Created
April 11, 2012 07:35
-
-
Save alistairtucker/2357604 to your computer and use it in GitHub Desktop.
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
(ns twitter.edfringe | |
(:require [clojure.java.io :as jio]) | |
(:require [clojure.contrib.io :as cio]) | |
(:require [clojure.contrib.json :as json])) | |
(def dir-name "/Users/ali/twitter/#edfringe") | |
(defn out-files [dir-name] | |
(let [dir (jio/file dir-name)] | |
(map #(str (jio/file dir %)) | |
(sort (filter #(.startsWith % "out") (.list dir)))))) | |
(defn tweet-seq [dir-name] | |
(map json/read-json | |
(mapcat #(with-open [r (jio/reader %)] (doall (line-seq r))) | |
(out-files dir-name)))) | |
(defn parse-status [s] | |
{:created-at (:created-at s) | |
:user-id (get-in s [:user :id]) | |
:wave-id (if-let [r (:retweeted-status s)] (:id r) (:id s))}) | |
(defn id-map [id-coll] | |
(reduce (fn [m i] (assoc m i (inc (count m)))) | |
{} | |
(into (sorted-set) id-coll))) | |
(defn transformed-seq [dir-name] | |
(let [raw-seq (map parse-status (tweet-seq dir-name)) | |
user-id-map (id-map (map :user-id raw-seq)) | |
wave-id-map (id-map (map :wave-id raw-seq))] | |
(for [j raw-seq] | |
{:created-at (:created-at j) | |
:user-id (user-id-map (:user-id j)) | |
:wave-id (wave-id-map (:wave-id j))}))) | |
(cio/with-out-writer "/Users/ali/Documents/MATLAB/tuwittuwu/edfringe3.txt" | |
(doseq [j (transformed-seq dir-name)] (println (:created-at j) (:user-id j) (:wave-id j)))) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment