research/pairs_trading
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fixes

Browse Source
This commit is contained in:
Oleg Sheynin 2025-06-12 23:59:36 -04:00
parent 671422976d
commit 2e589f7e8c
5 changed files with 249 additions and 32 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
configuration/crypto.cfg
View File

@ -2,9 +2,9 @@
"security_type": "CRYPTO",
"data_directory": "./data/crypto",
"datafiles": [
"20250519.mktdata.ohlcv.db"
"20250528.mktdata.ohlcv.db"
],
"db_table_name": "bnbspot_ohlcv_1min",
"db_table_name": "md_1min_bars",
"exchange_id": "BNBSPOT",
"instrument_id_pfx": "PAIR-",
"instruments": [

218
requirements.txt Normal file
View File

@ -0,0 +1,218 @@
aiohttp>=3.8.4
aiosignal>=1.3.1
apt-clone>=0.2.1
apturl>=0.5.2
async-timeout>=4.0.2
attrs>=21.2.0
beautifulsoup4>=4.10.0
black>=23.3.0
blinker>=1.4
Brlapi>=0.8.3
ccsm>=0.9.14.1
certifi>=2020.6.20
chardet>=4.0.0
charset-normalizer>=3.1.0
click>=8.0.3
colorama>=0.4.4
command-not-found>=0.3
compizconfig-python>=0.9.14.1
configobj>=5.0.6
cryptography>=3.4.8
cupshelpers>=1.0
dbus-python>=1.2.18
defer>=1.0.6
distro>=1.7.0
docker>=5.0.3
docker-compose>=1.29.2
dockerpty>=0.4.1
docopt>=0.6.2
eyeD3>=0.8.10
filelock>=3.6.0
frozenlist>=1.3.3
grpcio>=1.30.2
html5lib>=1.1
httplib2>=0.20.2
idna>=3.3
ifaddr>=0.1.7
IMDbPY>=2021.4.18
importlib-metadata>=4.6.4
iotop>=0.6
jeepney>=0.7.1
jsonschema>=3.2.0
keyring>=23.5.0
launchpadlib>=1.10.16
lazr.restfulclient>=0.14.4
lazr.uri>=1.0.6
louis>=3.20.0
lxml>=4.8.0
Mako>=1.1.3
Markdown>=3.3.6
MarkupSafe>=2.0.1
meld>=3.20.4
more-itertools>=8.10.0
multidict>=6.0.4
mypy>=0.942
mypy-extensions>=0.4.3
netaddr>=0.8.0
netifaces>=0.11.0
oauthlib>=3.2.0
onboard>=1.4.1
packaging>=23.1
pathspec>=0.11.1
pexpect>=4.8.0
Pillow>=9.0.1
platformdirs>=3.2.0
protobuf>=3.12.4
psutil>=5.9.0
ptyprocess>=0.7.0
pycairo>=1.20.1
pycups>=2.0.1
pycurl>=7.44.1
pyelftools>=0.27
Pygments>=2.11.2
PyGObject>=3.42.1
PyICU>=2.8.1
PyJWT>=2.3.0
PyNaCl>=1.5.0
pyparsing>=2.4.7
pyparted>=3.11.7
pyrsistent>=0.18.1
python-apt>=2.4.0+ubuntu4
python-debian>=0.1.43+ubuntu1.1
python-dotenv>=0.19.2
python-magic>=0.4.24
python-xapp>=2.2.2
python-xlib>=0.29
pyxdg>=0.27
PyYAML>=5.4.1
remarkable>=1.87
reportlab>=3.6.8
requests>=2.25.1
requests-file>=1.5.1
SecretStorage>=3.3.1
setproctitle>=1.2.2
six>=1.16.0
soupsieve>=2.3.1
ssh-import-id>=5.11
statsmodels>=0.14.4
systemd-python>=234
texttable>=1.6.4
tldextract>=3.1.2
tomli>=1.2.2
typed-ast>=1.4.3
types-aiofiles>=0.1
types-annoy>=1.17
types-appdirs>=1.4
types-atomicwrites>=1.4
types-aws-xray-sdk>=2.8
types-babel>=2.9
types-backports-abc>=0.5
types-backports.ssl-match-hostname>=3.7
types-beautifulsoup4>=4.10
types-bleach>=4.1
types-boto>=2.49
types-braintree>=4.11
types-cachetools>=4.2
types-caldav>=0.8
types-certifi>=2020.4
types-characteristic>=14.3
types-chardet>=4.0
types-click>=7.1
types-click-spinner>=0.1
types-colorama>=0.4
types-commonmark>=0.9
types-contextvars>=0.1
types-croniter>=1.0
types-cryptography>=3.3
types-dataclasses>=0.1
types-dateparser>=1.0
types-DateTimeRange>=0.1
types-decorator>=0.1
types-Deprecated>=1.2
types-docopt>=0.6
types-docutils>=0.17
types-editdistance>=0.5
types-emoji>=1.2
types-entrypoints>=0.3
types-enum34>=1.1
types-filelock>=3.2
types-first>=2.0
types-Flask>=1.1
types-freezegun>=1.1
types-frozendict>=0.1
types-futures>=3.3
types-html5lib>=1.1
types-httplib2>=0.19
types-humanfriendly>=9.2
types-ipaddress>=1.0
types-itsdangerous>=1.1
types-JACK-Client>=0.1
types-Jinja2>=2.11
types-jmespath>=0.10
types-jsonschema>=3.2
types-Markdown>=3.3
types-MarkupSafe>=1.1
types-mock>=4.0
types-mypy-extensions>=0.4
types-mysqlclient>=2.0
types-oauthlib>=3.1
types-orjson>=3.6
types-paramiko>=2.7
types-Pillow>=8.3
types-polib>=1.1
types-prettytable>=2.1
types-protobuf>=3.17
types-psutil>=5.8
types-psycopg2>=2.9
types-pyaudio>=0.2
types-pycurl>=0.1
types-pyfarmhash>=0.2
types-Pygments>=2.9
types-PyMySQL>=1.0
types-pyOpenSSL>=20.0
types-pyRFC3339>=0.1
types-pysftp>=0.2
types-pytest-lazy-fixture>=0.6
types-python-dateutil>=2.8
types-python-gflags>=3.1
types-python-nmap>=0.6
types-python-slugify>=5.0
types-pytz>=2021.1
types-pyvmomi>=7.0
types-PyYAML>=5.4
types-redis>=3.5
types-requests>=2.25
types-retry>=0.9
types-selenium>=3.141
types-Send2Trash>=1.8
types-setuptools>=57.4
types-simplejson>=3.17
types-singledispatch>=3.7
types-six>=1.16
types-slumber>=0.7
types-stripe>=2.59
types-tabulate>=0.8
types-termcolor>=1.1
types-toml>=0.10
types-toposort>=1.6
types-ttkthemes>=3.2
types-typed-ast>=1.4
types-tzlocal>=0.1
types-ujson>=0.1
types-vobject>=0.9
types-waitress>=0.1
types-Werkzeug>=1.0
types-xxhash>=2.0
typing-extensions>=3.10.0.2
ubuntu-drivers-common>=0.0.0
ufw>=0.36.1
Unidecode>=1.3.3
urllib3>=1.26.5
wadllib>=1.3.6
webencodings>=0.5.1
websocket-client>=1.2.3
xdg>=5
xkit>=0.0.0
yarl>=1.9.1
youtube-dl>=2021.12.17
zipp>=1.0.0

