Created
November 1, 2016 15:22
-
-
Save practicalli-johnny/05941171b7514e60102aa4fe026d73b6 to your computer and use it in GitHub Desktop.
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
;; Book: The importance of being Earnest, Oscar Wilde | |
;; Source: Project Guttenburg (UTF-8 format) | |
(def importance-of-being-earnest | |
(slurp "http://www.gutenberg.org/cache/epub/844/pg844.txt")) | |
(def common-english-words | |
(set | |
(clojure.string/split | |
(slurp | |
"http://www.textfixer.com/resources/common-english-words.txt") | |
#","))) | |
(defn most-common-words [book] | |
(reverse | |
(sort-by val | |
(frequencies | |
(remove common-english-words | |
(map | |
#(clojure.string/lower-case %) | |
(re-seq #"[a-zA-Z0-9|']+" book))))))) | |
(most-common-words importance-of-being-earnest) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment