Created
November 9, 2011 05:38
-
-
Save nathanmarz/1350522 to your computer and use it in GitHub Desktop.
Optimized variance in Cascalog
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
(defn one [] 1) | |
(defn div [v1 v2] | |
(float (/ v1 v2))) | |
(defparallelagg count | |
:init-var #'one | |
:combine-var #'+) | |
(defparallelagg sum-parallel | |
:init-var #'identity | |
:combine-var #'+) | |
(def sum (each sum-parallel)) | |
(def avg | |
(<- [!val :> !avg] | |
(count !count) | |
(sum !val :> !sum) | |
(div !sum !count :> !avg))) | |
(def variance | |
(<- [!val :> !var] | |
(* !val !val :> !squared) | |
(sum !squared :> !square-sum) | |
(count !count) | |
(avg !val :> !mean) | |
(* !mean !mean :> !mean-squared) | |
(div !square-sum !count :> !i) | |
(- !i !mean-squared :> !var))) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment