Queries against DuckDB

duckdb.sql

SELECT count(*)
FROM 'data/*.parquet';

SELECT * 
FROM 'data/*.parquet' 
LIMIT 10;

DESCRIBE
SELECT * 
FROM 'data/yellow_tripdata_2011-07.parquet';

DESCRIBE 
SELECT * 
FROM 'data/yellow_tripdata_2009-10.parquet';

-- We can see they have totally different schemas
-- So a bunch of Parquet files are presumably being ignored

SELECT string_split(file_name, '_')[-1] AS filename, stats_min, stats_max 
FROM parquet_metadata('data/*.parquet') 
WHERE path_in_schema IN (
    'tpep_pickup_datetime', 'tpep_dropoff_datetime'
) 
ORDER BY stats_min
LIMIT 20;