Convert CSV files to HDF5 format

csv2hdf.py

#!/usr/bin/env python

import pandas as pd
import sys

def convert(source_name, target_name, dataset_name=None, group_name=None):
    # data_set_name & group_name not yet used
    if not group_name:
        dataset_name = ".".join(s for s in source_name.split(".") if s not in ("csv", "gz", "dat", "txt", "tsv"))
    # print(group_name)
    data = pd.read_table(source_name, index_col=False)
    data.to_hdf(target_name, dataset_name, complib="zlib")

if __name__ == "__main__":
    if len(sys.argv) < 3:
        raise Exception("At least 3 parameters!")
    sources = sys.argv[1:-1]
    target = sys.argv[-1]
    for source in sources:
        convert(source, target)