gtfs-dagster/user_code/gtfs/assets.py

18 lines
498 B
Python

import pandas as pd
from dagster import asset
from dagster_duckdb import DuckDBResource
@asset
def agency_list(duckdb: DuckDBResource) -> None:
"""Load agency list from CSV into DuckDB."""
# Read the CSV (path is relative to container working directory)
df = pd.read_csv('data/gtfs/agency_list.csv')
# Write to DuckDB
with duckdb.get_connection() as conn:
conn.execute("""
CREATE OR REPLACE TABLE agency_list AS
SELECT * FROM df
""")