((*subsets* (make-array +subsets-quantity+ :fill-pointer 0))) | |
(dotimes (i +subsets-quantity+) | |
(vector-push (get-subset set) *subsets*)) | |
(return-from get-subsets *subsets*))) | |
(defun sets-intersection (first-set second-set) | |
(remove () | |
(map 'vector | |
(lambda (item) | |
(find item second-set)) | |
first-set))) | |
(defun jaccard-index (first-set second-set) | |
(let ((isection (sets-intersection first-set second-set))) | |
(/ (length (sets-intersection first-set second-set)) | |
(+ (length first-set) | |
(length second-set) | |
(- (length (sets-intersection first-set second-set))))))) | |
(defvar *sets* (get-subsets (create-first-set))) | |
(dotimes (i +subsets-quantity+) | |
(do ((j i (1+ j))) | |
((>= i +subsets-quantity+)) | |
(format t | |
"~D ~D ~F~%" | |
i j | |
(jaccard-index (elt *sets* i) | |
(elt *sets* j))))) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment