Search for holiday doy IN (string) (Postgresql) - sql

This work:
WITH month AS (
SELECT date_part('doy',d.dt) as doy,
dt::date as date
FROM generate_series('2017-01-01','2017-01-15', interval '1 day') as d(dt)
)
SELECT date,
CASE
WHEN doy IN (1,2,3) THEN 0 ELSE 8 END
FROM month
http://sqlfiddle.com/#!15/aed15/10
But if I store 1,2,3 as a string
CREATE TABLE holidays
(id int4,days character(60));
INSERT INTO holidays
(id,days)
VALUES
('2017','1,2,3');
...and replace 1,2,3 with this string:
WITH month AS (
SELECT date_part('doy',d.dt) as doy,
dt::date as date
FROM generate_series('2017-01-01','2017-01-15', interval '1 day') as d(dt)
)
SELECT date, days,
CASE
WHEN doy::text IN (days) THEN 0 ELSE 8 END
FROM month
LEFT JOIN holidays ON id=2017
http://sqlfiddle.com/#!15/aed15/13
It seems that 'days' is not casted correct. But I cannot figure out how.
TIA,

the shortest solution here would be turning string list to array and using ANY construct:
WITH month AS (
SELECT date_part('doy',d.dt) as doy,
dt::date as date
FROM generate_series('2017-01-01','2017-01-15', interval '1 day') as d(dt)
)
SELECT date, days,
CASE
WHEN doy::text = ANY(concat('{',days,'}')::text[]) THEN 0 ELSE 8 END
FROM month
LEFT JOIN holidays ON id=2017
But I would rethink the whole solution, as it feels wrong

Related

create table with dates - sql

I have a query that can create a table with dates like below:
with digit as (
select 0 as d union all
select 1 union all select 2 union all select 3 union all
select 4 union all select 5 union all select 6 union all
select 7 union all select 8 union all select 9
),
seq as (
select a.d + (10 * b.d) + (100 * c.d) + (1000 * d.d) as num
from digit a
cross join
digit b
cross join
digit c
cross join
digit d
order by 1
)
select (last_day(sysdate)::date - seq.num)::date as "Date"
from seq;
How could this be changed to generate only dates
Thanks
demo:db<>fiddle
WITH dates AS (
SELECT
date_trunc('month', CURRENT_DATE) AS first_day_of_month,
date_trunc('month', CURRENT_DATE) + interval '1 month -1 day' AS last_day_of_month
)
SELECT
generate_series(first_day_of_month, last_day_of_month, interval '1 day')::date
FROM dates
date_trunc() truncates a type date (or timestamp) to a certain date part. date_trunc('month', ...) removes all parts but year and month. All other parts are set to their lowest possible values. So, the day part is set to 1. That's why you get the first day of month with this.
adding a month returns the first of the next month, subtracting a day from this results in the last day of the current month.
Finally you can generate a date series with start and end date using the generate_series() function
Edit: Redshift does not support generate_series() with type date and timestamp but with integer. So, we need to create an integer series instead and adding the results to the first of the month:
db<>fiddle
WITH dates AS (
SELECT
date_trunc('month', CURRENT_DATE) AS first_day_of_month,
date_trunc('month', CURRENT_DATE) + interval '1 month -1 day' AS last_day_of_month
)
SELECT
first_day_of_month::date + gs
FROM
dates,
generate_series(
date_part('day', first_day_of_month)::int - 1,
date_part('day', last_day_of_month)::int - 1
) as gs
This answers the original version of the question.
You would use generate_series():
select gs.dte
from generate_series(date_trunc('month', now()::date),
date_trunc('month', now()::date) + interval '1 month' - interval '1 day',
interval '1 day'
) gs(dte);
Here is a db<>fiddle.

Customizing the range of a week with date_trunc

I've been trying for hours now to write a date_trunc statement to be used in a group by where my week starts on a Friday and ends the following Thursday.
So something like
SELECT
DATE_TRUNC(...) sales_week,
SUM(sales) sales
FROM table
GROUP BY 1
ORDER BY 1 DESC
Which would return the results for the last complete week (by those standards) as 09-13-2019.
You can subtract 4 days and then add 4 days:
SELECT DATE_TRUNC(<whatever> - INTERVAL '4 DAY') + INTERVAL '4 DAY' as sales_week,
SUM(sales) as sales
FROM table
GROUP BY 1
ORDER BY 1 DESC
The expression
select current_date - cast(cast(7 - (5 - extract(dow from current_date)) as text) || ' days' as interval);
should always give you the previous Friday's date.
if by any chance you might have gaps in data (maybe more granular breakdowns vs just per week), you can generate a set of custom weeks and left join to that:
drop table if exists sales_weeks;
create table sales_weeks as
with
dates as (
select generate_series('2019-01-01'::date,current_date,interval '1 day')::date as date
)
,week_ids as (
select
date
,sum(case when extract('dow' from date)=5 then 1 else 0 end) over (order by date) as week_id
from dates
)
select
week_id
,min(date) as week_start_date
,max(date) as week_end_date
from week_ids
group by 1
order by 1
;

