import pyarrow.dataset as ds

# Path to local datalake
datalake_path = "F:/datalake/AABBCCDD/CAN2_GnssSpeed"

# Create dateset containing multiple files
ds_gnss_speed = ds.dataset(datalake_path, format="parquet")

# Read all files into memory
gnss_speed = ds_gnss_speed.to_table()