hive 使用脚本清洗数据：时间戳转日期

import sys
import datetime

for line in sys.stdin:
  line = line.strip()
  userid, movieid, rating, unixtime = line.split('\t')
  weekday = datetime.datetime.fromtimestamp(float(unixtime)).isoweekday()
  print '\t'.join([userid, movieid, rating, str(weekday)])

Use the mapper script:

CREATE TABLE u_data_new (
  userid INT,
  movieid INT,
  rating INT,
  weekday INT)
ROW FORMAT DELIMITED
FIELDS TERMINATED BY '\t';

add FILE weekday_mapper.py;

INSERT OVERWRITE TABLE u_data_new
SELECT
  TRANSFORM (userid, movieid, rating, unixtime)
  USING 'python weekday_mapper.py'
  AS (userid, movieid, rating, weekday)
FROM u_data;

SELECT weekday, COUNT(*)
FROM u_data_new
GROUP BY weekday;

1. FROM (
2. MAP doctext USING 'python wc_mapper.py' AS (word, cnt)
3. FROM docs
4. CLUSTER BY word
5. ) a
6. REDUCE word, cnt USING 'python wc_reduce.py';