| Overall Statistics |
|
Total Orders 536 Average Win 2.02% Average Loss -0.74% Compounding Annual Return 5.883% Drawdown 36.800% Expectancy 0.280 Start Equity 100000 End Equity 168174.60 Net Profit 68.175% Sharpe Ratio 0.216 Sortino Ratio 0.209 Probabilistic Sharpe Ratio 0.918% Loss Rate 66% Win Rate 34% Profit-Loss Ratio 2.74 Alpha -0.004 Beta 0.485 Annual Standard Deviation 0.15 Annual Variance 0.023 Information Ratio -0.281 Tracking Error 0.152 Treynor Ratio 0.067 Total Fees $1167.90 Estimated Strategy Capacity $1100000000.00 Lowest Capacity Asset SPY R735QTJ8XC9X Portfolio Turnover 8.64% |
#region imports
from AlgorithmImports import *
from tensorflow.keras.models import Sequential, load_model
from tensorflow.keras.layers import Dense, Flatten
from tensorflow.keras.optimizers import Adam
#endregion
class KerasExampleAlgorithm(QCAlgorithm):
def Initialize(self):
self.SetStartDate(2015, 4, 1) # Set Start Date
self.SetEndDate(2024, 5, 1)
self.SetCash(100000) # Set Strategy Cash
self.symbol = self.AddEquity("SPY", Resolution.Daily).Symbol
self.SetBenchmark("SPY")
model_key = "model"
if self.ObjectStore.ContainsKey(model_key):
file_name = self.ObjectStore.GetFilePath(model_key)
self.model = load_model(file_name)
else:
self.model = Sequential([Dense(10, input_shape=(5,5), activation='relu'),
Dense(10, activation='relu'),
Dense(5, activation='relu'),
Dense(5, activation='relu'),
Flatten(),
Dense(1)])
self.model.compile(loss='mse',
optimizer=Adam(),
metrics=['mae', 'mse'])
training_length = 252*2
self.training_data = RollingWindow[TradeBar](training_length)
history = self.History[TradeBar](self.symbol, training_length, Resolution.Daily)
for trade_bar in history:
self.training_data.Add(trade_bar)
self.Train(self.my_training_method)
self.Train(self.DateRules.Every(DayOfWeek.Sunday), self.TimeRules.At(8, 0), self.my_training_method)
def get_features_and_labels(self, n_steps=5) -> Tuple[float, float]:
training_df = self.PandasConverter.GetDataFrame[TradeBar](list(self.training_data)[::-1])
daily_pct_change = training_df.pct_change().dropna()
features = []
labels = []
for i in range(len(daily_pct_change)-n_steps):
features.append(daily_pct_change.iloc[i:i+n_steps].values)
labels.append(daily_pct_change['close'].iloc[i+n_steps])
features = np.array(features)
labels = np.array(labels)
return features, labels
def my_training_method(self) -> None:
features, labels = self.get_features_and_labels()
self.model.fit(features, labels, epochs=5)
def OnData(self, slice: Slice) -> None:
if self.symbol in slice.Bars:
self.training_data.Add(slice.Bars[self.symbol])
features, _ = self.get_features_and_labels()
features = features[-1].reshape(1, 5, 5)
prediction = float(self.model.predict(features)[-1])
if prediction > 0:
self.SetHoldings(self.symbol, 1)
elif prediction < 0:
self.SetHoldings(self.symbol, -1)
def OnEndOfAlgorithm(self):
model_key = "model"
file_name = self.ObjectStore.GetFilePath(model_key)
#self.model.save(file_name)