<invoke name="query_sql"> <parameter name="sql">WITH allr AS ( SELECT 'Jan' m, "Company Name" c, CAST(Founded AS VARCHAR) f, Location l, Sector s, Amount a, Stage st FROM raw."Indian Startups _ Funding Investors Data January 2022" UNION ALL SELECT 'Feb', "Company Name", CAST(Founded AS VARCHAR), Location, Sector, Amount, Stage FROM raw."Indian Startups _ Funding Investors Data February 2022" UNION ALL SELECT 'Mar', "Company Name", CAST(Founded AS VARCHAR), Location, Sector, Amount, Stage FROM raw."Indian Startups _ Funding Investors Data March 2022" UNION ALL SELECT 'Apr', "Company Name", CAST(Founded AS VARCHAR), Location, Sector, Amount, Stage FROM raw."Indian Startups _ Funding Investors Data April 2022" UNION ALL SELECT 'May', "Company Name", Founded, Location, Sector, Amount, Stage FROM raw."Indian Startups _ Funding Investors Data May 2022") SELECT m, COUNT(*) n, COUNT(*) FILTER (WHERE c IS NULL) null_name, COUNT(*) FILTER (WHERE f IS NULL) null_founded, COUNT(*) FILTER (WHERE TRY_CAST(f AS INTEGER) IS NULL AND f IS NOT NULL) nonnum_founded, COUNT(*) FILTER (WHERE TRY_CAST(f AS INTEGER) < 1950) old_founded, COUNT(*) FILTER (WHERE a IS NULL) null_amt, COUNT(*) FILTER (WHERE st IS NULL) null_stage, COUNT(*) FILTER (WHERE l IS NULL) null_loc, COUNT(*) - COUNT(DISTINCT c) dup_names FROM allr GROUP BY m ORDER BY m</parameter> <parameter name="purpose">Profile nulls, non-numeric/old Founded, duplicates per month</parameter> </invoke>