Hive - lshhhhh/note GitHub Wiki
SELECT col1, CONCAT_WS(',', COLLECT_SET(col2))
FROM table
GROUP BY col1;
SELECT *
FROM table
DISTRIBUTE BY RAND()
SORT BY RAND()
LIMIT 100000;
SELECT col1, CONCAT_WS(',', COLLECT_SET(col2))
FROM table
GROUP BY col1;
SELECT *
FROM table
DISTRIBUTE BY RAND()
SORT BY RAND()
LIMIT 100000;