Useful Parquet oneliners, view and manipulate with DuckDB

duckdb_one_liners.sh

# view 10 lines
uvx duckdb -c "FROM 'results.parquet' LIMIT 10"

# add 2 new columns 
uvx duckdb -c "COPY (SELECT *, NULL::INT AS dominik_label, NULL::VARCHAR AS dominik_comments FROM 'results.parquet') TO 'results.parquet'"

# remove 2 columns
uvx duckdb -c "COPY (SELECT * EXCLUDE (dominik_label, dominik_comments) FROM 'results.parquet') TO 'results.parquet'"

# sort by 2 columns 
uvx duckdb -c "COPY (SELECT * FROM 'results.parquet' ORDER BY has_error DESC, has_deviation DESC) TO 'results.parquet'"

# display and copy as markdown 
uvx duckdb -markdown -c "FROM 'results.parquet' LIMIT 10" | pbcopy