Hadoop, Pig, and SQL (GROUP BY)

gistfile1.txt

SELECT COUNT(*) FROM mytable;

mytable = GROUP mytable ALL;
mytable = FOREACH mytable GENERATE COUNT(mytable);
DUMP mytable;
SELECT COUNT(DISTINCT col1) FROM mytable;

mytable = FOREACH mytable GENERATE col1;
mytable = DISTINCT col1;
mytable = GROUP mytable BY col1;
mytable = FOREACH mytable GENERATE group AS col1, COUNT(mytable) AS cnt;
DUMP mytable;