fixes
This commit is contained in:
Oleg Sheynin
@@ -9,16 +9,18 @@ from pt_trading.trading_pair import PairState, TradingPair
|
||||
from statsmodels.tsa.vector_ar.vecm import VECM, VECMResults
|
||||
|
||||
NanoPerMin = 1e9
|
||||
|
||||
|
||||
|
||||
class RollingFit(PairsTradingFitMethod):
|
||||
'''
|
||||
"""
|
||||
N O T E:
|
||||
=========
|
||||
- This class remains to be abstract
|
||||
- The following methods are to be implemented in the subclass:
|
||||
- create_trading_pair()
|
||||
=========
|
||||
'''
|
||||
"""
|
||||
|
||||
def __init__(self) -> None:
|
||||
super().__init__()
|
||||
|
||||
@@ -33,16 +35,18 @@ class RollingFit(PairsTradingFitMethod):
|
||||
|
||||
pair.user_data_["state"] = PairState.INITIAL
|
||||
# Initialize trades DataFrame with proper dtypes to avoid concatenation warnings
|
||||
pair.user_data_["trades"] = pd.DataFrame(columns=self.TRADES_COLUMNS).astype({
|
||||
"time": "datetime64[ns]",
|
||||
"symbol": "string",
|
||||
"side": "string",
|
||||
"action": "string",
|
||||
"price": "float64",
|
||||
"disequilibrium": "float64",
|
||||
"scaled_disequilibrium": "float64",
|
||||
"pair": "object"
|
||||
})
|
||||
pair.user_data_["trades"] = pd.DataFrame(columns=self.TRADES_COLUMNS).astype(
|
||||
{
|
||||
"time": "datetime64[ns]",
|
||||
"symbol": "string",
|
||||
"side": "string",
|
||||
"action": "string",
|
||||
"price": "float64",
|
||||
"disequilibrium": "float64",
|
||||
"scaled_disequilibrium": "float64",
|
||||
"pair": "object",
|
||||
}
|
||||
)
|
||||
|
||||
training_minutes = config["training_minutes"]
|
||||
curr_predicted_row_idx = 0
|
||||
@@ -66,7 +70,9 @@ class RollingFit(PairsTradingFitMethod):
|
||||
# ================================ PREDICTION ================================
|
||||
self.pair_predict_result_ = pair.predict()
|
||||
except Exception as e:
|
||||
raise RuntimeError(f"{pair}: TrainingPrediction failed: {str(e)}") from e
|
||||
raise RuntimeError(
|
||||
f"{pair}: TrainingPrediction failed: {str(e)}"
|
||||
) from e
|
||||
|
||||
# break
|
||||
|
||||
@@ -76,8 +82,8 @@ class RollingFit(PairsTradingFitMethod):
|
||||
curr_predicted_row_idx += 1
|
||||
|
||||
self._create_trading_signals(pair, config, bt_result)
|
||||
print(f"***{pair}*** FINISHED *** Num Trades:{len(pair.user_data_['trades'])}")
|
||||
|
||||
print(f"***{pair}*** FINISHED *** Num Trades:{len(pair.user_data_['trades'])}")
|
||||
|
||||
return pair.get_trades()
|
||||
|
||||
def _create_trading_signals(
|
||||
@@ -93,8 +99,14 @@ class RollingFit(PairsTradingFitMethod):
|
||||
pred_row = predicted_df.iloc[curr_predicted_row_idx]
|
||||
scaled_disequilibrium = pred_row["scaled_disequilibrium"]
|
||||
|
||||
if pair.user_data_["state"] in [PairState.INITIAL, PairState.CLOSE, PairState.CLOSE_POSITION]:
|
||||
if scaled_disequilibrium >= open_threshold:
|
||||
if pair.user_data_["state"] in [
|
||||
PairState.INITIAL,
|
||||
PairState.CLOSE,
|
||||
PairState.CLOSE_POSITION,
|
||||
PairState.CLOSE_STOP_LOSS,
|
||||
