<invoke name="query_sql"> <parameter name="sql">WITH u AS ( SELECT 'January' AS tbl, "Company Name" AS company, Amount, Founded::VARCHAR AS founded, Stage FROM raw."Indian Startups _ Funding Investors Data January 2022" UNION ALL SELECT 'February', "Company Name", Amount, Founded::VARCHAR, Stage FROM raw."Indian Startups _ Funding Investors Data February 2022" UNION ALL SELECT 'March', "Company Name", Amount, Founded::VARCHAR, Stage FROM raw."Indian Startups _ Funding Investors Data March 2022" UNION ALL SELECT 'April', "Company Name", Amount, Founded::VARCHAR, Stage FROM raw."Indian Startups _ Funding Investors Data April 2022" UNION ALL SELECT 'May', "Company Name", Amount, Founded::VARCHAR, Stage FROM raw."Indian Startups _ Funding Investors Data May 2022" ) SELECT tbl, COUNT(*) AS total_rows, COUNT(*) FILTER (WHERE Amount IS NULL OR TRIM(Amount) = '') AS blank_amount, COUNT(*) FILTER (WHERE LOWER(Amount) = 'undisclosed') AS undisclosed, COUNT(*) FILTER (WHERE regexp_matches(Amount, '^\$[0-9]{1,3}(,[0-9]{3})+$')) AS clean_usd_format, COUNT(*) FILTER (WHERE Amount IS NOT NULL AND TRIM(Amount) <> '' AND LOWER(Amount) <> 'undisclosed' AND NOT regexp_matches(Amount, '^\$[0-9]{1,3}(,[0-9]{3})+$')) AS other_format, COUNT(*) FILTER (WHERE company IS NULL OR TRIM(company) = '') AS blank_company, COUNT(*) - COUNT(DISTINCT company) AS duplicate_company_rows, COUNT(*) FILTER (WHERE Stage IS NULL OR TRIM(Stage) = '') AS blank_stage FROM u GROUP BY tbl ORDER BY tbl</parameter> <parameter name="purpose">Profile Amount format consistency, blanks and duplicates per monthly table</parameter> <parameter name="source">raw</parameter> </invoke>