MotherDuck社の公式ブログのチュートリアル「DuckDB Tutorial For Beginners」をやってみた

# 最新バージョンをダウンロード
wget https://github.com/duckdb/duckdb/releases/download/v1.1.0/duckdb_cli-linux-amd64.zip

# 解凍
unzip duckdb_cli-linux-amd64.zip

# 実行権限を付与
chmod +x duckdb

# オプション：システム全体で使用できるようにする
sudo mv duckdb /usr/local/bin/

$ duckdb
v1.1.0 fa5c2fe15f
Enter ".help" for usage hints.
Connected to a transient in-memory database.
Use ".open FILENAME" to reopen on a persistent database.
D

SELECT * FROM read_csv_auto('data/netflix_daily_top_10.csv');

SELECT * FROM read_parquet('data/netflix_daily_top_10.parquet');

mkdir database
duckdb database/myawesomedb.db

CREATE TABLE netflix_top10 AS SELECT * FROM read_csv_auto('data/netflix_daily_top_10.csv');

SHOW TABLES;

SELECT * FROM netflix_top10;

.mode markdown
.output myfile.md
SELECT * FROM netflix_top10;

duckdb -c "SELECT * FROM read_parquet('data/netflix_daily_top_10.parquet')"

duckdb -c "COPY 'data/netflix_daily_top_10.csv' TO 'output_netflix_daily_top_10.parquet' WITH (FORMAT 'PARQUET');"

SELECT * FROM duckdb_extensions();

INSTALL httpfs;
LOAD httpfs;

-- Install extensions
INSTALL httpfs;
LOAD httpfs;
-- Minimum configuration for loading S3 dataset if the bucket is public
SET s3_region='us-east-1';

CREATE TABLE netflix AS SELECT * FROM read_parquet('s3://duckdb-md-dataset-121/netflix_daily_top_10.parquet');
SHOW TABLES;

FROM netflix;

SELECT Title, max("Days In Top 10") from netflix
where Type='Movie'
GROUP BY Title
ORDER BY max("Days In Top 10") desc
limit 5;

COPY (
SELECT Title, max("Days In Top 10") from netflix
where Type='TV Show'
GROUP BY Title
ORDER BY max("Days In Top 10") desc
limit 5
) TO 'output.csv' (HEADER, DELIMITER ',');