Code/preprocess
parquet2csv
import pandas as pd import argparse parser = argparse.ArgumentParser() parser.add_argument('--dir', required=True, help='dir address') #C/.../file.parquet parser.add_argument('--out', required=True, help='out address') #C/.../out.csv args = parser.parse_args() df = pd.read_parquet(args.dir, engine='pyarrow') df.to_csv(args.out, index=False)