DuckDB Cheat Sheet

-- query a CSV directlySELECT customer_id, SUM(amount) AS totalFROM 'orders.csv'GROUP BY customer_idORDER BY total DESCLIMIT 10;-- query multiple partitioned parquet files with a globSELECT status, COUNT(*) FROM 'data/orders/*.parquet' GROUP BY status;

import duckdbimport pandas as pddf = pd.read_csv("orders.csv")# DuckDB can query a pandas DataFrame by variable name, no import stepresult = duckdb.sql("SELECT status, AVG(amount) FROM df GROUP BY status").df()# or via a persistent connectioncon = duckdb.connect("analytics.duckdb")con.execute("CREATE TABLE orders AS SELECT * FROM df")

INSTALL httpfs;LOAD httpfs;SET s3_region='us-east-1';SET s3_access_key_id='...';SET s3_secret_access_key='...';SELECT * FROM read_parquet('s3://my-bucket/events/*.parquet') LIMIT 100;

COPY (  SELECT customer_id, SUM(amount) AS total  FROM orders  GROUP BY customer_id) TO 'summary.parquet' (FORMAT PARQUET);COPY orders TO 'orders.csv' (HEADER, DELIMITER ',');