Averaging values and getting standard devs from database to build graph - sql

Question

Tricky to Explain so Ill shrink down the info to a minimum:
But first, I'll try and explain my ultimate goal, I want to take users who trialed a product and determine how that product affected a value as a percentage compared to their average baseline and then average all these percentages with stand devs.
I have database with the a table that has a user_id, a value, a date.
user_id
value
date
int
int
int in epoch miliseconds
I then have a second table which indicates when a trial began and ends for a user and the product they are using for said trial.
user_id
start_date
end_date
product id
int
int in epoch milisecs
int in epoch milisecs
int
What I want to do is gather all the user's trials for one product type, and for each user that participated get a baseline value and their percent change each day. Then take all these percentages and average them and get a standard deviation for each day.
One problem is date needs to convert to days since start_date so anything between the start date and the first 24 hrs will be lumped as day 0, next 24 as day 1, and so forth. So ill be averaging the percents of each day
Not every day was recorded for each user so some will have multiple missing days, so I cant need to mark each day as days from start
The start_date's are random between users
So the graph will look like this:
picture
I would prefer to do as much of it in sql as possible, but the rest will be in Golang.
I was thinking about grabbing each trial , and then each trial will have an array of results. so then I iterate over each trial and iteriate over the results for each trial picking day 0, day 1, day 2 and saving these in their own arrays which I will then average. Everything start getting super messy though
such as in semi pseudo code:
db.Query("select user_id, start_date from trials where product_id = $1", productId).Scan(&trial.UserId, &trial.StartDate)
//extract trials from rows
for _, trial := range trials {
// extract leadingAvgStart from StartDate
db.QueryRow("select AVG(value) from results where user_id = $1 date between $2 and $3", trial.UserId, leadingAvgStart, trial.StartDate)
// Now we have the baseline for the user
rows := db.Query("select value, date from results where product_id = $1", start)
//Now we extract the results and have and array
//Convert Dates to Dates from start Date
//...? It just start getting ugly and I believe there has to be a better way
}
How can I do most of the heavy lifting with sql?
create table users (id int PRIMARY KEY, name text);
create table products (id int PRIMARY KEY, name text);
create table values (
id int PRIMARY KEY
, user_id int REFERENCES users(id)
, value int
, date numeric
);
create table trials (
id int PRIMARY KEY
, user_id int REFERENCES users(id)
, start_date numeric
, end_date numeric
, product_id int REFERENCES products(id)
);
INSERT INTO users (id, name ) VALUES
(1,'John'),
(2,'Jane'),
(3,'Billy'),
(4,'Miranda');
INSERT INTO products (id, name ) VALUES
(1, 'pill A'),
(2, 'pill B'),
(3, 'pill C'),
(4, 'exercise bal'),
(5, 'diet plan');
INSERT INTO trials (id,user_id,start_date,end_date,product_id) VALUES
(1, 1, 1667896408000, 1668099442000, 1),
(2, 1, 1667896408000, 1668099442000, 2),
(3, 2, 1667576960000, 1668074401000, 3),
(4, 3, 1667896408000, 1668099442000, 1);
INSERT INTO values (id, user_id, value, date) VALUES
(38, 1, 7, 1668182428000),
(1, 1, 7, 1668099442000),
(2, 1, 8, 1668074401000),
(3, 1, 8, 1668012300000),
(4, 1, 6, 1668011197000),
(5, 1, 6, 1667978268000),
(6, 1, 9, 1667925002000),
(7, 1, 9, 1667896408000),
(8, 1, 4, 1667838601000),
(9, 1, 6, 1667803049000),
(10, 1, 7, 1667576960000),
(12, 1, 5, 1667546428000),
(13, 1, 8, 1667490149000),
(14, 2, 8, 1668182428000),
(15, 2, 7, 1668099442000),
(16, 2, 8, 1668074401000),
(17, 2, 9, 1668012300000),
(18, 2, 6, 1668011197000),
(19, 2, 6, 1667978268000),
(20, 2, 5, 1667925002000),
(21, 2, 9, 1667896408000),
(22, 2, 4, 1667803049000),
(23, 2, 4, 1667576960000),
(24, 2, 5, 1667546428000),
(25, 2, 9, 1667490149000),
(26, 3, 6, 1668182428000),
(27, 3, 7, 1668099442000),
(28, 3, 8, 1668074401000),
(29, 3, 9, 1668011197000),
(30, 3, 6, 1667978268000),
(31, 3, 9, 1667925002000),
(32, 3, 9, 1667896408000),
(33, 3, 8, 1667838601000),
(34, 3, 6, 1667803049000),
(35, 3, 4, 1667576960000),
(36, 3, 5, 1667546428000),
(37, 3, 6, 1667490149000);

Answer 1

Ok I figures it out, basically I do two inner join queries and treat those as tables and then inner join those, and use a group by to average
select
query1.product_uuid,
query1.days,
AVG(query1.value / query2.avg) as avg_percent
from
(
select
DATE_PART(
'day',
to_timestamp(
values
.date / 1000
):: date - trials.start_date
) as days,
trials.uuid as trial_uuid,
trials.product_uuid,
values
.value as value
from
values
as
values
inner join product_trials as trials ON
values
.user_id = trials.user_id
where
values
.source = 'Trued'
and
values
.use = 'true'
AND trials.start_date IS NOT NULL
AND trials.end_date IS NOT NULL
AND to_timestamp(
values
.date / 1000
):: date > trials.start_date
AND to_timestamp(
values
.date / 1000
):: date < trials.end_date
) as query1
inner join (
select
values
.user_id,
trials.uuid as trial_uuid,
AVG(value)
from
values
inner join product_trials as trials ON
values
.user_id = trials.user_id
where
source = 'Trued'
and use = true
AND trials.start_date IS NOT NULL
AND trials.end_date IS NOT NULL
AND to_timestamp(
values
.date / 1000
):: date < trials.start_date
AND DATE_PART(
'day',
to_timestamp(
values
.date / 1000
):: date - trials.start_date
) > -20
GROUP BY
values
.user_id,
trials.uuid
) as query2 ON query1.trial_uuid = query2.trial_uuid
where
query2.avg > 0
GROUP BY
query1.days,
query1.product_uuid
ORDER BY
query1.product_uuid,
query1.days