jupysql_duckdb_inmemory_csv_query_quickstart.py

1# Install the necessary packages
2# %pip install jupysql duckdb-engine --quiet
3
4# Load the SQL extension
5%load_ext sql
6
7# Connect to an in-memory DuckDB database
8%sql duckdb://
9
10# Download a sample dataset
11from urllib.request import urlretrieve
12urlretrieve("https://raw.githubusercontent.com/mwaskom/seaborn-data/master/penguins.csv", "penguins.csv")
13
14# Query the CSV file directly and display the first few rows
15%sql SELECT * FROM penguins.csv LIMIT 5