t-ob

(define atom?
  (lambda (x)
    (and (not (pair? x)) (not (null? x)))))

t-ob

(fn gcd [a b]
  (if (zero? b)
    a
    (recur b (rem a b))))

t-ob

(defn val-p-fact [n p]
  (letfn [(prime-powers [n p i]
            (lazy-seq
             (when (<= (Math/pow p i) n)
               (cons (Math/floor (/ n (Math/pow p i)))
                     (prime-powers n p (inc i))))))]
    (reduce + (prime-powers n p 1))))

(defn interview-street-equations [n]
  (int (reduce #(mod (* %1 %2) 1000007)

t-ob

(defn graph-tour [edges]
  (let [vertices (reduce #(into %1 %2) #{} edges)
        degree (fn [vertex] (count (filter #(some #{vertex} %) edges)))]
    (<= (count (filter odd? (map degree vertices))) 2)))

t-ob

(def short-urls
  [["http://t.co/yERArQn0"]
   ["http://t.co/gI8TjreI"]
   ["http://t.co/CBsucpNm"]
   ["http://t.co/F74GG1oN"]
   ["http://t.co/hyoXObbU"]])

(def longified-urls
  [["http://t.co/yERArQn0" "http://news.sky.com/story/964624/olympic-lanes-open-traffic-delays-in-london"]
   ["http://t.co/CBsucpNm" "http://media.tumblr.com/tumblr_m65uu5UsrQ1r7h1lt.gif"]

t-ob

(defn tweets
  []
  (let [scheme (HBaseScheme. (Fields. (into-array String ["id"]))
                             (into-array String ["base" "raw"])
                             (into-array [(Fields. (into-array String ["tweet_id"
                                                          "screen_name"
                                                          "content"
                                                          "created_at"
                                                          "urls"]))
                                          (Fields. (into-array String ["topsy_url"]))]))

t-ob

(defn limited-output
  [keywords-str limit]
  (let [tweets-tap (tweets-new)
        urls-tap (short-urls)
        jdbc-sink db/jdbc-tap]
    (?- (stdout)
        (c/first-n
         (<- [ ?args ]
             ; query
         limit))))

t-ob

#!/bin/bash
NOW=$(date +"%Y-%m-%d-%T")

USERS10="users-10.$NOW.csv"
EVENTS10="events-10.$NOW.csv"
USERS20="users-20.$NOW.csv"
EVENTS20="events-20.$NOW.csv"

echo $USERS10;

t-ob

import org.apache.hadoop.hbase.filter.CompareFilter
import org.apache.hadoop.hbase.filter.SingleColumnValueFilter
import org.apache.hadoop.hbase.filter.SubstringComparator
import org.apache.hadoop.hbase.util.Bytes
scan 'tweets', { COLUMNS => 'base:content', FILTER => SingleColumnValueFilter.new(Bytes.toBytes('base'),Bytes.toBytes('content'), CompareFilter::CompareOp.valueOf('EQUAL'),SubstringComparator.new('burn')) }

t-ob

select count(*), tweet_id, content, max(screen_name), max(created_at), min(screen_name), min(created_at)
from tweets_with_id
group by tweet_id
having count(*) = 2