PostgreSQL generate month and year series based on table field and fill with nulls if no data for a given month

I want to generate series of month and year from the next month of current year(say, start_month) to 12 months from start_month along with the corresponding data (if any, else return nulls) from another table in PostgreSQL.
SELECT ( ( DATE '2019-03-01' + ( interval '1' month * generate_series(0, 11) ) )
:: DATE ) dd,
extract(year FROM ( DATE '2019-03-01' + ( interval '1' month *
generate_series(0, 11) )
)),
coalesce(SUM(price), 0)
FROM items
WHERE s.date_added >= '2019-03-01'
AND s.date_added < '2020-03-01'
AND item_type_id = 3
GROUP BY 1,
2
ORDER BY 2;
The problem with the above query is that it is giving me the same value for price for all the months. The requirement is that the price column be filled with nulls or zeros if no price data is available for a given month.
Put the generate_series() in the FROM clause. You are summarizing the data -- i.e. calculating the price over the entire range -- and then projecting this on all months. Instead:
SELECT gs.yyyymm,
coalesce(SUM(i.price), 0)
FROM generate_series('2019-03-01'::date, '2020-02-01', INTERVAL '1 MONTH'
) gs(yyyymm) LEFT JOIN
items i
ON gs.yyyymm = DATE_TRUNC('month', s.date_added) AND
i.item_type_id = 3
GROUP BY gs.yyyymm
ORDER BY gs.yyyymm;
You want generate_series in the FROM clause and join with it, somewhat like
SELECT months.m::date, ...
FROM generate_series(
start_month,
start_month + INTERVAL '11 months',
INTERVAL '1 month'
) AS months(m)
LEFT JOIN items
ON months.m::date = items.date_added

update table with dates with month

There's a table dates_calendar:
id | date
-------------------------
13 | 2016-10-23 00:00:00
14 | 2016-10-24 00:00:00
I need to update this table and insert dates until the next month counting from the last date in the table. E.g. last date is 2016-10-24 00:00:00 - I need to insert dates till 2016-10-31. After that (the last date now is 2016-10-31) next statement call should insert dates till 2016-11-30 and so on.
Example of my SQL code, but it inserts 30 days all the time.
INSERT INTO dates_calendar (date)
VALUES (
generate_series(
(SELECT date FROM dates_calendar ORDER BY date DESC LIMIT 1) + interval '1 day',
(SELECT date FROM dates_calendar ORDER BY date DESC LIMIT 1) + interval '1 month',
'1 day'
)
);
I'm using PostgreSQL. As well would be fine to get rid of a duplicated SELECT statement of the last date.
insert into dates_calendar (date)
select dates::date
from (
select max(date)::date+ 1 next_day, '1day'::interval one_day, '1month'::interval one_month
from dates_calendar
) s,
generate_series(
next_day,
date_trunc('month', next_day)+ one_month- one_day,
one_day) dates;
To calculate the first and last date you need to insert you can use this query:
select max(date) + interval '1' day as first_day,
date_trunc('month', max(date) + interval '1' month) - interval '1' day as last_day
from dates_calendar
The expression date_trunc('month', max(date) + interval '1' month) calculates the start date of the next month. Subtracting one day from that will give you the last day of that month.
This can then be used to generate the list of dates:
with from_to (first_day, last_day) as (
select max(date) + interval '1' day,
date_trunc('month', max(date) + interval '1' month) - interval '1' day
from dates_calendar
)
select dt
from generate_series( (select first_day from from_to), (select last_day from from_to), interval '1' day) as t(dt);
And finally this can be used to insert the generated rows into the table:
with from_to (first_day, last_day) as (
select max(date) + interval '1' day,
date_trunc('month', max(date) + interval '1' month) - interval '1' day
from dates_calendar
)
insert into dates_calendar (date)
select dt
from generate_series( (select first_day from from_to), (select last_day from from_to), interval '1' day) as t(dt);
with max_date (d) as (select max(date)::date from dates_calendar)
insert into dates_calendar (date)
select d
from generate_series (
(select d from max_date) + 1,
(select date_trunc('month', d + interval '1 month')::date - 1 from max_date),
'1 day'
) g(d)