PairState.CLOSE_STOP_PROFIT,
|
||||
]:
|
||||
if scaled_disequilibrium >= open_threshold:
|
||||
open_trades = self._get_open_trades(
|
||||
pair, row=pred_row, open_threshold=open_threshold
|
||||
)
|
||||
@@ -121,23 +133,21 @@ class RollingFit(PairsTradingFitMethod):
|
||||
pair, row=pred_row, close_threshold=close_threshold
|
||||
)
|
||||
if close_trades is not None:
|
||||
close_trades["status"] = pair.user_data_["stop_close_state"].name
|
||||
close_trades["status"] = pair.user_data_[
|
||||
"stop_close_state"
|
||||
].name
|
||||
print(f"STOP CLOSE TRADES:\n{close_trades}")
|
||||
pair.add_trades(close_trades)
|
||||
pair.user_data_["state"] = pair.user_data_["stop_close_state"]
|
||||
pair.user_data_["state"] = pair.user_data_["stop_close_state"]
|
||||
pair.on_close_trades(close_trades)
|
||||
|
||||
# Outstanding positions
|
||||
if pair.user_data_["state"] == PairState.OPEN:
|
||||
print(
|
||||
f"{pair}: *** Position is NOT CLOSED. ***"
|
||||
)
|
||||
print(f"{pair}: *** Position is NOT CLOSED. ***")
|
||||
# outstanding positions
|
||||
if config["close_outstanding_positions"]:
|
||||
close_position_trades = self._get_close_trades(
|
||||
pair=pair,
|
||||
row=pred_row,
|
||||
close_threshold=close_threshold
|
||||
pair=pair, row=pred_row, close_threshold=close_threshold
|
||||
)
|
||||
if close_position_trades is not None:
|
||||
close_position_trades["status"] = PairState.CLOSE_POSITION.name
|
||||
@@ -223,15 +233,17 @@ class RollingFit(PairsTradingFitMethod):
|
||||
columns=self.TRADES_COLUMNS,
|
||||
)
|
||||
# Ensure consistent dtypes
|
||||
return df.astype({
|
||||
"time": "datetime64[ns]",
|
||||
"action": "string",
|
||||
"symbol": "string",
|
||||
"price": "float64",
|
||||
"disequilibrium": "float64",
|
||||
"scaled_disequilibrium": "float64",
|
||||
"pair": "object"
|
||||
})
|
||||
return df.astype(
|
||||
{
|
||||
"time": "datetime64[ns]",
|
||||
"action": "string",
|
||||
"symbol": "string",
|
||||
"price": "float64",
|
||||
"disequilibrium": "float64",
|
||||
"scaled_disequilibrium": "float64",
|
||||
"pair": "object",
|
||||
}
|
||||
)
|
||||
|
||||
def _get_close_trades(
|
||||
self, pair: TradingPair, row: pd.Series, close_threshold: float
|
||||
@@ -277,16 +289,17 @@ class RollingFit(PairsTradingFitMethod):
|
||||
columns=self.TRADES_COLUMNS,
|
||||
)
|
||||
# Ensure consistent dtypes
|
||||
return df.astype({
|
||||
"time": "datetime64[ns]",
|
||||
"action": "string",
|
||||
"symbol": "string",
|
||||
"price": "float64",
|
||||
"disequilibrium": "float64",
|
||||
"scaled_disequilibrium": "float64",
|
||||
"pair": "object"
|
||||
})
|
||||
return df.astype(
|
||||
{
|
||||
"time": "datetime64[ns]",
|
||||
"action": "string",
|
||||
"symbol": "string",
|
||||
"price": "float64",
|
||||
"disequilibrium": "float64",
|
||||
"scaled_disequilibrium": "float64",
|
||||
"pair": "object",
|
||||
}
|
||||
)
|
||||
|
||||
def reset(self) -> None:
|
||||
curr_training_start_idx = 0
|
||||
|
||||
|
||||
Reference in New Issue
Block a user