pig - pages p/min

gistfile1.txt

-- Job to count the number of logged requests p/min

record = load '12_ip-10-226-85-155.processed/part-r-00000' using PigStorage();

projected = foreach record generate
    REGEX_EXTRACT((chararray)$1, '(.*)\\:(.*)', 1) as time
    ;

group_by_minute = group projected by (time);

ppm = foreach group_by_minute generate group,
        COUNT(projected.time) as count;

store ppm into '12_ip-10-226-85-155.a' using PigStorage();