17
src/pt_backtest.py
View File

@ -6,7 +6,6 @@ from typing import Any, Dict, List
import pandas as pd
from strategies import SlidingFitStrategy, StaticFitStrategy
from tools.data_loader import load_market_data
from tools.trading_pair import TradingPair
from results import BacktestResult
@ -68,21 +67,21 @@ def main() -> None:
)
args = parser.parse_args()
CONFIG = load_config(args.config)
config: Dict = load_config(args.config)
# Dynamically instantiate strategy class
strategy_class_name = CONFIG.get("strategy_class", "strategies.StaticFitStrategy")
strategy_class_name = config.get("strategy_class", "strategies.StaticFitStrategy")
module_name, class_name = strategy_class_name.rsplit(".", 1)
module = importlib.import_module(module_name)
STRATEGY = getattr(module, class_name)()
strategy = getattr(module, class_name)()
# Initialize a dictionary to store all trade results
all_results: Dict[str, Dict[str, Any]] = {}
bt_results = BacktestResult(config=CONFIG)
bt_results = BacktestResult(config=config)
# Process each data file
price_column = CONFIG["price_column"]
for datafile in CONFIG["datafiles"]:
price_column = config["price_column"]
for datafile in config["datafiles"]:
print(f"\n====== Processing {datafile} ======")
# Clear the TRADES global dictionary and reset unrealized PnL for the new file
@ -91,11 +90,11 @@ def main() -> None:
# Process data for this file
try:
run_all_pairs(
config=CONFIG,
config=config,
datafile=datafile,
price_column=price_column,
bt_result=bt_results,
strategy=STRATEGY,
strategy=strategy,
)
# Store results with file name as key

