hive> create table user_foods (user_id  string, food_type string, datetime string
)  partitioned by(dt string) ROW FORMAT DELIMITED 
FIELDS TERMINATED BY '\t' LINES TERMINATED BY '\n' STORED AS TEXTFILE

# partitioned by(dt string) ÒÔÈÕÆÚ·ÖÇø
# бÌ岿·Ö±íʾÐÐÓëÐÐÖ®¼äÒÔ\n·Ö¸ô, ×Ö¶ÎÓë×ֶμäÒÔ\t·Ö¸ô.

hive> ALTER TABLE user_foods ADD PARTITION(dt='2014-06-07');

user_1	food1	2014-06-07 09:00
user_1	food1	2014-06-07 09:02
user_1	food2	2014-06-07 09:00
user_2	food2	2014-06-07 09:00
user_2	food23	2014-06-07 09:00

hive> LOAD DATA LOCAL INPATH '/Users/life/Desktop/data.txt' 
OVERWRITE INTO TABLE user_foods PARTITION(dt='2014-06-07');

hive> select * from user_foods where user_id='user_1'

hive> select user_id, food_type, count(*) from user_foods where dt='2014-06-07' group by user_id, food_type;

#!/usr/bin/env python
#encoding=utf-8

import sys

if __name__=="__main__":

# ½âÎöÿһÐÐÊý¾Ý
for line in sys.stdin:
# ÂÔ¹ý¿ÕÐÐ
if not line or not line.strip():
continue

# ÕâÀïÓÃtry ±ÜÃâÌØÊâÐнâÎö´íÎóµ¼ÖÂÈ«²¿³ö´í
try:
userId, foodType, dt = line.strip().split("\t")
except:
continue

# ÇåÏ´Êý¾Ý, ¿ÕÊý¾ÝÂÔ¹ý
if userId == '' or foodType == '':
continue

# ÇåÏ´Êý¾Ý
if(foodType == "food23"):
foodType = "food2"

# Êä³ö, ÒÔ\t·Ö¸ô, ¼´mapµÄÊä³ö
print userId + "\t" + foodType

hive> add file /Users/life/Desktop/m.py;
hive> select user_id, food_type, count(*) from (
select transform (user_id, food_type, datetime) using 'python m.py' as (user_id, food_type)
from user_foods where dt='2014-06-07'
) tmp group by user_id, food_type;

$> cat data.txt | python m.py
user_1	food1
user_1	food1
user_1	food2
user_2	food2
user_2	food2