SQL: How to create a weekly user count summary by month - sql

Question

I’m trying to create a week over week active user count summary report/table aggregated by month. I have one table for June 2017 and one table for May 2016 which I need to join together in order to. The date timestamp is created_utc which is a UNIX timestamp which I can figure out to transform into a human-readable format and from there extract the week of the year value so 1 through 52. The questions I have are:
Number the weeks just by values of 1 through 4. So, week 1 for June, Week 1 for May, Week 2 for June week 2 for May and so on.
Joining the tables based by those weeks 1 through 4 values
Pivoting the table and adding a WOW Change variable.
I'd like the final table to look like this:
W
| Week | June_count | May_count |WOW_Change |
|:-----------|:-----------:|:------------:|:----------:
| Week_1 | 5 | 8 | 0.6 |
| Week_2 | 2 | 1 | -0.5 |
| Week_3 | 10 | 5 | -0.5 |
| Week_4 | 30 | 6 | 1 |
Below is some sample data as well as the code I've started.
CREATE TABLE June
(created_utc int, id varchar(6))
;
INSERT INTO June
(created_utc, userid)
VALUES
(1496354167, '6eq4xf'),
(1496362973, '6eqzz3'),
(1496431934, '6ewlm8'),
(1496870877, '6fwied'),
(1496778080, '6fo79k'),
(1496933893, '6g1gcg'),
(1497154559, '6gjkid'),
(1497618561, '6hmeud'),
(1497377349, '6h1osm'),
(1497221017, '6god73'),
(1497731470, '6hvmic'),
(1497273130, '6gs4ay'),
(1498080798, '6ioz8q'),
(1497769316, '6hyer4'),
(1497415729, '6h5cgu'),
(1497978764, '6iffwq')
;
CREATE TABLE May
(created_utc int, id varchar(6))
;
INSERT INTO May
(created_utc, userid)
VALUES
(1493729491, '68sx7k'),
(1493646801, '68m2s2'),
(1493747285, '68uohf'),
(1493664087, '68ntss'),
(1493690759, '68qe5k'),
(1493829196, '691fy9'),
(1493646344, '68m1dv'),
(1494166859, '69rhkl'),
(1493883023, '6963qb'),
(1494362328, '6a83wv'),
(1494525998, '6alv6c'),
(1493945230, '69bkhb'),
(1494050355, '69jqtz'),
(1494418011, '6accd0'),
(1494425781, '6ad0xm'),
(1494024697, '69hx2z'),
(1494586576, '6aql9y')
;
#standardSQL
SELECT created_utc,
DATE(TIMESTAMP_SECONDS(created_utc)) as event_date,
CAST(EXTRACT(WEEK FROM TIMESTAMP_SECONDS(created_utc)) AS STRING) AS week_number,
COUNT(distinct userid) as user_count
FROM June
SELECT created_utc,
DATE(TIMESTAMP_SECONDS(created_utc)) as event_date,
CAST(EXTRACT(WEEK FROM TIMESTAMP_SECONDS(created_utc)) AS STRING) AS week_number,
COUNT(distinct userid) as user_count
FROM May