Weekly total sums

I have a table in a PostgreSQL database containing dates and a total count per day.
mydate total
2012-05-12 12
2012-05-14 8
2012-05-13 4
2012-05-12 12
2012-05-15 2
2012-05-17 1
2012-05-18 1
2012-05-21 1
2012-05-25 1
Now I need to get the weekly totals for a given date range.
Ex. I want to get the weekly totals from 2012-05-01 up to 2012-05-31.
I'm looking at this output:
2012-05-01 2012-05-07 0
2012-05-08 2012-05-14 36
2012-05-15 2012-05-22 5
2012-05-23 2012-05-29 1
2012-05-30 2012-05-31 0
This works for any given date range:
CREATE FUNCTION f_tbl_weekly_sumtotals(_range_start date, _range_end date)
RETURNS TABLE (week_start date, week_end date, sum_total bigint)
LANGUAGE sql AS
$func$
SELECT w.week_start, w.week_end, COALESCE(sum(t.total), 0)
FROM (
SELECT week_start::date, LEAST(week_start::date + 6, _range_end) AS week_end
FROM generate_series(_range_start::timestamp
, _range_end::timestamp
, interval '1 week') week_start
) w
LEFT JOIN tbl t ON t.mydate BETWEEN w.week_start and w.week_end
GROUP BY w.week_start, w.week_end
ORDER BY w.week_start
$func$;
Call:
SELECT * FROM f_tbl_weekly_sumtotals('2012-05-01', '2012-05-31');
Major points
I wrapped it in a function for convenience, so the date range has to be provided once only.
The subquery w produces the series of weeks starting from the first day of the given date range. The upper bound is capped with LEAST to stay within the upper bound of the given date range.
Then LEFT JOIN to the data table (tbl in my example) to keep all weeks in the result, even where no data rows are found.
The rest should be obvious. COALESCE to output 0 instead of NULL for empty weeks.
Data types have to match, I assumed mydate date and total int for lack of information. (The sum() of an int is bigint.)
Explanation for my particular use of generate_series():
Generating time series between two dates in PostgreSQL
Using this function
CREATE OR REPLACE FUNCTION last_day(date)
RETURNS date AS
$$
SELECT (date_trunc('MONTH', $1) + INTERVAL '1 MONTH - 1 day')::date;
$$ LANGUAGE 'sql' IMMUTABLE STRICT;
AND generate_series (from 8.4 onwards) we can create the date partitions.
SELECT wk.wk_start,
CAST(
CASE (extract(month from wk.wk_start) = extract(month from wk.wk_start + interval '6 days'))
WHEN true THEN wk.wk_start + interval '6 days'
ELSE last_day(wk.wk_start)
END
AS date) AS wk_end
FROM
(SELECT CAST(generate_series('2012-05-01'::date,'2012-05-31'::date,interval '1 week') AS date) AS wk_start) AS wk;
Then putting it together with the data
CREATE TABLE my_tab(mydate date,total integer);
INSERT INTO my_tab
values
('2012-05-12'::date,12),
('2012-05-14'::date,8),
('2012-05-13'::date,4),
('2012-05-12'::date,12),
('2012-05-15'::date,2),
('2012-05-17'::date,1),
('2012-05-18'::date,1),
('2012-05-21'::date,1),
('2012-05-25'::date,1);
WITH month_by_week AS
(SELECT wk.wk_start,
CAST(
CASE (extract(month from wk.wk_start) = extract(month from wk.wk_start + interval '6 days'))
WHEN true THEN wk.wk_start + interval '6 days'
ELSE last_day(wk.wk_start)
END
AS date) AS wk_end
FROM
(SELECT CAST(generate_series('2012-05-01'::date,'2012-05-31'::date,interval '1 week') AS date) AS wk_start) AS wk
)
SELECT month_by_week.wk_start,
month_by_week.wk_end,
SUM(COALESCE(mt.total,0))
FROM month_by_week
LEFT JOIN my_tab mt ON mt.mydate BETWEEN month_by_week.wk_start AND month_by_week.wk_end
GROUP BY month_by_week.wk_start,
month_by_week.wk_end
ORDER BY month_by_week.wk_start;