So I was checking out Quantconnect's example demo code for XGBoost in Python from

(https://www.quantconnect.com/docs/v2/writing-algorithms/machine-learning/popular-libraries/xgboost#09-Clone-Example-Algorithm). 

However, I when I cloned the demo and tried running the backtest with the code unchanged, I keep on receiving the error 

"During the algorithm initialization, the following exception has occurred: Can't get attribute 'NeuralNetwork' on  at _getattribute".

I tried asking Mia AI but couldn't find a working solution. I'm pretty new to machine learning libraries so I'm stuck on this one.

# region imports
from AlgorithmImports import *
import xgboost as xgb
import joblib
# endregion
class XGBoostExampleAlgorithm(QCAlgorithm):
    
    def Initialize(self):
        self.SetStartDate(2022, 7, 4)
        self.SetEndDate(2022, 7, 8)
        self.SetCash(100000)
        self.symbol = self.AddEquity("SPY", Resolution.Daily).Symbol
        training_length = 252*2
        self.training_data = RollingWindow[float](training_length)
        history = self.History[TradeBar](self.symbol, training_length, Resolution.Daily)
        for trade_bar in history:
            self.training_data.Add(trade_bar.Close)
        if self.ObjectStore.ContainsKey("model"):
            file_name = self.ObjectStore.GetFilePath("model")
            self.model = joblib.load(file_name)
        else:
            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):
        close_prices = np.array(list(self.training_data)[::-1])
        df = (np.roll(close_prices, -1) - close_prices) * 0.5 + close_prices * 0.5
        df = df[:-1]
        features = []
        labels = []
        for i in range(len(df)-n_steps):
            features.append(df[i:i+n_steps])
            labels.append(df[i+n_steps])
        features = np.array(features)
        labels = np.array(labels)
        features = (features - features.mean()) / features.std()
        labels = (labels - labels.mean()) / labels.std()
        d_matrix = xgb.DMatrix(features, label=labels)
        return d_matrix
    def my_training_method(self):
        d_matrix = self.get_features_and_labels()
        params = {
            'booster': 'gbtree',
            'colsample_bynode': 0.8,
            'learning_rate': 0.1,
            'lambda': 0.1,
            'max_depth': 5,
            'num_parallel_tree': 100,
            'objective': 'reg:squarederror',
            'subsample': 0.8,
        }
        self.model = xgb.train(params, d_matrix, num_boost_round=2)
    def OnData(self, slice: Slice) -> None:
        if self.symbol in slice.Bars:
            self.training_data.Add(slice.Bars[self.symbol].Close)
        new_d_matrix = self.get_features_and_labels()
        prediction = self.model.predict(new_d_matrix)
        prediction = prediction.flatten()
        if float(prediction[-1]) > float(prediction[-2]):
            self.SetHoldings(self.symbol, 1)
        else:            
            self.SetHoldings(self.symbol, -1)
    def OnEndOfAlgorithm(self):
        model_key = "model"
        file_name = self.ObjectStore.GetFilePath(model_key)
        joblib.dump(self.model, file_name)
        self.ObjectStore.Save(model_key)
+ Expand
- Collapse