Complex query analyzing historical records - sql

Question

I am using Oracle and trying to retrieve the total number of days a person was out of the office during the year. I have 2 tables involved:
Statuses
1 - Active
2 - Out of the Office
3 - Other
ScheduleHistory
RecordID - primary key
PersonID
PreviousStatusID
NextStatusID
DateChanged
I can easily find when the person went on vacation and when they came back, using
SELECT DateChanged FROM ScheduleHistory WHERE PersonID=111 AND NextStatusID = 2
and
SELECT DateChanged FROM ScheduleHistory WHERE PersonID=111 AND PreviousStatusID = 2
But in case a person went on vacation more than once, how can I can I calculate total number of days a person was out of the office. Is it possible to do programmatically, given only PersonID?
Here is some sample data:
RecordID PersonID PreviousStatusID NextStatusID DateChanged
-----------------------------------------------------------------------------
1 111 1 2 03/11/2020
2 111 2 1 03/13/2020
3 111 1 3 04/01/2020
4 111 3 1 04/07/2020
5 111 1 2 06/03/2020
6 111 2 1 06/05/2020
7 111 1 2 09/14/2020
8 111 2 1 09/17/2020
So from the data above, for the year 2020 for PersonID 111 the query should return 7

Answer 1

Try this:
with aux1 AS (
SELECT
a.*,
to_date(datechanged, 'MM/DD/YYYY') - LAG(to_date(datechanged, 'MM/DD/YYYY')) OVER(
PARTITION BY personid
ORDER BY
recordid
) lag_date
FROM
ScheduleHistory a
)
SELECT
personid,
SUM(lag_date) tot_days_ooo
FROM
aux1
WHERE
previousstatusid = 2
GROUP BY
personid;

Answer 2

If you want total days (or weekdays) for each year (and to account for periods when it goes over the year boundary) then:
WITH date_ranges ( personid, status, start_date, end_date ) AS (
SELECT personid,
nextstatusid,
datechanged,
LEAD(datechanged, 1, datechanged) OVER(
PARTITION BY personid
ORDER BY datechanged
)
FROM table_name
),
split_year_ranges ( personid, year, start_date, end_date, max_date ) AS (
SELECT personid,
TRUNC( start_date, 'YY' ),
start_date,
LEAST(
end_date,
ADD_MONTHS( TRUNC( start_date, 'YY' ), 12 )
),
end_date
FROM date_ranges
WHERE status = 2
UNION ALL
SELECT personid,
end_date,
end_date,
LEAST( max_date, ADD_MONTHS( end_date, 12 ) ),
max_date
FROM split_year_ranges
WHERE end_date < max_date
)
SELECT personid,
EXTRACT( YEAR FROM year) AS year,
SUM( end_date - start_date ) AS total_days,
SUM(
( TRUNC( end_date, 'IW' ) - TRUNC( start_date, 'IW' ) ) * 5 / 7
+ LEAST( end_date - TRUNC( end_date, 'IW' ), 5 )
- LEAST( start_date - TRUNC( start_date, 'IW' ), 5 )
) AS total_weekdays
FROM split_year_ranges
GROUP BY personid, year
ORDER BY personid, year
Which, for the sample data:
CREATE TABLE table_name ( RecordID, PersonID, PreviousStatusID, NextStatusID, DateChanged ) AS
SELECT 1, 111, 1, 2, DATE '2020-03-11' FROM DUAL UNION ALL
SELECT 2, 111, 2, 1, DATE '2020-03-13' FROM DUAL UNION ALL
SELECT 3, 111, 1, 3, DATE '2020-04-01' FROM DUAL UNION ALL
SELECT 4, 111, 3, 1, DATE '2020-04-07' FROM DUAL UNION ALL
SELECT 5, 111, 1, 2, DATE '2020-06-03' FROM DUAL UNION ALL
SELECT 6, 111, 2, 1, DATE '2020-06-05' FROM DUAL UNION ALL
SELECT 7, 111, 1, 2, DATE '2020-09-14' FROM DUAL UNION ALL
SELECT 8, 111, 2, 1, DATE '2020-09-17' FROM DUAL UNION ALL
SELECT 9, 222, 1, 2, DATE '2019-12-31' FROM DUAL UNION ALL
SELECT 10, 222, 2, 2, DATE '2020-12-01' FROM DUAL UNION ALL
SELECT 11, 222, 2, 2, DATE '2021-01-02' FROM DUAL;
Outputs:
PERSONID
YEAR
TOTAL_DAYS
TOTAL_WEEKDAYS
111
2020
7
7
222
2019
1
1
222
2020
366
262
222
2021
1
1
db<>fiddle here