Answer 1

Below is for BigQuery Standard SQL
#standardSQL
SELECT
CONCAT('Week_', CAST(week AS STRING)) Week,
June.user_count AS June_count,
May.user_count AS May_count,
ROUND((May.user_count - June.user_count) / June.user_count, 2) AS WOW_Change
FROM (
SELECT COUNT(DISTINCT userid) user_count,
DIV(EXTRACT(DAY FROM DATE(TIMESTAMP_SECONDS(created_utc))) - 1, 7) + 1 week
FROM `project.dataset.June`
GROUP BY week
) June
JOIN (
SELECT COUNT(DISTINCT userid) user_count,
DIV(EXTRACT(DAY FROM DATE(TIMESTAMP_SECONDS(created_utc))) - 1, 7) + 1 week
FROM `project.dataset.May`
GROUP BY week
) May
USING(week)
You can test, play with above using sample data from your question as in example below
#standardSQL
WITH `project.dataset.June` AS (
SELECT 1496354167 created_utc, '6eq4xf' userid UNION ALL
SELECT 1496362973, '6eqzz3' UNION ALL
SELECT 1496431934, '6ewlm8' UNION ALL
SELECT 1496870877, '6fwied' UNION ALL
SELECT 1496778080, '6fo79k' UNION ALL
SELECT 1496933893, '6g1gcg' UNION ALL
SELECT 1497154559, '6gjkid' UNION ALL
SELECT 1497618561, '6hmeud' UNION ALL
SELECT 1497377349, '6h1osm' UNION ALL
SELECT 1497221017, '6god73' UNION ALL
SELECT 1497731470, '6hvmic' UNION ALL
SELECT 1497273130, '6gs4ay' UNION ALL
SELECT 1498080798, '6ioz8q' UNION ALL
SELECT 1497769316, '6hyer4' UNION ALL
SELECT 1497415729, '6h5cgu' UNION ALL
SELECT 1497978764, '6iffwq'
), `project.dataset.May` AS (
SELECT 1493729491 created_utc, '68sx7k' userid UNION ALL
SELECT 1493646801, '68m2s2' UNION ALL
SELECT 1493747285, '68uohf' UNION ALL
SELECT 1493664087, '68ntss' UNION ALL
SELECT 1493690759, '68qe5k' UNION ALL
SELECT 1493829196, '691fy9' UNION ALL
SELECT 1493646344, '68m1dv' UNION ALL
SELECT 1494166859, '69rhkl' UNION ALL
SELECT 1493883023, '6963qb' UNION ALL
SELECT 1494362328, '6a83wv' UNION ALL
SELECT 1494525998, '6alv6c' UNION ALL
SELECT 1493945230, '69bkhb' UNION ALL
SELECT 1494050355, '69jqtz' UNION ALL
SELECT 1494418011, '6accd0' UNION ALL
SELECT 1494425781, '6ad0xm' UNION ALL
SELECT 1494024697, '69hx2z' UNION ALL
SELECT 1494586576, '6aql9y'
)
SELECT
CONCAT('Week_', CAST(week AS STRING)) Week,
June.user_count AS June_count,
May.user_count AS May_count,
ROUND((May.user_count - June.user_count) / June.user_count, 2) AS WOW_Change
FROM (
SELECT COUNT(DISTINCT userid) user_count,
DIV(EXTRACT(DAY FROM DATE(TIMESTAMP_SECONDS(created_utc))) - 1, 7) + 1 week
FROM `project.dataset.June`
GROUP BY week
) June
JOIN (
SELECT COUNT(DISTINCT userid) user_count,
DIV(EXTRACT(DAY FROM DATE(TIMESTAMP_SECONDS(created_utc))) - 1, 7) + 1 week
FROM `project.dataset.May`
GROUP BY week
) May
USING(week)
-- ORDER BY week
with result (as sample data is limited to just first two weeks result is also showing two weeks only which should not be an issue when you apply it to real data)
Row Week June_count May_count WOW_Change
1 Week_1 5 12 1.4
2 Week_2 6 5 -0.17

Answer 2

Use arithmetic on the day of the month to get the week:
SELECT j.weeknumber, j.user_count as june_user_count,
m.user_count as may_user_count
FROM (SELECT (EXTRACT(DAY FROM DATE(TIMESTAMP_SECONDS(created_utc))) - 1) / 7 as week_number,
COUNT(distinct userid) as user_count
FROM June
GROUP BY week_number
) j JOIN
(SELECT (EXTRACT(DAY FROM DATE(TIMESTAMP_SECONDS(created_utc))) - 1) / 7 as week_number,
COUNT(distinct userid) as user_count
FROM May
GROUP BY week_number
) m
ON m.week_number = j.week_number;
Note that splitting data into different tables just based on the date is bad idea. The data should all go into one table, perhaps partitioned if data volume is an issue.