neilkod

112725 gol
82963 goal
20344 Goal
17272 Gol
14193 GOL
9626 GOAL
2862 gool
1770 ggol
1404 goll
1292 GOOOL

neilkod

112725 gol
82963 goal
20344 Goal
17272 Gol
14193 GOL
9626 GOAL
2862 gool
1770 ggol
1404 goll
1292 GOOOL

neilkod

neil-kodners-MacBook-Pro:mapReduce nkodner$ cat goals2.txt |./mapper.py |sort|./reducer.py 
3	144821
4	121345
5	5934
6	5340
7	4949
8	4178
9	4148
10	3352
11	3276

neilkod

neil-kodners-MacBook-Pro:gardenhose nkodner$ wc -l sample.201006230[789]*.json
  163684 sample.201006230700.json
  177151 sample.201006230730.json
  194996 sample.201006230800.json
  210033 sample.201006230830.json
  223665 sample.201006230900.json
  232632 sample.201006230930.json
 1202161 total
neil-kodners-MacBook-Pro:gardenhose nkodner$ ls -ltrh sample.201006230[789]*.json
-rw-r--r--  1 nkodner  staff   239M Jun 23 07:30 sample.201006230700.json

neilkod

set serverout on  size 999999 lines 300 longchunksize 500000
spool go
DECLARE
  CURSOR c_objects IS
    SELECT  table_name
         ,  constraint_name name 
         ,  'CONSTRAINT' type
      FROM  user_constraints
     WHERE  constraint_type='P'
     UNION

neilkod

{"in_reply_to_status_id":null,"text":"@mikeypmeanie aint that the truth!","favorited":false,"coordinates":null,"in_reply_to_user_id":18127635,"source":"web","geo":null,"created_at":"Wed Jun 16 04:00:00 +0000 2010","contributors":null,"place":null,"user":{"profile_text_color":"8a0000","screen_name":"nickolasmadore","time_zone":"Eastern Time (US & Canada)","url":"http://www.verynick.tumblr.com","profile_link_color":"1e1e3b","profile_background_image_url":"http://a3.twimg.com/profile_background_images/107613263/3864319148_b084a415e0.jpg","description":"Yes, my background is my dog. Meet Bentley. He is a Min Pin/Chihuahua mix. \r\n\r\nI'm currently working on my new project, NICKY RAY.\r\n\r\nONE.","statuses_count":1425,"profile_sidebar_fill_color":"ffffff","profile_background_tile":true,"contributors_enabled":false,"lang":"en","notifications":null,"created_at":"Sun Jan 25 22:59:02 +0000 2009","profile_sidebar_border_color":"fafafa","following":null,"geo_enabled":false,"followers_count":904,"protected":false,"fri

neilkod

set serverout on
/* advance_sequences.sql
   kodner, 2008
   for every sequence in user_sequences, modify the INCREMENT BY value,
   then advance the sequence once, then restore the INCREMENT BY value
   back to one.  This script can be easily modified to increment
   just a single sequnce at a time, or to change the increment by value
*/
   
DECLARE

neilkod

neil-kodners-MacBook-Pro:parsed nkodner$ ls -ltrh 20100617.txt 
-rw-r--r--  1 nkodner  staff   697M Jun 28 20:17 20100617.txt
neil-kodners-MacBook-Pro:parsed nkodner$ wc -l 20100617.txt 
 5194723 20100617.txt


neil-kodners-MacBook-Pro:parsed nkodner$ time cat 20100617.txt |awk -F\t '{print $3'}|sort|uniq -c|sort -rg > srtd.out

real	5m13.857s
user	2m53.029s

neilkod

20 Million records, about 3GB data

neil-kodners-MacBook-Pro:parsed nkodner$ time cat 2010061*.txt |awk -F\t '{print $3'}|sort|uniq -c|sort -rg > srtd.out

real	14m45.107s
user	11m14.684s
sys	0m15.476s

neil-kodners-MacBook-Pro:parsed nkodner$ time cat 2010061*.txt|wc -l
 20457105

neilkod

local laptop drive:

neil-kodners-MacBook-Pro:parsed nkodner$ time cat *.txt|wc -l
 101434582

real	4m6.528s
user	0m17.373s
sys	0m20.308s