19
src/tools/data_loader.py
View File

@ -1,9 +1,7 @@
import sys
import sqlite3
from typing import Dict, Tuple
from typing import Dict
import pandas as pd
from tools.trading_pair import TradingPair
def load_sqlite_to_dataframe(db_path, query):
@ -15,15 +13,15 @@ def load_sqlite_to_dataframe(db_path, query):
except sqlite3.Error as excpt:
print(f"SQLite error: {excpt}")
raise
except Exception as e:
except Exception as excpt:
print(f"Error: {excpt}")
raise
raise Exception() from excpt
finally:
if "conn" in locals():
conn.close()
def convert_time_to_UTC(value: str, timezone: str):
def convert_time_to_UTC(value: str, timezone: str) -> str:
from zoneinfo import ZoneInfo
from datetime import datetime
@ -32,12 +30,9 @@ def convert_time_to_UTC(value: str, timezone: str):
local_dt = datetime.strptime(value, "%Y-%m-%d %H:%M:%S")
zinfo = ZoneInfo(timezone)
result = local_dt.replace(tzinfo=zinfo)
result: datetime = local_dt.replace(tzinfo=zinfo).astimezone(ZoneInfo("UTC"))
result = result.astimezone(ZoneInfo("UTC"))
result = result.strftime("%Y-%m-%d %H:%M:%S")
return result
return result.strftime("%Y-%m-%d %H:%M:%S")
def load_market_data(datafile: str, config: Dict) -> pd.DataFrame:
@ -52,7 +47,7 @@ def load_market_data(datafile: str, config: Dict) -> pd.DataFrame:
query = "select"
if security_type == "CRYPTO":
query += " strftime('%Y-%m-%d %H:%M:%S', tstamp/1000000000, 'unixepoch') as tstamp"
query += " strftime('%Y-%m-%d %H:%M:%S', tstamp_ns/1000000000, 'unixepoch') as tstamp"
query += ", tstamp as time_ns"
else:
query += " tstamp"

23
src/tools/trading_pair.py
View File

@ -1,7 +1,7 @@
from typing import Any, Dict, List, Optional
import pandas as pd
from statsmodels.tsa.vector_ar.vecm import VECM
import pandas as pd #type:ignore
from statsmodels.tsa.vector_ar.vecm import VECM #type:ignore
class TradingPair:
market_data_: pd.DataFrame
@ -16,7 +16,7 @@ class TradingPair:
testing_df_: Optional[pd.DataFrame]
vecm_fit_: Optional[VECM]
user_data_: Dict[str, Any]
def __init__(self, market_data: pd.DataFrame, symbol_a: str, symbol_b: str, price_column: str):
@ -24,13 +24,13 @@ class TradingPair:
self.symbol_b_ = symbol_b
self.price_column_ = price_column
self.market_data_ = self._transform_dataframe(market_data)[["tstamp"] + self.colnames()]
self.training_mu_ = None
self.training_std_ = None
self.training_df_ = None
self.testing_df_ = None
self.vecm_fit_ = None
self.user_data_ = {}
def _transform_dataframe(self, df: pd.DataFrame):
@ -41,7 +41,9 @@ class TradingPair:
result_df: pd.DataFrame = pd.DataFrame(df_selected["tstamp"]).drop_duplicates().reset_index(drop=True)
# For each unique symbol, add a corresponding close price column
for symbol in df_selected["symbol"].unique():
symbols = df_selected["symbol"].unique()
for symbol in symbols:
# Filter rows for this symbol
df_symbol = df_selected[df_selected["symbol"] == symbol].reset_index(drop=True)
@ -60,7 +62,7 @@ class TradingPair:
return result_df
def get_datasets(self, training_minutes: int, training_start_index: int = 0, testing_size: Optional[int] = None) -> None:
testing_start_index = training_start_index + training_minutes
self.training_df_ = self.market_data_.iloc[training_start_index:testing_start_index, :].copy()
self.training_df_ = self.training_df_.dropna().reset_index(drop=True)
@ -108,6 +110,7 @@ class TradingPair:
# print('*' * 80 + '\n' + f"**************** {self} IS COINTEGRATED ****************\n" + '*' * 80)
self.fit_VECM()
assert self.training_df_ is not None and self.vecm_fit_ is not None
diseq_series = self.training_df_[self.colnames()] @ self.vecm_fit_.beta
self.training_mu_ = diseq_series.mean().iloc[0]
self.training_std_ = diseq_series.std().iloc[0]
@ -121,10 +124,12 @@ class TradingPair:
return True
def predict(self) -> None:
assert self.testing_df_ is not None
assert self.vecm_fit_ is not None
predicted_prices = self.vecm_fit_.predict(steps=len(self.testing_df_))
# Convert prediction to a DataFrame for readability
# predicted_df =
# predicted_df =
self.predicted_df_ = pd.merge(
self.testing_df_.reset_index(drop=True),
@ -144,7 +149,7 @@ class TradingPair:
self.predicted_df_ = self.predicted_df_.reset_index()
return self.predicted_df_
def __repr__(self) ->str:
return f"{self.symbol_a_} & {self.symbol_b_}"