Snippet Running dask_cudf on Coiled GPU Dask Cluster

afar_dask_cudf_cluster.py

%%time
with afar.run, remotely:
    import dask_cudf

    df = dask_cudf.read_csv(
        "s3://nyc-tlc/trip data/yellow_tripdata_2019-*.csv",
        parse_dates=["tpep_pickup_datetime", "tpep_dropoff_datetime"],
        storage_options={"anon": True},
        assume_missing=True,
    ).persist()

    res = (
        df.groupby("passenger_count").tip_amount.mean().compute().to_pandas()
    )
res.result()