Support Board

import sys
from pathlib import Path
import numpy as np
import pandas as pd

def get_scid_df(filename, limitsize=sys.maxsize):
f = Path(filename)
assert f.exists(), f"{f} file not found"
stat = f.stat()
offset = 56 if stat.st_size < limitsize else stat.st_size - ((limitsize // 40) * 40)
sciddtype = np.dtype(
[
("Time", "<u8"),
("Open", "<f4"),
("High", "<f4"),
("Low", "<f4"),
("Close", "<f4"),
("Trades", "<i4"),
("Volume", "<i4"),
("BidVolume", "<i4"),
("AskVolume", "<i4"),
]
)
df = pd.DataFrame(
data=np.memmap(f, dtype=sciddtype, offset=offset, mode="r"), copy=False
)
df.dropna(inplace=True)
df["Time"] = df["Time"] - 2209161600000000
df.drop(df[(df.Time < 1)].index, inplace=True)
df.set_index("Time", inplace=True)
df.index = pd.to_datetime(df.index, unit="us")
df.index = df.index.tz_localize(tz="utc")
return df


def resample_scdf(scdf_or_filename, period="1Min", tz="UTC", limitsize=sys.maxsize):
df = (
get_scid_df(scdf_or_filename, limitsize)
if isinstance(scdf_or_filename, str)
else scdf_or_filename
)
assert isinstance(
df, pd.DataFrame
), f"{scdf_or_filename} has to be SC df or valid scid file"
df = df.resample(period).agg(
{
"Open": "first",
"High": "max",
"Low": "min",
"Close": "last",
"Trades": "sum",
"Volume": "sum",
"BidVolume": "sum",
"AskVolume": "sum",
}
)
if tz != "UTC":
tz = "America/New_York" if tz == "EST" else tz
tz = "America/Los_Angeles" if tz == "PST" else tz
df.index = df.index.tz_convert(tz)
return df