Sierra Chart Intraday Data File parser

scid_parser.py

import numpy as np
import pandas as pd

from struct import unpack, calcsize
from collections import namedtuple


def parse_scid_file(filename):
    SIERRA_CHART_EPOCH =  pd.to_datetime('1899-12-30')

    header_record = '<4sLLHHL36s'
    header_size = calcsize(header_record)
    Header = namedtuple('Header', 'FileTypeUniqueHeaderID HeaderSize RecordSize Version Unused1 UTCStartIndex Reserve')

    intraday_record = np.dtype([
        ('DateTime', 'timedelta64[us]'),
        ('Open', np.float32),
        ('High', np.float32),
        ('Low', np.float32),
        ('Close', np.float32),
        ('NumTrades', np.uint32),
        ('TotalVolume', np.uint32),
        ('BidVolume', np.uint32),
        ('AskVolume', np.uint32),
    ])

    arr = None
    with open(filename, 'rb') as file:
        header = file.read(header_size)
        header = Header._make(unpack(header_record, header))
        arr = np.fromfile(file, dtype=intraday_record)
        
    df = pd.DataFrame(arr)
    df['DateTime'] = SIERRA_CHART_EPOCH + df['DateTime']
    return df