Snowflake SQL - OBJECT_CONSTRUCT from COUNT and GROUP BY - sql

Question

I'm trying to summarize data in a table:
counting total rows
counting values on specific fields
getting the distinct values on specific fields
and, more importantly, I'm struggling with:
getting the count for each field nested in an object
given this data
COL1
COL2
A
0
null
1
B
null
B
null
the expected result from this query would be:
with dummy as (
select 'A' as col1, 0 as col2
union all
select null, 1
union all
select 'B', null
union all
select 'B', null
)
select
count(1) as total
,count(col1) as col1
,array_agg(distinct col1) as dist_col1
--,object_construct(???) as col1_object_count
,count(col2) as col2
,array_agg(distinct col2) as dist_col2
--,object_construct(???) as col2_object_count
from
dummy
TOTAL
COL1
DIST_COL1
COL1_OBJECT_COUNT
COL2
DIST_COL2
COL2_OBJECT_COUNT
4
3
["A", "B"]
{"A": 1, "B", 2, null: 1}
2
[0, 1]
{0: 1, 1: 1, null: 2}
I've tried several functions inside OBJECT_CONSTRUCT mixed with ARRAY_AGG, but all failed
OBJECT_CONSTRUCT can work with several columns but only given all (*), if you try a select statement inside, it will fail
another issue is that analytical functions are not easily taken by the object or array functions in Snowflake.

Answer 1

You could use Snowflake Scripting or Snowpark for this but here's a solution that is somewhat flexible so you can apply it to different tables and column sets.
Create test table/view:
Create or Replace View dummy as (
select 'A' as col1, 0 as col2
union all
select null, 1
union all
select 'B', null
union all
select 'B', null
);
Set session variables for table and colnames.
set tbname = 'DUMMY';
set colnames = '["COL1", "COL2"]';
Create view that generates the required table_column_summary data:
Create or replace View table_column_summary as
with
-- Create table of required column names
cn as (
select VALUE::VARCHAR CNAME
from table(flatten(input => parse_json($colnames)))
)
-- Convert rows into objects
,ro as (
select
object_construct_keep_null(*) row_object
-- using identifier on session variable to dynamically supply table/view name
from identifier($tbname) )
-- Flatten row objects into key/values
,rof as (
select
key col_name,
ifnull(value,'null')::VARCHAR col_value
from ro, lateral flatten(input => row_object), cn
-- You will only need this filter if you need a subset
-- of columns from the source table/query summarised
where col_name = cn.cname)
-- Get the column value distinct value counts
,cdv as (
select col_name,
col_value,
sum(1) col_value_count
from rof
group by 1,2
)
-- and derive required column level stats and combine with cdv
,cv as (
select
(select count(1) from dummy) total,
col_name,
object_construct('COL_COUNT', count(col_value) ,
'COL_DIST', array_agg(distinct col_value),
'COL_OBJECT_COUNT', object_agg(col_value,col_value_count)) col_values
from cdv
group by 1,2)
-- Return result
Select * from cv;
Use this final query if you want a solution that works flexibility with any table/columns provided as input...
Select total, object_agg(col_name, col_values) col_values_obj
From table_column_summary
Group by 1;
Or use this final query if you want the fixed columns output as described in your question...
Select total,
COL1[0]:COL_COUNT COL1,
COL1[0]:COL_DIST DIST_COL1,
COL1[0]:COL_OBJECT_COUNT COL1_OBJECT_COUNT,
COL2[0]:COL_COUNT COL2,
COL2[0]:COL_DIST DIST_COL2,
COL2[0]:COL_OBJECT_COUNT COL2_OBJECT_COUNT
from table_column_summary
PIVOT ( ARRAY_AGG ( col_values )
FOR col_name IN ( 'COL1', 'COL2' ) ) as pt (total, col1, col2);