Sample Hive example

sample2013.sql

insert overwrite local directory '/scratch.1/sample2013_1'
row format delimited 
fields terminated by "\t"
select id_str, created_at, regexp_replace(text, "[ \t\r\n]+", " "), user.id_str, regexp_replace(user.name, "[ \t\r\n]+", " "), user.screen_name, retweeted_status.id_str, retweeted_status.created_at, regexp_replace(retweeted_status.text, "[ \t\r\n]+", " "), retweeted_status.user.id_str, regexp_replace(retweeted_status.user.name, "[ \t\r\n]+", " "), retweeted_status.user.screen_name 
from gh_rc TABLESAMPLE (10 PERCENT)
WHERE year = 2013 and month = 1;

insert overwrite local directory '/scratch.1/sample2013_2'
row format delimited 
fields terminated by "\t"
select id_str, created_at, regexp_replace(text, "[ \t\r\n]+", " "), user.id_str, regexp_replace(user.name, "[ \t\r\n]+", " "), user.screen_name, retweeted_status.id_str, retweeted_status.created_at, regexp_replace(retweeted_status.text, "[ \t\r\n]+", " "), retweeted_status.user.id_str, regexp_replace(retweeted_status.user.name, "[ \t\r\n]+", " "), retweeted_status.user.screen_name 
from gh_rc TABLESAMPLE (10 PERCENT)
WHERE year = 2013 and month = 2;

insert overwrite local directory '/scratch.1/sample2013_3'
row format delimited 
fields terminated by "\t"
select id_str, created_at, regexp_replace(text, "[ \t\r\n]+", " "), user.id_str, regexp_replace(user.name, "[ \t\r\n]+", " "), user.screen_name, retweeted_status.id_str, retweeted_status.created_at, regexp_replace(retweeted_status.text, "[ \t\r\n]+", " "), retweeted_status.user.id_str, regexp_replace(retweeted_status.user.name, "[ \t\r\n]+", " "), retweeted_status.user.screen_name 
from gh_rc TABLESAMPLE (10 PERCENT)
WHERE year = 2013 and month = 3;

insert overwrite local directory '/scratch.1/sample2013_4'
row format delimited 
fields terminated by "\t"
select id_str, created_at, regexp_replace(text, "[ \t\r\n]+", " "), user.id_str, regexp_replace(user.name, "[ \t\r\n]+", " "), user.screen_name, retweeted_status.id_str, retweeted_status.created_at, regexp_replace(retweeted_status.text, "[ \t\r\n]+", " "), retweeted_status.user.id_str, regexp_replace(retweeted_status.user.name, "[ \t\r\n]+", " "), retweeted_status.user.screen_name 
from gh_rc TABLESAMPLE (10 PERCENT)
WHERE year = 2013 and month = 4;

insert overwrite local directory '/scratch.1/sample2013_5'
row format delimited 
fields terminated by "\t"
select id_str, created_at, regexp_replace(text, "[ \t\r\n]+", " "), user.id_str, regexp_replace(user.name, "[ \t\r\n]+", " "), user.screen_name, retweeted_status.id_str, retweeted_status.created_at, regexp_replace(retweeted_status.text, "[ \t\r\n]+", " "), retweeted_status.user.id_str, regexp_replace(retweeted_status.user.name, "[ \t\r\n]+", " "), retweeted_status.user.screen_name 
from gh_rc TABLESAMPLE (10 PERCENT)
WHERE year = 2013 and month = 5;

insert overwrite local directory '/scratch.1/sample2013_6'
row format delimited 
fields terminated by "\t"
select id_str, created_at, regexp_replace(text, "[ \t\r\n]+", " "), user.id_str, regexp_replace(user.name, "[ \t\r\n]+", " "), user.screen_name, retweeted_status.id_str, retweeted_status.created_at, regexp_replace(retweeted_status.text, "[ \t\r\n]+", " "), retweeted_status.user.id_str, regexp_replace(retweeted_status.user.name, "[ \t\r\n]+", " "), retweeted_status.user.screen_name 
from gh_rc TABLESAMPLE (10 PERCENT)
WHERE year = 2013 and month = 6;

