SQL query to answer: If occurs in timepoint A, does occur in time period B-C?

Question

I\'m querying a large data set to figure out if a bunch of campaign events (i.e. event 1,2,..) during different timepoints gives a result in user activity (active, inactive) dur

Answer 1

You seem to be quite there. A range partition is the right way to go. BigQuery only supports integers in such frame, so we need to convert the date to a number; since you have dates with no time component, UNIX_DATE() comes to mind:

WINDOW 3d_later AS (
    PARTITION BY user 
    ORDER BY UNIX_DATE(cm.date) 
    RANGE BETWEEN 1 FOLLOWING AND 3 FOLLOWING
)

Answer 2

Below example is for BigQuery Standard SQL

#standardSQL
SELECT *, IF(events IS NULL, 0, COUNTIF(day_activity = 'active') OVER(three_day_activity_window)) AS three_day_activity
FROM `project.dataset.table`
WINDOW three_day_activity_window AS (
  PARTITION BY user 
  ORDER BY UNIX_DATE(date) 
  RANGE BETWEEN 1 FOLLOWING AND 3 FOLLOWING
)

You can test, play with above using sample data from your question as in below example

#standardSQL
WITH `project.dataset.table` AS (
  SELECT DATE '2020-01-01' date , 1 user, 'event1' events, 'active' day_activity UNION ALL
  SELECT '2020-01-01', 2, 'event1', 'inactive' UNION ALL
  SELECT '2020-01-02', 1, NULL, 'inactive' UNION ALL
  SELECT '2020-01-02', 2, NULL, 'active' UNION ALL
  SELECT '2020-01-03', 1, NULL, 'inactive' UNION ALL
  SELECT '2020-01-03', 2, NULL, 'active' UNION ALL
  SELECT '2020-01-04', 1, NULL, 'active' UNION ALL
  SELECT '2020-01-04', 2, NULL, 'active' 
)
SELECT *, IF(events IS NULL, 0, COUNTIF(day_activity = 'active') OVER(three_day_activity_window)) AS three_day_activity
FROM `project.dataset.table`
WINDOW three_day_activity_window AS (
  PARTITION BY user 
  ORDER BY UNIX_DATE(date) 
  RANGE BETWEEN 1 FOLLOWING AND 3 FOLLOWING
)
ORDER BY date, user   

with output

Row date        user    events  day_activity    three_day_activity   
1   2020-01-01  1       event1  active          1    
2   2020-01-01  2       event1  inactive        3    
3   2020-01-02  1       null    inactive        0    
4   2020-01-02  2       null    active          0    
5   2020-01-03  1       null    inactive        0    
6   2020-01-03  2       null    active          0    
7   2020-01-04  1       null    active          0    
8   2020-01-04  2       null    active          0       

Update for - to avoid registering the same user as active multiple times in one day (and tallying those up to a huge sum)?

If you want to avoid counting all activity for user on same day - use below adjusted version (note extra entry in sample data to introduce user's multiple activity on same day)

#standardSQL
WITH `project.dataset.table` AS (
  SELECT DATE '2020-01-01' DATE , 1 user, 'event1' events, 'active' day_activity UNION ALL
  SELECT '2020-01-01', 2, 'event1', 'inactive' UNION ALL
  SELECT '2020-01-02', 1, NULL, 'inactive' UNION ALL
  SELECT '2020-01-02', 2, NULL, 'active' UNION ALL
  SELECT '2020-01-03', 1, NULL, 'inactive' UNION ALL
  SELECT '2020-01-03', 2, NULL, 'active' UNION ALL
  SELECT '2020-01-04', 1, NULL, 'active' UNION ALL
  SELECT '2020-01-04', 1, NULL, 'active' UNION ALL
  SELECT '2020-01-04', 2, NULL, 'active' 
)
SELECT *, 
  IF(events IS NULL, 0, COUNTIF(day_activity = 'active') OVER(three_day_activity_window)) AS three_day_activity
FROM (
  SELECT date, user, MAX(events) events, MIN(day_activity) day_activity
  FROM `project.dataset.table` 
  GROUP BY date, user
)
WINDOW three_day_activity_window AS (
  PARTITION BY user 
  ORDER BY UNIX_DATE(date) 
  RANGE BETWEEN 1 FOLLOWING AND 3 FOLLOWING
)
ORDER BY date, user