data_source_tables_gen.py 文件源码

def merge_all_files_into_pytables(file_dir, file_out):
    """
    process each file into pytables
    """
    start = None
    start = datetime.datetime.now()
    out_h5 = tables.openFile(file_out,
                             mode="w",
                             title="bars",
                             filters=tables.Filters(complevel=9,
                                                    complib='zlib'))
    table = None
    for file_in in glob.glob(file_dir + "/*.gz"):
        gzip_file = gzip.open(file_in)
        expected_header = ["dt", "sid", "open", "high", "low", "close",
                           "volume"]
        csv_reader = csv.DictReader(gzip_file)
        header = csv_reader.fieldnames
        if header != expected_header:
            logging.warn("expected header %s\n" % (expected_header))
            logging.warn("header_found %s" % (header))
            return

        for current_date, rows in parse_csv(csv_reader):
            table = out_h5.createTable("/TD", "date_" + current_date,
                                       OHLCTableDescription,
                                       expectedrows=len(rows),
                                       createparents=True)
            table.append(rows)
            table.flush()
        if table is not None:
            table.flush()
    end = datetime.datetime.now()
    diff = (end - start).seconds
    logging.debug("finished  it took %d." % (diff))