Answer 3

Provided no vacation crosses a year boundary
with grps as (
SELECT sh.*,
row_number() over (partition by PersonID, NextStatusID order by DateChanged) grp
FROM ScheduleHistory sh
WHERE NextStatusID in (1,2) and 3 not in (NextStatusID, PreviousStatusID)
), durations as (
SELECT PersonID, min(DateChanged) DateChanged, max(DateChanged) - min(DateChanged) duration
FROM grps
GROUP BY PersonID, grp
)
SELECT PersonID, sum(duration) days_out
FROM durations
GROUP BY PersonID;
db<>fiddle

Answer 4

year_span is used to split an interval spanning across two years in two different records
H1 adds a row number dependent from PersonID to get the right sequence for each person
H2 gets the periods for each status change and extract 1st day of the year of the interval end
H3 split records that span across two years and calculate the right date_start and date_end for each interval
H calculates days elapsed in each interval for each year
final query sum up the records to get output
EDIT
If you need workdays instead of total days, you should not use total_days/7*5 because it is a bad approximation and in some cases gives weird results.
I have posted a solution to jump on fridays to mondays here
with
statuses (sid, sdescr) as (
select 1, 'Active' from dual union all
select 2, 'Out of the Office' from dual union all
select 3, 'Other' from dual
),
ScheduleHistory(RecordID, PersonID, PreviousStatusID, NextStatusID , DateChanged) as (
select 1, 111, 1, 2, date '2020-03-11' from dual union all
select 2, 111, 2, 1, date '2020-03-13' from dual union all
select 3, 111, 1, 3, date '2020-04-01' from dual union all
select 4, 111, 3, 1, date '2020-04-07' from dual union all
select 5, 111, 1, 2, date '2020-06-03' from dual union all
select 6, 111, 2, 1, date '2020-06-05' from dual union all
select 7, 111, 1, 2, date '2020-09-14' from dual union all
select 8, 111, 2, 1, date '2020-09-17' from dual union all
SELECT 9, 222, 1, 2, date '2019-12-31' from dual UNION ALL
SELECT 10, 222, 2, 2, date '2020-12-01' from dual UNION ALL
SELECT 11, 222, 2, 2, date '2021-01-02' from dual
),
year_span (n) as (
select 1 from dual union all
select 2 from dual
),
H1 AS (
SELECT ROW_NUMBER() OVER (PARTITION BY PersonID ORDER BY RecordID) PID, H.*
FROM ScheduleHistory H
),
H2 as (
SELECT
H1.*, H2.DateChanged DateChanged2,
EXTRACT(YEAR FROM H2.DateChanged) - EXTRACT(YEAR FROM H1.DateChanged) + 1 Y,
trunc(H2.DateChanged,'YEAR') Y2
FROM H1 H1
LEFT JOIN H1 H2 ON H1.PID = H2.PID-1 AND H1.PersonID = H2.PersonID
),
H3 AS (
SELECT Y, N, H2.PID, H2.RecordID, H2.PersonID, H2.NextStatusID,
CASE WHEN Y=1 THEN H2.DateChanged ELSE CASE WHEN N=1 THEN H2.DateChanged ELSE Y2 END END D1,
CASE WHEN Y=1 THEN H2.DateChanged2 ELSE CASE WHEN N=1 THEN Y2 ELSE H2.DateChanged2 END END D2
FROM H2
JOIN year_span N ON N.N <=Y
),
H AS (
SELECT PersonID, NextStatusID, EXTRACT(year FROM d1) Y, d2-d1 D
FROM H3
)
select PersonID, sdescr Status, Y, sum(d) d
from H
join statuses s on NextStatusID = s.sid
group by PersonID, sdescr, Y
order by PersonID, sdescr, Y
output
PersonID Status Y d
111 Active 2020 177
111 Other 2020 6
111 Out of the Office 2020 7
222 Out of the Office 2019 1
222 Out of the Office 2020 366
222 Out of the Office 2021 1
check the fiddle here