Generating distrubted amount of records - sql

Question

I have some code that is generating parent and a random number of child records for each parent. I want there to 5 or more child records for each parent and less than 20.
I ran this several times and I seem to be getting none or very few child records in the range of 5-13.
Can someone please explain how I can get a more distributed value of child records.
If you run the last query below you will see there are no count(*) or very few for from the values 6-15.
No doubt I have a problem with my logic but I can't seem to find it. I'm also open to any new code that accomplishes the same task and produces a distributed amount of child records with an INSERT all statement.
My goal is to generate a huge amount of testing data to examine the application queries. For now I'm only generating 30 days worth.
CREATE TABLE emp_info
(
empid INTEGER,
empname VARCHAR2(50)
);
CREATE TABLE emp_attendance
(
empid INTEGER,
start_date DATE,
end_date DATE
);
INSERT ALL
-- WHEN rn=1 insert the parent record.
-- 1 will always =1 always insert a
-- child record.
WHEN rn = 1 then into emp_info (empid, empname) values (id, name)
WHEN 1 = 1 then into emp_attendance (empid, start_date, end_date)
VALUES(id, d1, d1 + DBMS_RANDOM.value (0, .75))
SELECT *
FROM
(
-- get the highest empid as start
-- so this can be run more than once.
-- if never run before start WITH 0.
WITH t AS ( SELECT nvl(max(empid), 0) maxid FROM emp_info )
SELECT CEIL(maxid + level/20) id,
CASE MOD(maxid + level, 20) WHEN 1 THEN 1 END rn,
-- create an alpha name from 3-15
-- characters in length.
DBMS_RANDOM.string('U', DBMS_RANDOM.value(3, 15)) name,
-- set the start date any where from
-- today + 30 days
TRUNC(sysdate) + DBMS_RANDOM.value (1, 30) d1,
CASE WHEN ROW_NUMBER() OVER (PARTITION BY CEIL(maxid + level/20) ORDER BY level) > 5 THEN
-- Ensure there is a minimum of
-- 5 child and a max of 20 records
-- for each parent.
--
-- Exclude first 5 records and then
-- for 6-20 records, generating
-- random number between 5-20.
-- We can then compare with any
-- number between 5-20 so that it
-- can give us any number of
-- records.
DBMS_RANDOM.value(5, 20) ELSE 5 END AS random_val
FROM t
CONNECT BY level <= 20 * 1000
)
WHERE random_val <= 19;
-- why is this where clause neeed?
SELECT empid, COUNT(*)
FROM emp_attendance
GROUP BY empid
ORDER BY empid;
EMPID COUNT(*)
1 20
2 20
3 20
4 18
5 19
6 20
7 20
8 19
9 20
10 20
11 19
……
50 20

Answer 1

Something like this should get you going.
SQL> with
2 emps as
3 ( select level empid, dbms_random.value(5,20) children from dual connect by level <= 20 ),
4 empatt as
5 ( select e.empid , x.start_date, x.start_date+dbms_random.value(0,0.75) end_date
6 from emps e,
7 lateral(
8 select
9 trunc(sysdate)+dbms_random.value(1,30) start_date
10 from dual
11 connect by level <= e.children
12 ) x
13 )
14 select empid, count(*)
15 from empatt
16 group by empid
17 order by 1;
EMPID COUNT(*)
---------- ----------
1 5
2 14
3 17
4 6
5 10
6 18
7 12
8 13
9 16
10 11
11 7
12 14
13 7
14 7
15 7
16 13
17 18
18 9
19 9
20 12

Answer 2

INSERT ALL
WHEN attendid = 1
THEN INTO emp_info (empid, empname) VALUES
(empid, dbms_random.string ( 'U', dbms_random.value (3, 15))
)
WHEN attendid <= attend_cnt
THEN INTO emp_attendance (empid, start_date, end_date) VALUES
(empid, start_date, start_date + dbms_random.value (0, .75))
WITH got_maxid AS
(
SELECT NVL (MAX (empid), 0) AS maxid
FROM emp_info
)
, new_emps AS
(
SELECT maxid + CEIL (LEVEL / 50) AS empid
, MOD (LEVEL, 50) + 1 AS attendid,
CASE
WHEN MOD (LEVEL, 50) = 0
THEN dbms_random.value (5, 50+ 1)
END AS attend_cnt0
FROM got_maxid
CONNECT BY LEVEL <= 2000
)
SELECT n.*,
MIN (attend_cnt0) OVER (PARTITION BY empid) AS attend_cnt,
TRUNC (SYSDATE) + dbms_random.value (5, 30) AS start_date
FROM new_emps n;