insert overwrite local directory '/scratch.1/sample2013_7'
row format delimited 
fields terminated by "\t"
select id_str, created_at, regexp_replace(text, "[ \t\r\n]+", " "), user.id_str, regexp_replace(user.name, "[ \t\r\n]+", " "), user.screen_name, retweeted_status.id_str, retweeted_status.created_at, regexp_replace(retweeted_status.text, "[ \t\r\n]+", " "), retweeted_status.user.id_str, regexp_replace(retweeted_status.user.name, "[ \t\r\n]+", " "), retweeted_status.user.screen_name 
from gh_rc TABLESAMPLE (10 PERCENT)
WHERE year = 2013 and month = 7;

insert overwrite local directory '/scratch.1/sample2013_8'
row format delimited 
fields terminated by "\t"
select id_str, created_at, regexp_replace(text, "[ \t\r\n]+", " "), user.id_str, regexp_replace(user.name, "[ \t\r\n]+", " "), user.screen_name, retweeted_status.id_str, retweeted_status.created_at, regexp_replace(retweeted_status.text, "[ \t\r\n]+", " "), retweeted_status.user.id_str, regexp_replace(retweeted_status.user.name, "[ \t\r\n]+", " "), retweeted_status.user.screen_name 
from gh_rc2 TABLESAMPLE (10 PERCENT)
WHERE year = 2013 and month = 8;

insert overwrite local directory '/scratch.1/sample2013_9'
row format delimited 
fields terminated by "\t"
select id_str, created_at, regexp_replace(text, "[ \t\r\n]+", " "), user.id_str, regexp_replace(user.name, "[ \t\r\n]+", " "), user.screen_name, retweeted_status.id_str, retweeted_status.created_at, regexp_replace(retweeted_status.text, "[ \t\r\n]+", " "), retweeted_status.user.id_str, regexp_replace(retweeted_status.user.name, "[ \t\r\n]+", " "), retweeted_status.user.screen_name 
from gh_rc2 TABLESAMPLE (10 PERCENT)
WHERE year = 2013 and month = 9;

insert overwrite local directory '/scratch.1/sample2013_10'
row format delimited 
fields terminated by "\t"
select id_str, created_at, regexp_replace(text, "[ \t\r\n]+", " "), user.id_str, regexp_replace(user.name, "[ \t\r\n]+", " "), user.screen_name, retweeted_status.id_str, retweeted_status.created_at, regexp_replace(retweeted_status.text, "[ \t\r\n]+", " "), retweeted_status.user.id_str, regexp_replace(retweeted_status.user.name, "[ \t\r\n]+", " "), retweeted_status.user.screen_name 
from gh_rc2 TABLESAMPLE (10 PERCENT)
WHERE year = 2013 and month = 10;

insert overwrite local directory '/scratch.1/sample2013_11'
row format delimited 
fields terminated by "\t"
select id_str, created_at, regexp_replace(text, "[ \t\r\n]+", " "), user.id_str, regexp_replace(user.name, "[ \t\r\n]+", " "), user.screen_name, retweeted_status.id_str, retweeted_status.created_at, regexp_replace(retweeted_status.text, "[ \t\r\n]+", " "), retweeted_status.user.id_str, regexp_replace(retweeted_status.user.name, "[ \t\r\n]+", " "), retweeted_status.user.screen_name 
from gh_rc2 TABLESAMPLE (10 PERCENT)
WHERE year = 2013 and month = 11;

insert overwrite local directory '/scratch.1/sample2013_12'
row format delimited 
fields terminated by "\t"
select id_str, created_at, regexp_replace(text, "[ \t\r\n]+", " "), user.id_str, regexp_replace(user.name, "[ \t\r\n]+", " "), user.screen_name, retweeted_status.id_str, retweeted_status.created_at, regexp_replace(retweeted_status.text, "[ \t\r\n]+", " "), retweeted_status.user.id_str, regexp_replace(retweeted_status.user.name, "[ \t\r\n]+", " "), retweeted_status.user.screen_name 
from gh_rc2 TABLESAMPLE (10 PERCENT)
WHERE year = 2013 and month = 12;