Login Page - Create Account

Support Board


Date/Time: Sat, 23 Nov 2024 15:02:35 +0000



Post From: Python for Sierra Chart

[2024-05-05 15:10:40]
User656492 - Posts: 143
<BUMP> I'm using code from above:

import sys

from pathlib import Path

import numpy as np

import pandas as pd



def get_scid_df(filename, limitsize=sys.maxsize):

f = Path('/Users/Me/SierraPython/NQM4.CME.scid' )

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

print(resample_scdf("NQM4.CME.scid", tz="EST"))

And I get this:
Open High Low Close \
Time
2024-02-25 19:01:00-05:00 0.000000e+00 1822300.0 1822125.0 1822125.0
2024-02-25 19:02:00-05:00 -1.999001e+37 1820775.0 1820275.0 1820775.0
2024-02-25 19:03:00-05:00 0.000000e+00 1820850.0 1820250.0 1820875.0
2024-02-25 19:04:00-05:00 0.000000e+00 1820900.0 1820025.0 1820625.0
2024-02-25 19:05:00-05:00 0.000000e+00 1820700.0 1819900.0 1820600.0
... ... ... ... ...
2024-04-30 12:20:00-04:00 0.000000e+00 1777300.0 1776650.0 1777175.0
2024-04-30 12:21:00-04:00 0.000000e+00 1777625.0 1776950.0 1777000.0
2024-04-30 12:22:00-04:00 0.000000e+00 1777350.0 1776950.0 1777150.0
2024-04-30 12:23:00-04:00 -1.999001e+37 1777575.0 1776900.0 1777175.0
2024-04-30 12:24:00-04:00 -1.999001e+37 1777350.0 1777125.0 1777175.0

Trades Volume BidVolume AskVolume
Time
2024-02-25 19:01:00-05:00 1 1 1 0
2024-02-25 19:02:00-05:00 2 2 0 2
2024-02-25 19:03:00-05:00 4 4 0 4
2024-02-25 19:04:00-05:00 10 10 0 10
2024-02-25 19:05:00-05:00 6 6 2 4
... ... ... ... ...
2024-04-30 12:20:00-04:00 869 959 376 583
2024-04-30 12:21:00-04:00 861 1023 430 593
2024-04-30 12:22:00-04:00 462 518 225 293
2024-04-30 12:23:00-04:00 522 548 279 269
2024-04-30 12:24:00-04:00 58 58 18 40

[93144 rows x 8 columns]

As you can see the Open field is fubar. I think time stamp is being parsed incorrectly but have no idea how to address it. Any thoughts?